literature review of a construction project

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, generate accurate citations for free.

• Knowledge Base
• Methodology
• How to Write a Literature Review | Guide, Examples, & Templates

How to Write a Literature Review | Guide, Examples, & Templates

Published on January 2, 2023 by Shona McCombes .

What is a literature review? A literature review is a survey of scholarly sources on a specific topic. It provides an overview of current knowledge, allowing you to identify relevant theories, methods, and gaps in the existing research that you can later apply to your paper, thesis, or dissertation topic .

There are five key steps to writing a literature review:

• Search for relevant literature
• Evaluate sources
• Identify themes, debates, and gaps
• Outline the structure
• Write your literature review

A good literature review doesn’t just summarize sources—it analyzes, synthesizes , and critically evaluates to give a clear picture of the state of knowledge on the subject.

Table of contents

What is the purpose of a literature review, examples of literature reviews, step 1 – search for relevant literature, step 2 – evaluate and select sources, step 3 – identify themes, debates, and gaps, step 4 – outline your literature review’s structure, step 5 – write your literature review, free lecture slides, frequently asked questions, introduction.

• Quick Run-through
• Step 1 & 2

When you write a thesis , dissertation , or research paper , you will likely have to conduct a literature review to situate your research within existing knowledge. The literature review gives you a chance to:

• Demonstrate your familiarity with the topic and its scholarly context
• Develop a theoretical framework and methodology for your research
• Position your work in relation to other researchers and theorists
• Show how your research addresses a gap or contributes to a debate
• Evaluate the current state of research and demonstrate your knowledge of the scholarly debates around your topic.

Writing literature reviews is a particularly important skill if you want to apply for graduate school or pursue a career in research. We’ve written a step-by-step guide that you can follow below.

Writing literature reviews can be quite challenging! A good starting point could be to look at some examples, depending on what kind of literature review you’d like to write.

• Example literature review #1: “Why Do People Migrate? A Review of the Theoretical Literature” ( Theoretical literature review about the development of economic migration theory from the 1950s to today.)
• Example literature review #2: “Literature review as a research methodology: An overview and guidelines” ( Methodological literature review about interdisciplinary knowledge acquisition and production.)
• Example literature review #3: “The Use of Technology in English Language Learning: A Literature Review” ( Thematic literature review about the effects of technology on language acquisition.)
• Example literature review #4: “Learners’ Listening Comprehension Difficulties in English Language Learning: A Literature Review” ( Chronological literature review about how the concept of listening skills has changed over time.)

You can also check out our templates with literature review examples and sample outlines at the links below.

Download Word doc Download Google doc

What can proofreading do for your paper?

Scribbr editors not only correct grammar and spelling mistakes, but also strengthen your writing by making sure your paper is free of vague language, redundant words, and awkward phrasing.

See editing example

Before you begin searching for literature, you need a clearly defined topic .

If you are writing the literature review section of a dissertation or research paper, you will search for literature related to your research problem and questions .

Make a list of keywords

Start by creating a list of keywords related to your research question. Include each of the key concepts or variables you’re interested in, and list any synonyms and related terms. You can add to this list as you discover new keywords in the process of your literature search.

• Social media, Facebook, Instagram, Twitter, Snapchat, TikTok
• Body image, self-perception, self-esteem, mental health
• Generation Z, teenagers, adolescents, youth

Search for relevant sources

Use your keywords to begin searching for sources. Some useful databases to search for journals and articles include:

• Your university’s library catalogue
• Google Scholar
• Project Muse (humanities and social sciences)
• Medline (life sciences and biomedicine)
• EconLit (economics)
• Inspec (physics, engineering and computer science)

You can also use boolean operators to help narrow down your search.

Make sure to read the abstract to find out whether an article is relevant to your question. When you find a useful book or article, you can check the bibliography to find other relevant sources.

You likely won’t be able to read absolutely everything that has been written on your topic, so it will be necessary to evaluate which sources are most relevant to your research question.

For each publication, ask yourself:

• What question or problem is the author addressing?
• What are the key concepts and how are they defined?
• What are the key theories, models, and methods?
• Does the research use established frameworks or take an innovative approach?
• What are the results and conclusions of the study?
• How does the publication relate to other literature in the field? Does it confirm, add to, or challenge established knowledge?
• What are the strengths and weaknesses of the research?

Make sure the sources you use are credible , and make sure you read any landmark studies and major theories in your field of research.

You can use our template to summarize and evaluate sources you’re thinking about using. Click on either button below to download.

Take notes and cite your sources

As you read, you should also begin the writing process. Take notes that you can later incorporate into the text of your literature review.

It is important to keep track of your sources with citations to avoid plagiarism . It can be helpful to make an annotated bibliography , where you compile full citation information and write a paragraph of summary and analysis for each source. This helps you remember what you read and saves time later in the process.

To begin organizing your literature review’s argument and structure, be sure you understand the connections and relationships between the sources you’ve read. Based on your reading and notes, you can look for:

• Trends and patterns (in theory, method or results): do certain approaches become more or less popular over time?
• Themes: what questions or concepts recur across the literature?
• Debates, conflicts and contradictions: where do sources disagree?
• Pivotal publications: are there any influential theories or studies that changed the direction of the field?
• Gaps: what is missing from the literature? Are there weaknesses that need to be addressed?

This step will help you work out the structure of your literature review and (if applicable) show how your own research will contribute to existing knowledge.

• Most research has focused on young women.
• There is an increasing interest in the visual aspects of social media.
• But there is still a lack of robust research on highly visual platforms like Instagram and Snapchat—this is a gap that you could address in your own research.

There are various approaches to organizing the body of a literature review. Depending on the length of your literature review, you can combine several of these strategies (for example, your overall structure might be thematic, but each theme is discussed chronologically).

Chronological

The simplest approach is to trace the development of the topic over time. However, if you choose this strategy, be careful to avoid simply listing and summarizing sources in order.

Try to analyze patterns, turning points and key debates that have shaped the direction of the field. Give your interpretation of how and why certain developments occurred.

If you have found some recurring central themes, you can organize your literature review into subsections that address different aspects of the topic.

For example, if you are reviewing literature about inequalities in migrant health outcomes, key themes might include healthcare policy, language barriers, cultural attitudes, legal status, and economic access.

Methodological

If you draw your sources from different disciplines or fields that use a variety of research methods , you might want to compare the results and conclusions that emerge from different approaches. For example:

• Look at what results have emerged in qualitative versus quantitative research
• Discuss how the topic has been approached by empirical versus theoretical scholarship
• Divide the literature into sociological, historical, and cultural sources

Theoretical

A literature review is often the foundation for a theoretical framework . You can use it to discuss various theories, models, and definitions of key concepts.

You might argue for the relevance of a specific theoretical approach, or combine various theoretical concepts to create a framework for your research.

Like any other academic text , your literature review should have an introduction , a main body, and a conclusion . What you include in each depends on the objective of your literature review.

The introduction should clearly establish the focus and purpose of the literature review.

Depending on the length of your literature review, you might want to divide the body into subsections. You can use a subheading for each theme, time period, or methodological approach.

As you write, you can follow these tips:

• Summarize and synthesize: give an overview of the main points of each source and combine them into a coherent whole
• Analyze and interpret: don’t just paraphrase other researchers — add your own interpretations where possible, discussing the significance of findings in relation to the literature as a whole
• Critically evaluate: mention the strengths and weaknesses of your sources
• Write in well-structured paragraphs: use transition words and topic sentences to draw connections, comparisons and contrasts

In the conclusion, you should summarize the key findings you have taken from the literature and emphasize their significance.

When you’ve finished writing and revising your literature review, don’t forget to proofread thoroughly before submitting. Not a language expert? Check out Scribbr’s professional proofreading services !

This article has been adapted into lecture slides that you can use to teach your students about writing a literature review.

Scribbr slides are free to use, customize, and distribute for educational purposes.

Open Google Slides Download PowerPoint

A literature review is a survey of scholarly sources (such as books, journal articles, and theses) related to a specific topic or research question .

It is often written as part of a thesis, dissertation , or research paper , in order to situate your work in relation to existing knowledge.

There are several reasons to conduct a literature review at the beginning of a research project:

• To familiarize yourself with the current state of knowledge on your topic
• To ensure that you’re not just repeating what others have already done
• To identify gaps in knowledge and unresolved problems that your research can address
• To develop your theoretical framework and methodology
• To provide an overview of the key findings and debates on the topic

Writing the literature review shows your reader how your work relates to existing research and what new insights it will contribute.

The literature review usually comes near the beginning of your thesis or dissertation . After the introduction , it grounds your research in a scholarly field and leads directly to your theoretical framework or methodology .

A literature review is a survey of credible sources on a topic, often used in dissertations , theses, and research papers . Literature reviews give an overview of knowledge on a subject, helping you identify relevant theories and methods, as well as gaps in existing research. Literature reviews are set up similarly to other  academic texts , with an introduction , a main body, and a conclusion .

An  annotated bibliography is a list of  source references that has a short description (called an annotation ) for each of the sources. It is often assigned as part of the research process for a  paper .  

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the “Cite this Scribbr article” button to automatically add the citation to our free Citation Generator.

McCombes, S. (2023, January 02). How to Write a Literature Review | Guide, Examples, & Templates. Scribbr. Retrieved May 22, 2023, from https://www.scribbr.com/dissertation/literature-review/

Is this article helpful?

Shona McCombes

Other students also liked, what is a theoretical framework | guide to organizing, what is a research methodology | steps & tips, how to write a research proposal | examples & templates, what is your plagiarism score.

We apologize for the inconvenience...

To ensure we keep this website safe, please can you confirm you are a human by ticking the box below.

If you are unable to complete the above request please contact us using the below link, providing a screenshot of your experience.

https://ioppublishing.org/contacts/

Please solve this CAPTCHA to request unblock to the website

• Reference Manager
• Simple TEXT file

People also looked at

Specialty grand challenge article, grand challenges in construction management.

• Department of Architecture, Faculty of Engineering, University of Strathclyde, Glasgow, United Kingdom

This article is written for the launch of the specialty section on construction management at the Frontiers in Built Environment. This new specialty section opens an on-line platform for academics and practitioners in the subject field to share valuable experiences and findings from innovative research and development as well as practices, which focus on the management of people/workforce, product/production, and processes across built environment project stages, including development and construction, operation and maintenance, as well as demolition and redevelopment, under considerations on the dependability and productivity of construction management services. In this article, the writer presents his humble opinions limited from experiences from academic research and professional services around the world in the past three decades. The topics derived on grand challenges in construction management are gigantic in terms of their coverages, but may have huge impacts on professional development in both short and longer term. Discussions presented here on grand challenges in construction management consist of four parts to respectively focus on an initial cognitive framework of the construction management body of knowledge (CMBOK), intelligence pervasive construction management systems, interdisciplinary digital innovation, and solutions for performance enhancement in megaproject delivery. The research methodology that support the writer to describe the four grand challenges includes literature review, comparison study, site observation, and system architecture analysis and development. It was the writer's initial abductive reasoning to identify the four grand challenges in construction management through an extensive literature review, which was based on national and regional strategies for the construction industry from the world top economies. Some key references relating to these four major topics are collected to support discussions in this article. It is expected that this article could contribute to the debate as well as research and development in construction management in terms of continuous technical enhancements on project-oriented performance and value regardless the scope, the location, and the time associated and concerned. As the study was conducted through abductive reasoning, this article should have its limitation on the coverage to all grand challenges in construction management, and this should leave many unanswered questions for further exploratory research.

Introduction

Construction management (CM) is an important field of management practice oriented research into related issues at both the macro and micro sphere across the entire life cycle ( CIOB, 2010 ) of the built environment. The macro sphere of CM can generally cover all management related issues on the built environment across its life-cycle stages; for example, the industry wide statistics, analysis and projections on codes and standards, building information management, procurement and contracts, supply network, workforce productivity, and workplace health and safety, etc. at national, regional and/or international level. The micro sphere of CM, on the other hand, covers specific issues relating to project delivery at various work stages; for example, project specific study on feasibility, cost plan, design justification, process schedule, risk assessment, quality and traceability assurance, productivity analysis, post occupancy evaluation, and service level agreements, etc. The cross-stage process of CM makes it possible to conduct inter-connected professional services for clients to have maximum value from investment.

Since the principles of scientific management was put forward by Taylor (1911) , the theory has profound influence to the evolving theory of management science in over 10 decades, and there has been a significant theoretical evolution in the management world. As summarized by Jones and George (2016) , the evolution of management theories in the past century has demonstrated a trans-disciplinary development across five fundamental theories, including the scientific management theory, the administrative management theory, the behavioral management theory, the management science theory, and the organizational environment theory. This theoretical evolution in management science has eventually formed an entire body of knowledge (BOK) for management practice in various professional fields across industry sectors, and consequently it has continuously provided strong theoretical support to CM oriented research and practice.

The purpose of this article is to describe a recent research undertaken by the author to identify grand challenges in construction management in response to present national/regional strategies for the construction industry in world top economies, and to inform decision making on further research and development as well as learning and training with regard to the enhancement of dependability and productivity in construction management services. In order to justify the need for this research, the author has looked into the gigantic accumulation of related resources as collected in not only civil engineering databases at ASCE (2019) and ICE (2019) but also multidisciplinary databases on the Web of Science platform ( Clarivate, 2019 ), and the search term used is “challenges AND construction management.” It has been found that there is limited number of publications related to this topic, and it looks there is currently no publication dedicating to a discussion on grand challenges in CM focused research and development. From this point of view, this article has the opportunity to fill the gap in research into construction management.

This article is based on the author's observations through academic research and professional services in related areas around the world over the past three decades. Based on a further review on grand challenges and strategic priorities for the construction sector in six world's major economies, including United States, China, Japan, Germany, United Kingdom, and European Union, four grand challenges that reflect national/regional strategic priorities were eventually derived as significant ones. Table 1 is used to clarify the reflection of four perceived grand challenges in construction management to existing strategic proprieties in these world's major economies. It's the author's opinion that these four grand challenges are responsive to those national/regional strategies and therefore could be useful with further discussions to inform further research and development in construction management with regard to the pursuit of national/international leadership in this subject field.

Table 1 . Four topics on grand challenges in construction management.

According to this simplified independent response to the national/regional strategic priorities for the construction sector in the six world's major economies, this article aims to provide further discussions on the four grand challenges, and focuses on Frontiers of Research and Development in Construction Management with regard to the increasing need for service dependability and productivity in the development and operation of the built environment in both short and a relative longer term. This article therefore covers four topics on the four grand challenges in relation to three identified managerial domains on people/workforce, product/production, and processes, respectively, in the provision of CM services.

In developing the contents of this article, the four grand challenges are used for its structure to cover the following specific discussions:

• The grand challenge on the development and use of a theoretical CMBOK framework and its contents in accordance with research and practice accumulated across disciplines over long term in the past,

• Two grand challenges, in response to the needs for intelligent management systems and interdisciplinary digital innovations respectively, in order to improve the performance of constructions management services, and

• The grand challenge on technical enhancement for construction management in megaproject delivery in order to promote best practices through large-scale construction management services.

The relevance of these topics to the three management domains derived from an extensive review on five main management theories (see Figure 1 ) is further described in Table 1 . This qualitative analysis helped the author to make decision on topics to discuss grand challenges in construction management.

Figure 1 . Management domains of CMBOK interconnected with management theories.

This article is based on the author' recent research through the use of two methods, including extensive literature review and qualitative comparison study, while his long-term experiences and observations in academic research and professional practices were also incorporated. In addition, this article has been thoroughly improved according to a huge amount of insightful comments given by reviewers.

In this article, the author uses terms, including the dependability of construction management services and the dependable built environment, to incorporate the need for dependability ( Chen, 2017 ) at life-cycle stages of the built environment. According to the only three results from searching on Google as of 3 November 2018, the term dependable built environment was also used in practice by the Stonepay Construction in Canada. For the built environment, dependability ( BSI, 2014 ) can be regarded as a collective term for time-related quality characteristics with regard to the ability to perform as and when required throughout the life cycle of either a product or a service. It is the author's assumption that the incorporation of dependability with the technical term of built environment on the product side and construction management on the service side can facilitate an integrated measure that can cover engineering and management aspects connecting to dependability characteristics, which can include adaptability, availability, construability, durability, maintainability, recoverability, reliability, health and safety, security, supportability, and sustainability, etc. It is the author's opinion that the use of dependability for both built environment as the product and its life-cycle oriented services can effectively integrate various interconnected considerations and decision making on people/workforce, products/production, and processes in construction management for quantified quality assurance across its whole life cycle oriented services in the built environment. While numerous cases have shown that a lack of dependability may have significantly adverse impact through rewordings on productivity, it is important to give priority to dependability in the pursuit of productivity in construction management.

It is the author's expectation for this article to be useful for not only colleagues working on innovative research and development in the subject field of construction management, but also the specialty section on construction management at the Frontiers in Built Environment to be part of long-term leadership development in research and development for the construction management profession across the world. As the four described grand challenges were derived in response to current national/regional strategies for the construction sector in major economies, further research and development under the four grand challenges are also expected in order to timely and effectively support technical enhancements on both dependability and productivity in construction management services for the sustainable built environment.

Construction Management Body of Knowledge (CMBOK)

The first grand challenge to discuss is to establish a CMBOK, which can be useful for construction management oriented learning, practice, research and development in terms of both dependable professional services and continuous technical enhancements. Generally speaking, construction management is an elemental subject of the built environment discipline, and it is an essential professional service interactively connecting with other specific professions working inside the construction industry. It has extensive connections to other subject fields such as planning, design, and operation ( CIOB, 2010 ) within the built environment sector, in addition to resources and manufacturing, computing and programming, transportation and supply management, legislations and governances from other adjunct sectors to support its work procedure at various stages. For professional construction management services, there are mature work procedures such as the definitive UK model Plan of Work ( RIBA, 2013 ), the code of practice such as the CIOB (2014) Code of Practice for Project Management for Construction and Development, and regulations such as the Construction (Design and Management) Regulations 2015 ( HSE, 2015 ) in the United Kingdom. Construction management is therefore a dedicated profession that provides services focusing on construction to satisfy both project-wide and industry-wide needs for professional management within the built environment.

Management Domains

The BOK for a specific subject field is generally essential and useful for both practice toward excellence and research for innovation. As a good example, the body of knowledge for project management (PMBOK) ( PMI, 2017 ) has demonstrated the value of BOK in project management across industry sectors over the past two decades. It was originally published and continuously updated at the Project Management Institute ( PMI, 2017 ) to guide practice in project management, and eventually adopted by the International Organization for Standardization ( ISO, 2012 ) as an international standard for project management. In addition to professional guidance for general project management, PMI (2016) has continuously provided the extension to the PMBOK ® Guide for construction management since 2003, and this provides useful reference to form the CMBOK. The author would like to determine CMBOK as a set of structured descriptions about professional knowledge and underpinned techniques to sustain dependable quality services of construction management at both macro and micro scale in the built environment.

In connection with the evolution of theories and technologies in engineering and management, the technical scope of construction management has been enlarged, and the delivered service focuses on enhanced dependence and efficiency across life-cycle work stages ( CIOB, 2010 ). It is a matter of fact that an enormous amount of endeavors made by academics and practitioners in construction management worldwide is a huge contribution to form the CMBOK, although there is currently not a definitive framework, such as the PMBOK ( PMI, 2016 , 2017 ) and the Civil Engineering Body of Knowledge (CEBOK) ( ASCE, 2008 , 2019 ), for construction management in both project-wide and industry-wide scale. It is therefore a big task for further research into the cognitive framework of CMBOK and its elements and contents with regard to three identified cognitive domains, including people, products and processes (See Figure 1 ), to foster innovations in a more effective way for not only the dependence and efficiency of this professional service in practice, but also quality higher education ( Pellicer et al., 2013 ) and continuing professional development (CPD) ( Chen et al., 2006b ) for professionals and students, respectively.

For the three technical domains mentioned above on people/workforce, products/production, and processes in construction management, Figure 1 is used to clarify its origin by illustrating the connections between management theories ( Jones and George, 2016 ) to three identified main management domains that can be used to structure the construction management body of knowledge (CMBOK). It summarizes five representative toolkits derived from management theories that can support construction management on three managerial domains, which cover people/workforce, products/production, and processes. These managerial domains are identified through an extensive review into the five management theories with regard to fundamental issues that they are dealing with. As described by Oakland and Marosszeky (2017) and Kajima (2018) based on need for best practices, these domains are essential for total construction management (TCM) that enables a comprehensive use of all contemporary management theories to tackle issues on workforce, production, and processes across project life cycle in the built environment. In theory, TCM can be used as a term for the provision of all types of specific construction management services together under one contract, in comparison with construction management that refers to professional services in a generic term.

It is profoundly meaningful for the CM profession to have a cognitive framework of the body of professional knowledge, like the one ASCE and PMI have been working on for continuous professional development and further research. There are several critical reasons to justify its importance with regard to its value for different stakeholders involved in construction management. For stakeholders such as construction contractors, it could be a useful guide to take the initiative under the blue ocean strategy ( Kim and Mauborgne, 2004 ), which is defined as the simultaneous pursuit of differentiation and low cost to open up a new market space and create new demand, to develop outstanding expertise above horizontal competition. In other words, a bespoke BOK can ensure a sound development of expertise in providing professional services in one or more specific areas within an entire knowledge map. For clients who invest in the construction project, it is a useful benchmark for them to evaluate the performance of construction management at various project stages. In addition to its value for construction management practice, the cognitive framework of construction management body of knowledge can also be useful to inform higher education ( Arditi and Polat, 2010 ; Nguyen et al., 2017 ), professional training, as well as academic and professional research in terms of well-scoped depth and long-term continuous professional development. It is therefore considerate to develop a cognitive framework of BOK for the construction management profession.

Cognitive Domains

The structure of CMBOK, as one particular focus of this article to promote an initiative development for the whole construction management profession, can be outlined by using related cognitive domains, also called knowledge areas or domains, as structural elements of professional knowledge for the framework. For the structure of CMBOK, it therefore becomes critical to define its cognitive domains and their contents in order to establish such a framework of professional knowledge.

The definition of cognitive domains relies on a comprehensive coverage to both explicit and tacit knowledge ( Dalkir, 2017 ), which is required for quality services in specific professional areas such as civil engineering, construction management, and project management, respectively. One particular effort to identify all cognitive domains relating to construction management is to review possible ones adopted in existing BOKs such as CEBOK ( ASCE, 2008 , 2019 ) and PMBOK ( PMI, 2016 , 2017 ) and to make holistically consolidated connections to construction management profession. In the meantime, the review needs to incorporate a thorough consideration on work procedure such as the Plan of Work ( RIBA, 2013 ) with regard to interconnections among identified cognitive domains; moreover it is always necessary to incorporate learning from the best practice in CM. At the initial stage of CMBOK development, as described here, a technical review into the two existing BOKs was conducted through a comprehensive comparison between them and this comparison study can help to develop the CMBOK framework at initial stage.

The sources of knowledge are critical for the establishment and justification of a dependable cognitive framework of professional knowledge. Two reference knowledge frameworks including CEBOK ( ASCE, 2008 , 2019 ) and PMBOK for construction management ( PMI, 2016 ) are recommended for both the structure and contents development of CMBOK. Through the author's initial study on an outline structure of CMBOK, a preliminary framework of 18 cognitive domains under 3 management domains is put forward in Table 2 . This preliminary main structure was developed in comparison with the two highly relevant cognitive frameworks, i.e., CEBOK and PMBOK for CM, respectively, and through evidence based learning from various sources, including:

• Standard industrial classifications such as the UK Standard Industrial Classification of Economic Activities ( ONS, 2009 ),

• Databases run by both professional bodies, including the ASCE Civil Engineering Database and the ICE Virtual Library, and professional publishers, including Elsevier, Emerald, McGraw-Hill, Sage, Springer, Taylor & Francis, and Wiley, etc.,

• Books published in construction management by world-renowned scholars,

• Professional reports by top construction management organizations such as high-ranked main construction contractors ( EMAP, 2017 , 2018 ; ENR, 2018 ),

• Degree programmes accredited by professional bodies such as the American Council for Construction Education ( ACCE, 2017 ), the Chartered Institute of Building ( CIOB, 2018a ), and the Royal Institution of Chartered Surveyors ( RICS, 2018 ), and

• The author's extensive observations on site and online in relation to construction management for numerous projects worldwide.

Table 2 . Cognitive domains of professional BOK.

The 18 cognitive domains proposed as the preliminary main structure of CMBOK (see Table 2 ) are divided into three categories in terms of management domains, including People/Workforce, Product/Production, and Processes, which are consistent with the three generic management domains identified through the author's extensive review on five main management theories (see Figure 1 ). The incorporation of the three management domains into structuring CMBOK here is based on the following considerations:

• CM practices are well-guided and supported by generic management theories,

• The development of CM theories is based on both management science and professional practices,

• The three management domains can provide an extensive coverage to CMBOK related issues in not only professional practices, but also education, training, research and development, and

• The need for and potentials of further research and development to sustain dependable CM services for the sustainable built environment.

Details about how the preliminary main structure of CMBOK (see Table 2 ) was defined under these four considerations are describe below in response to the three management domains.

For the management domain on People/Workforce in the case of construction management, four cognitive domains are proposed here for the CMBOK framework, and these include the management of Enterprises in relation to construction organizations, the management of Knowledge to support construction practices, the management of Stakeholders involved in various construction operations, and the management of Workforce to undertake construction activities at both project and non-project scale. The choice and definitions of People/Workforce related cognitive domains for CMBOK are essentials for developing its technical details relating to the constitution and competence of workforce working on either building or infrastructure project at various stages where construction management services are in need.

For the management domain on Product/Production in the case of construction management, seven cognitive domains are proposed here for the CMBOK framework, and these cover the management of construction project at various work stages across the whole life to cover the management of Cost across project life cycle; the management of Design upon interconnected technical outcomes across three stages covering concept design, developed design, and technical design; the management of Engineering solutions during construction, maintenance, repair, refurbishment, decommissioning and demolition; the management of Facilities in terms of relevant professional services at operation stage; the management of Plant at both construction and operation stage, the management of Quality of built assets in construction, maintenance, repair, refurbishment; the management of the use of Resources in relation to key considerations on quality, quantity, and embodied energy, etc. The choice and definitions of Product/Production related cognitive domains for CMBOK are essentials for developing its technical details relating to the physical products and production of buildings and infrastructures that construction management profession can support.

For the management domain of Processes in the case of construction management, seven cognitive domains are proposed for the CMBOK framework cover the management of Communications, the management of Supply network, the use of Management systems for various purposes on either individual issues such as environment, health, quality, safety, and welfare, or all tasks of the entire project; the management of Procurement through sound procedure and effective contract control; the management of Risk and Time at various work stages and scopes across project life cycle; and the management of Changes and Emergency whenever unexpected issues may occur in the whole project life. The choice and definitions of Processes related cognitive domains for CMBOK are essential for developing its technical details relating to a whole range of processes of making the built environment built through construction management services.

In addition to the main structure of CMBOK framework, there is another aspect constituting the entire challenge of developing CEBOK, for which the substructure of the main knowledge framework under the 18 cognitive domains described above needs to be defined. It is the author's consideration that the definition of the substructure system also relies on all knowledge sources identified for the proposed preliminary main structure of CMBOK.

A further review into three key sources of information was conducted to detect whether the 18 cognitive domains proposed as the preliminary main structure of CMBOK could be recognized at a satisfactory level. Table 3 presents a comparison from this review, in support of three sets of key references selected from CIOB, British Standards Institution (BSI), and ISO, respectively.

Table 3 . Recognition of cognitive domains proposed for CMBOK.

The three sets of key references (see Table 3 ) selected for this comparison study include:

• CIOB (2014) Code of practice for project management for construction and development, in harness with several other related publications including the Design Manager's Handbook ( Eynon, 2013 ), CIOB (2015) Time and Cost Management Contract suite, CIOB (2018b) report on Improving Quality in the Built Environment, CIOB (2018c) Guide to Good Practice in the Management of Time in Major Projects, and CIOB (2018d) course on Accident Investigation and Root Cause Analysis.

• BSI (2006) Guide to project management in the construction industry, and

• ISO (2017a) standards for construction, in harness with several other related ISO standards with regard to improving the performance of construction management services, for which relevant issues on quality, productivity, and sustainability, etc. ( Bernold and AbouRizk, 2010 ) need to be dealt with.

It looks from this comparison study that all 18 cognitive domains proposed to structure the CMBOK are well-covered by three sets of key references in terms of various issues in construction management practice. This coverage indicates a good justification associated with the preliminary main structure of CMBOK proposed here. Therefore, the CMBOK framework proposed in Table 2 is recommended for further use to fulfill the gap on the shortage of such a BOK currently available for construction management at various scales in terms of practices, education and training, and research and development.

For CEBOB, in addition to its structure system, it is a continued process supported by professionals to add contents into this structured knowledge system. The contents of CEBOK under an established knowledge structure are gigantic in terms of the amount of knowledge accumulated from long-term practice and research in construction management across industry sectors worldwide. From this point of view, it is ideal to have an international organization to lead the development and maintenance of CMBOK, which can be widely recognized and used for construction management.

Intelligent Construction Management System

The second grand challenge to discuss is the establishment and utilization of intelligence pervasive construction management systems to thoroughly support project-based practices at workplaces across work stages. From the author's point of view, an intelligence pervasive management system is a computer aided management system that incorporates the use of experts' knowledge and artificial intelligence (AI) based on the collection and process of relevant data and information from the real world. With regard to the importance of Industry 4.0, the construction industry is now under rapid transformations to adopt digital technologies that enable innovations in products and processes across the supply chain network, and it has become inevitable to incorporate new concepts driven by digital technologies into traditional management systems such as management information system (MIS) and enterprise management system (EMS) for construction management.

It has been always an inspiring learning experience for the author to look into progresses on research and development in the theory and solutions of AI since he put forward the concept of intelligent methods for construction engineering and management ( Chen and Xu, 1996 ; Xu and Chen, 1997 ). In connection with the fast development of information and communication technologies (ICT) since 1990s, recent research and development in applied AI solutions for enhanced practice in construction management has shown insightful perspectives and effective progressions. For example:

• The use of artificial neural network (ANN) ( Waziri et al., 2017 ) across various predication related issues in construction management,

• The use of knowledge sustained analytic network process (ANP) ( Chen, 2007 ) to evaluate options for informed decision making in construction management, and

• The integration with automation technology to deploy single-task and multi-task robots ( Skibniewski, 1988 ; Castro-Lacouture et al., 2007 ; Bock and Linner, 2016 ; Black and Pettitt, 2018 ) in construction projects.

It has been further emphasized by Blanco et al. (2018) recently regarding the adoption of applied AI in construction management in terms of project planning optimization, constructability justification, materials and inventory management, and risk and safety management; and these applications all demand a systems-based approach ( Briesemeister, 2018 ) to improve the quality and productivity of construction management. It looks that an integrative use of data, information and knowledge (DIK) ( Allee, 1997 ; Walker, 2016 ) is now just in front of the construction management profession, while the DIK set can be collected from either construction projects or construction professionals in dealing with specific issues such as those listed in Table 2 in a more accurate and efficient manner.

In response to the increasing need for comprehensive use for DIK in construction management, a new concept about intelligent construction management system (iCMS) is described below in terms of its concept, purpose and value, conceptual model, and two tier systems. Hopefully this description could be useful for further considerations, discussions, and research and development in this area.

An iCMS is a construction management system aided by AI techniques that can trigger human/rational learning, thinking and acting ( Russell and Norvig, 2010 ) in connection to integrated DIK clusters and their elemental sets (see Table 4 ), which are specifically structured on a spectrum of expected helpfulness to assist the use of human intelligence at an enhanced consistent level in CM practice.

Table 4 . DIK clusters and their elemental sets for CM.

The entire DIK set need to be carefully collected with continuous updating manually and/or automatically from various sources under the CMBOK framework, and this ensures the system performs effective practical support connecting with experts' wisdom, which can be derived from computing processes at different scopes covering project/programme level, enterprise/group level, and local/regional level, etc. in a high efficient manner toward excellent professional performance. The iCMS needs to be well-connected with DIK sources covering the management team and a range of databases and knowledge bases to ensure dependable support to construction management practice.

Purpose and Value

The purpose of incorporating an iCMS in practice is to equip the project-oriented management team with dependable technical toolkits for better CM service delivery. The iCMS toolkit aims to facilitate the integrative use of not only expertise and knowledge accumulated from the past practice, but also data and information collected from the on-going project in real time. From the best practice point of view, specific DIK sets are required to deal with critical problems relating to the management of people/workforce, product/production, and processes across project stages.

The value of iCMS for construction management practice is its function to precisely perform calculated decision making support through the effective and efficient use of DIK. This calculation can be made through co-computing processes over a gigantic body of chaotic interactions among workforce, production, and processes within the dynamic project environment across work stages. Therefore, the iCMS is to provide a systematic approach to better using DIK that quantify chaotic interactions in construction projects. In terms of the need for continuous excellent performance across construction management teams, the iCMS is to run through computing systems as an essential smart assistant.

Conceptual Model

A conceptual model of iCMS is illustrated in Figure 2 . The intelligence expected from such a system for construction management can be achieved in its capacity on the integrative use of relevant DIK through a formal work procedure based on individual management systems such as environmental management system ( Chen and Li, 2006 ), health and safety management system ( Griffith, 2010 ), knowledge management system ( Anumba et al., 2005 ), quality management system ( Thorpe and Sumner, 2004 ; Rumane, 2018 ), and project management system ( Chen, 2018 ), etc., which can be dynamically connected inside individual project-oriented computer systems in connections with building information models (BIM) for continued accurate inputs and useful outcomes.

Figure 2 . A conceptual model of iCMS.

This conceptual model illustrated in Figure 2 consists of four functional entities that are connected through DIK and/or supporting procedures, and these entities include CMBOK, CM practices, intelligent CM systems, and AI technologies and other digital technologies.

A two-way connection between entity CMBOK and entity CM Practices is set up to describe their relationship, which covers the two aspects, including:

• CMBOK as a collection of well-structured professional knowledge is to accumulate relevant DIK from CM practices, and the inputs under a given CMBOK structure are collected from CM practices, which covers all individual practices on construction management; and

• CMBOK would influence/support CM practices at various scales through purpose driven application/reuse and/or continuous learning/training based on its classified collections.

For the entity of intelligent CM systems, it has two sub-entities forming an entire tier system, which is described in the next section. This entity is integrated with three other entities in the following ways:

• CMBOK provides the structure and contents of DIK for individual intelligent CM systems,

• CM Practices can be assisted/supported through the use of individual intelligent CM systems, and

• AI technologies and other digital technologies are adopted to support individual intelligent CM systems with expected functions.

It is anticipated that this conceptual model can be useful to clarify the concept of iCMS and its research and development toward intelligent construction management.

Tier Systems

Exploratory research facing grand challenge on intelligence systems for construction management can be conducted through two stages, including the initial stage on sub-systems, i.e., individual management systems, and the secondary stage on an entire iCMS system, i.e., an integration of all its elemental sub-systems. They are called Tier 1 systems and Tier 2 systems, respectively, here based on different functions that individual systems can provide. Generally speaking, Tier 1 systems are sub-sets of Tier 2 systems. The research and development of the two types of systems highly rely on thorough system analysis and design, reliable inputs, and effective use of DIK within the system to support usages in construction management upon various issues and situations. A brief description about the two types of systems is given below for discussion toward further actions in research and development.

Tier 1 systems: Individual intelligent management systems. These systems are designed, developed and implemented for construction management in specific areas as listed in Table 2 . For example, the system for purposes on managing people/workforce, product/production, and processes, respectively, could be:

• An intelligent EMS for managing people/workforce involved in construction projects or project enterprise at various levels in an organization of either clients' or contractors',

• An intelligent cost/quality management system for managing product/production targeted by either an organization of clients' through the investment into their capital projects, or an organization of contractors' through the delivery of entrusted construction projects, and

• An intelligent information and communication management system for managing processes deployed within an organizational environment of construction projects on either clients' or contractors' side.

The intelligent functionality and capability of these individual management systems need to be casted by incorporating a number of interconnected inputs on DIK under the CMBOK framework. There have been initiatives in research and development in Tier 1 systems. For example, Grahovac and Devedzic (2010) presented an expert system to support decision making in cost management; although it was not for construction cost management, their experiment has indicated a promising application of intelligent cost management system in construction, and such an application can be hybrid by incorporating the use of other relevant techniques such as the research that Chou et al. (2015) have conducted by interactively using Genetic Algorithm (GA), ANN, and Case-based Reasoning (CBR) to predict project award price, and this hybrid use of intelligent methods can be further integrated with BIM ( Allplan, 2018 ) for intelligent cost management at various project stages. By learning lessons from other sectors, such as the healthcare sector where it was found that an intelligent cost management system, for example, can leverage relevant data to swiftly identify opportunities so as to achieve savings of $10 per member per month (PMPM) with a conservative calculation ( MedSolutions, 2013 ), it can be anticipated with a positive sensation that the adoption of individual intelligent management systems in construction can significantly improve construction management on various aspects.

According to the concept of iCMS, the use of well-developed practical solutions of AI is essential for Tier 1 systems. In addition to the example given above, it is obvious through literature review that initiatives in research and development in Tier 1 systems have widely developed through the use of AI techniques in natural language processing, knowledge representation, automated reasoning, machine learning, computer vision, and robotics ( Russell and Norvig, 2010 ) for construction management. The following are good examples for Tier 1 systems:

• A natural language processing system to extract precursors and outcomes from unstructured injury reports ( Tixier et al., 2016 ),

• A knowledge extraction and representation system for narrative analysis in the construction industry ( Yeung et al., 2014 ),

• An expert system for crack diagnosis in cast-in-place reinforced concrete structures ( Chen et al., 1999 ),

• A construction noise prediction model based on case-based reasoning in the preconstruction phase ( Kwon et al., 2017 ),

• A machine-learning model for estimating construction costs ( Rafiei and Adeli, 2018 ),

• A computer vision-based workforce activity assessment in construction ( Luo et al., 2018 ),

• A robotic approach to construction waste recycling ( Wang et al., 2019 ).

The adoptions of individual AI techniques in these exploratory research and development have demonstrated the effectiveness of Tier 1 systems to support construction management, and these systems also shows potentials for integration to form a more powerful iCMS toward Tier 2 systems.

Tier 2 systems: Integrated intelligent management system. In principle, an integration of several individual Tier 1 systems can be further developed by using groupware (collaborative software) technology to form collaboration systems ( Nunamaker et al., 2014 ), and this integration is expected to enable more functional intelligent construction management system. From a conceptual point of view, the integration of selected Tier 1 systems can yield one Tier 2 system that can support construction management activities in a transdisciplinary way in multiple functional areas covered by Tier 1 systems, respectively. There are different levels of system integrations, for example, it can be either an integration of several individual Tier 1 systems for project-specific intelligent management based on individual contracts with clients, or the integration of all individual types of Tier 1 systems to form all-round intelligent management for general use by main contractors. In other words, for a bespoke iCMS, the scope of system integration may reflect the scope of construction management contract for which the system is expected to work for in specific projects. On the other hand, there is another type of Tier 2 systems, for example, the i-Construction system ( STI, 2017b ), which is developed as an entire system with sub-systems to perform designed functions for generic use to support CM activities across all types of projects. In comparison with groupware integration that satisfy specific needs for construction management at suitable workplaces in the project environment, the new development of an entire intelligent system faces more challenges in terms of the incorporation of complex sub-systems and human intelligence with thorough connections to CMBOK and DIK in a general way to make enable all necessary functions for construction management.

There are specific issues to be dealt with in the research and development for iCMS. For example, it is essential to not only sufficiently describe DIK and sources for collection, but also accurately collect and effectively use them in order to make the system useful. By learning lessons from construction management practice in relation to the use of computer systems such as a BIM system, for which a comprehensive collection of relevant data and information from construction stage may not be typically well-functioned inside the system and consequently leave data gaps less filled across design, construction and operation stage. Therefore, a set of essential questions and answers under systematic considerations connecting to multiple disciplines within construction projects may help system design, development and usage.

Digital Innovations

The third grand challenge to discuss is the digital innovation throughout its project-oriented work procedure. The need for and demand on innovative reengineering ( Love and Li, 1998 ) in construction management has progressively emerged and increased through the requirement and provision of dependable management services in the construction sector. In the meantime, the availability of advanced technical solutions in sciences and technologies has greatly supported (with huge potentials) the technical enhancement of construction management by incorporating interdisciplinary digital innovations. The discussion here focuses on adopting advanced technologies in relation to the theories and solutions of informatics and automation for further development in construction management.

Construction Informatics

Construction informatics is the interdisciplinary science of the application of advanced computing and ICT to construction engineering and management. The adoption of technical solutions based on ICT driven research and development has been significantly increasing in construction management over the past several decades. For example, technologies such as artificial intelligence (AI), artificial reality (AR), which is the author's term to cover virtual reality (VR), augmented reality (AR), mixed reality (MR), BIM; geographic information systems (GIS), global positioning system (GPS), management information system (MIS), and process simulation (PS) etc. have all been applied in research and development for practice enhancement in management on people/workforce, products/production and processes in building and infrastructure projects. Table 5 makes a summary of exemplar research and development initiatives focused on adopting various digital innovations for construction management through research and development. These initiatives were identified from not only relevant strategies and practices by top international construction contractors, including Balfour Beatty, Bechtel, Kajima, Laing O'Rourke, and Skanska, but also some representative academic research published in China, European Union, UK, and USA.

Table 5 . Exemplar R&D initiatives on construction informatics.

These technical innovations have demonstrated anticipated results such as significantly improved work efficiency via multidisciplinary construction information management although there are still potentials for further research and development in terms of system functionality and interoperability. On the other hand, it is also necessary for interdisciplinary digital innovation to incorporate useful ideas from various professions relating to project management. For example, it is an unresolved question regarding how the incorporation of economics, psychology and sociology ( Harty, 2005 ; Winch, 2009 ; Mascia, 2012 ; Walker, 2015 ) focusing on the performance of individuals and project team into ICT systems for construction management can make further technical enhancement. Further interdisciplinary digital innovations through the use of theory and techniques in construction informatics may therefore need to consider both tangible and intangible aspects within project environment and related scenarios.

From a research and development point of view, there are a number of areas in interdisciplinary digital innovation for enhanced practice and learning in construction management, and these areas can be connected to the three identified domains (see Figure 1 ) of construction management with regard to innovations in:

• People/Workforce management. For example, DIK collection, analysis, and integrative usage,

• Product/Production management. For example, Performance (on Cost, Quality, and Schedule, etc.) modeling, monitoring and assessment, and

• Processes management. For example, Process (for Construction Engineering and Management) reengineering design and coordinated implementation.

In the area of applied AI with regard to the need for alternative research approaches ( AlSehaimi et al., 2013 ) as well as the provision of useful technical solutions, the deep learning technology has indicated a promising future for adoption in order to improve the productivity of construction management professionals, and the technical enhancement needs to be pursued toward accuracies in management in terms of interconnected working efficiency within networked teams to effectively tackle persistent problems relating to major issues on cost, quality and time in project delivery.

Construction Automation

Construction automation is regarded as the use of automatic equipment or machines in construction. The automation technology has been increasingly studied and adopted in the construction sector ( Bock, 2015 ; Chen et al., 2018a ; Hawksworth et al., 2018 ) to improve not only the quality of products but also the efficiency of processes as well as resources use. For construction management, new industrialized construction engineering solutions have been introduced to practices, and these include:

• Design for Manufacturing and Assembly (DfMA) ( BCA, 2016 ),

• Design for deconstruction/disassembly (DfD) ( Rios et al., 2015 ),

• Digital production systems such as 3D printing ( Bechtel, 2018 ; De Laubier et al., 2018 ; García de Soto et al., 2018 ; Skanska, 2018 ),

• Digital data collection and construction verification systems such as drones ( Skanska, 2018 ), and 3D scanning ( Faro, 2019 ),

• Autonomous construction equipment ( Black and Pettitt, 2018 ) and vehicles ( Bechtel, 2018 ), and

• Construction site automation ( Kajima, 2018 ).

These industry led initiatives have shown progressive achievements and new opportunities for lean construction ( Alarcón, 1997 ) toward a wide range of technical enhancements at interdisciplinary scale that integrates construction engineering and construction management across the supply network. For both research and practice to be well-prepared for this disruptive innovation in the construction sector, it is important to learn lessons from the manufacture industry where the automation technology and industrialized automation systems have been very well-developed and widely used in a process of continuous innovations over the past many decades, and this can significantly change the landscape of construction management in terms of professional competence and resources efficiency oriented performance toward the best practice. The adoption of automatic systems in construction projects brings the opportunity for professionals to reconstruct ( Morris, 2013 ) management procedure and associated activities and systems.

For interdisciplinary digital innovation in construction management, it has been learnt from past research and development that both decent deep learning from and efficient DIK sharing in multiple disciplinary areas are necessary and beneficial for a dedicated construction management team; in addition, a fast paced innovation process driven by well-organized collaboration under the Blue Ocean strategy ( Kim and Mauborgne, 2004 ) can be achieved through team-based multi-disciplinary learning, which can foster as well as enable powerful integrations of new digital DIK compounds into existing construction management. For example, the Asta Powerproject ( Elecosoft, 2018 ), which was originally developed for construction planners to develop and maintain project schedules by using the critical path method (CPM) like other same type of software packages for managing construction schedule, has now evolved to be a powerful 4D planning solution by linking project plans made by construction planners to 3D models provided by design engineers so as to match the need for adopting BIM in construction management. The multidisciplinary connection realized in this software package has demonstrated the advantage of further research and development in leading the way forwards. A continuous leadership in research and development is therefore inevitable by providing new solutions on not only Construction Informatics but also Construction Automation, and those innovative digital solution can satisfy new needs for digitalization across various interconnected disciplines within the construction project environment to serve more (wider and deeper) in required management services.

Megaproject Delivery

The fourth grand challenge to discuss is the delivery of megaproject with regard to satisfactory performance toward targets on life-cycle cost, quality of the built environment, resources use, and staged schedule, etc. A megaproject is a large-scale capital project typically costing more than US $1 billion ( PricewaterhouseCoopers, 2014 ), and it can be considered as a subset of major projects which have a wide scope of project costing above US100m for example. Megaproject has its uniqueness in terms of their significant and substantial impacts on social, technical, economic, environmental and political (STEEP) spheres. Generally speaking, these impacts are related to the big set of designed functions and service capacities under the purpose to transform public services and to deliver a robust infrastructure system to serve people and/or the nature in both short and longer term. There have been a huge amount of lessons learnt from past practices on megaproject development and operation across the world. One of the significant and persistent problems in megaproject delivery is the overruns on cost and time against estimated budget and schedule, and this has been widely recognized as specific megaproject risks ( Flyvbjerg et al., 2003 ) and the need for mature risk management ( Jia et al., 2013 ). It is therefore a grand challenge for further research and development to explore better technical solutions that are capable to support significant performance improvement on construction management in megaproject delivery. From this point of view, the description here about the grand challenge in megaproject delivery focuses on two relevant issues, including megaproject knowledge, and knowledge-driven solutions.

Megaproject Knowledge

It is evident through the author's extensive literature review and observations from both research and practices that a new research frontier in megaproject management with regard to scope, contents and potentials in relation to challenges, methodologies and solutions has emerged from a series of initiatives in focused research and practices. Table 6 is used to summarize the author's literature review in relation to megaproject knowledge, and it covers a range of topics about the performance of megaproject delivery. According to this summary, publications from research and practices around the world, especially from world's top economies, have accumulated a quick increase of megaproject knowledge in the past decade, and can strongly foster and support further research and development being embarked on this new frontier for research into megaproject delivery. As summarized in Table 6 , accumulated knowledge for megaproject delivery can be classified in the following four categories of publications to form a new landscape of dedicated research:

• Books on various issues relating to megaproject sustainability with regard to STEEP issues;

• Books on methodological issues about successful megaproject delivery in relation to Decision making, Project finance, Project governance, Project leadership, Multi-stakeholder lessons learned, Project procurement, Management solutions, and Management theories;

• Themed collection of research articles in 12 international journals; and

• Practitioners' learning legacy on megaproject delivery.

Table 6 . Classified publications on megaproject delivery.

The purpose of Table 6 is to develop a knowledge structure in terms of important issues relevant to performance improvement in megaproject delivery. Knowledge materials that were used to establish this structure include books, themed issues of journals, and practitioners' learning legacy. With regard to other types of relevant publications such as numerous individual articles published in journals and newspapers, in addition to case oriented study, a further review and collection can be conducted to verify and improve this structure, to enrich the collection of knowledge materials, and to incorporate megaproject knowledge into CMBOK. As it is always important to use DIK in both effective and efficient way in construction management practice, one challenge in front of further research and development is inevitably to focus on knowledge-driven solutions, which are expected to provide well-informed decision making support in areas relating to construction management. For megaproject, due to the scale and complexity of management, the value and power of structured knowledge reuse are expected and in need for proofs from future practices.

Knowledge-Driven Solutions

Knowledge-driven solutions refer to techniques and tools that can facilitate an effective and efficient use of knowledge in dealing with questions or problems in management practices. For megaproject delivery, it is assumed that one possible solution to effectively tackle the problem on overruns within an enlarged project scale, which is probably beyond the one where traditional theories, techniques and processes can work well for small-size projects, is to deploy significant technical enhancement through the development and enablement of re-engineering-led leadership and capability on various aspects of construction management. In addition to the adoption of digitalized tools to increase productivity at work stages, knowledge-driven solutions that can facilitate a thorough use of DIK in construction management are reckoned to improve the quality of professional services and expected outcomes with regard to contract, legislation, and professional code, etc.; and to increase the momentum that the use of DIK can add into the culture and impacts of construction management enterprises.

Figure 3 is used here as an example to illustrate how knowledge-driven solutions can be crafted for decision making support in a DIK immersive environment of megaproject management. It aims to establish possible connections among five solutions, including:

• Information models such as BIM and CIM to accumulate DIK from stakeholders and site of the megaproject,

• Megaproject case base to store DIK from current and past megaprojects,

• Analytic network process to reuse DIK to identify priorities among project related options,

• Artificial neural network to reuse DIK to derive conclusions for individual project related goals, and

• System dynamics to reuse DIK to predicate possibilities upon specific project related issues.

Figure 3 . Knowledge-driven solutions for megaproject management.

This figure also provides indications about all connections across exemplary solutions to clarify how stakeholders and experts can work together within DIK immersive project environment where various ways of using knowledge are made available and integrated toward better-performed services in construction management.

An example of research into the use of knowledge-driven solutions to deal with the big issue on cost and time overruns in megaproject delivery is the experimental case studies conducted by Boateng et al. (2017) who explored the integrative use of ANP ( Saaty, 1996 ) and system dynamics (SD) ( Sterman, 1992 ) to predict cost and time overruns in the Edinburgh Tram Network project, which has a total capital cost of approximately £776 million ( Cardownie, 2017 ). The outcome from their experiment provided a promising accuracy above 80% in prediction on cost and time overruns, and the simulation method can be interactively used in project management to achieve optimized delivery processes across stages by timely adjusting errors that may cause problems. While it is necessary to reinforce structural and governance arrangements ( Croft et al., 2016 ) in megaproject delivery, this research initiative and outcome is making a suggestion on the necessity to incorporate disruptive technical solutions in megaproject delivery, and has attracted practitioners' interest. As described by Davies et al. (2009) , innovation through process-oriented systems integration by incorporating lean thinking ( Womack and Jones, 1996 ) can significantly improve the performance of megaproject delivery. It is therefore anticipated that disruptive innovations such as the knowledge-driven systems through introducing the usages of new theories and technologies into megaproject management can effectively tackle the persistent problem such as the overruns on budget and schedule, and there is an array of value proposition canvases ( Osterwalder et al., 2014 ) for reconstructing project management ( Morris, 2013 ) toward proactive results through further practice-oriented exploratory research.

Regarding the challenge on megaproject delivery, as it is defined in this article as the one for best practices for which methods described under, the first three challenges need to be used in an integrative way.

Conclusions

This article provides brief discussions on four grand challenges connecting to further research and development in the subject field of construction management with regard to three technical domains on people/workforce, products/production and processes, respectively. In addition to an extensive review into current national/regional strategies for the construction sector in major economies, the four grand challenges were identified through the author's observations on academic research and professional practices in relation to the body of professional knowledge, intelligent management systems, interdisciplinary digital innovation, and megaproject delivery. It is the author's expectation that discussions presented here on the four grand challenges could be useful to inform further research and development at the Frontiers of Construction Management for the dependable built environment.

Contributions

The main contribution of this article is to provide an initial description about four identified grand challenges in construction management together with regard to further research and development under practice oriented strategies at various scales. In order to detail the four grand challenges in relation to leadership development and capability growth for the goals on both dependability and productivity in the provision of construction management services, this article has attempted to clarify four related issues for the advancement of construction management profession, and these include:

• A preliminary structure of cognitive domains of CMBOK,

• The definition with a conceptual model of iCMS,

• A research and development strategy oriented review to further digital innovations under the three knowledge domains of CM, and

• A detailed summary on the structure and tools of using knowledge materials to inform further research and practices for leadership development as well as capability growth in megaproject delivery.

The structure adopted to derive the four grand challenges is generic and could be useful for further discussions on other grand challenges.

Framework and Advantages

The connections among research and development activates across the four grand challenges can form a generic framework to advance the construction management profession. These connections need to include the use of the proposed CMBOK framework as a guideline to develop iCMS, make and perform constant interdisciplinary digital innovations, and conduct improved megaproject management. In return, continuous outcomes and usages of new technical solutions from research and development in iCMS and interdisciplinary digital innovations, as well as megaproject management practice can provide new compounds of CMBOK. The reason for setting up these coherent connections is that it is an essential requirement for such intelligent systems as well as interdisciplinary digital innovations to be both applicable and useful in construction management practices, including those in megaproject delivery. It is therefore an important task for construction management professionals to specify decent connections to CMBOK when a new technical solution is to be developed and adopted. The advantages of using CMBOK framework to guide and connect research and development activities in construction management can be recognized from various sides, and these include standardizations in not only research and development but also professional services, the enrichment of professional knowledge, constant CPD, and extensive interdisciplinary collaborations, etc.

Limitations

This article is based on the author's literature review and observations in construction management, and these were used in discussions on the four grand challenges through qualitative analysis. Although reviewers' comments have hugely helped him to conduct further research in order to illustrate a more vivid landscape with regard to the four identified grand challenges in construction management, there is limited time for him to make the description comprehensive with more details in both qualitative and quantitative way. Further research is inevitably necessary so as to not only describe the four grand challenges in more details, but also identify more technical challenges inside different scopes so as to pursue excellent professional services in construction management.

Climate change and variability has been giving challenges to construction management professionals around the world over the past century ( Stehr and von Storch, 2000 ). In the pursuit of dependability and productivity of professional services in the life cycle of the built environment, professionals need to have thorough considerations upon constant interactions of complex variables between the built environment and the social environment within the natural environment in both short and longer term. While the four grand challenges discussed in this article were derived from a literature review on current national/regional strategies for the construction industry in world top economies, the author would like to recommend further research and development for long-term competence enhancement in areas relating to the four grand challenges, and these advances include:

• A national/regional CMBOK to support the provision of construction management services in the ear of Industry 4.0, and it can be used to develop relevant standards for construction management,

• Knowledge-driven solutions for thorough use of DIK within an immersive environment for construction management, and

• Techniques and tools for construction management incorporating with site automation, and

• Theories, techniques and tools to tackle overrun problems in megaproject management.

About the Author

The author is specialty chief editor for the Construction Management section of Frontiers in Built Environment. He has relevant experiences accumulated from academic and professional services worldwide since later 1980s. He has engaged in more than 50 funded research projects totalling over £5m from research councils and industry partners in UK and internationally. In collaborations with colleagues worldwide, he has made contributions to more than 200 publications, including more than 50 publications collected on the Web of Science (Researcher ID C-1587-2010), in addition to some other publications collected at ORCID 0000-0003-0212-1140 and Google Scholars. He is member of the management committee of COST Action TU1003 (2011-2015) for research into the effective design and delivery of megaprojects in the European Union. He serves as member at several relevant technical committees, including committees on Airport Planning and Operations, and the CEBOK, respectively, at ASCE, and committees on Facilities Management, and Project, Programme and Portfolio Management, respectively, at BSI.

Author Contributions

The author confirms being the sole contributor of this work and has approved it for publication.

Conflict of Interest Statement

The author declares that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Acknowledgments

This article is prepared for the launch of the specialty section on construction management at the international open-access journal of Frontiers in Built Environment. The author would like to thank Professor Izuru Takewaki, the Chief Editor of the Frontiers in Built Environment for huge support in developing the specialty section on Construction Management. Ruth Miller, Journal Development Manager; Emily Young, and Sarah Yardley, Journal Development Specialists; and other colleagues at Frontiers have all provided strong support and thorough help in the establishment of this specialty section and its research topics. Special thanks to Nicholas Fraser, former Journal Development Manager at Frontiers, for the development of the new specialty section at initial stage. The author would also like to thank all colleagues on the editorial board as either Associate Editor or Review Editor for their strong support and contributions to the specialty section on Construction Management. The author would like to express special thanks to Dr. Conor Mooney at the Council of Europe Development Bank for his strong support as Associate Editor to the establishment of this specialty section at Frontiers in Built Environment.

The author is deeply grateful to his mentors and colleagues from both academia and industry around the world for their help and giving him great opportunities to learn from them more or less in the past three decades. His learning experience with them are extensive, useful, and inspiring.

The unique opportunity that colleagues at Frontiers give to the author for this article focusing on grand challenges in construction management is huge inspirational for him to rethink about the research and development of construction management for both short and longer term.

This article was finalized at the Royal Society of Edinburgh where the author was attending the IDE (Institute of Demolition Engineers) Scottish Seminar in July 2018. It's an inspiring experience there for the author to further think about fundamental questions and answers in relation to the long-term leadership development and capability growth for considerate construction management to fulfill professional responsibilities on total project-oriented sustainability, which relies on a spur of engineering and management genius to spread enlightenment ideas among professionals so as to provide quality services that can support to create and sustain dependable built environment through project-oriented activities that have minimum adverse impacts to people and the nature.

This article cannot achieve the level of publication without a great amount of very insightful comments from reviewers. The author would like to acknowledge their help to make this publication possible. The author would also like to thank colleagues in the Review Operations Team and the Engineering Production Office at Frontiers for their efficient professional support.

For the specialty section on Construction Management at Frontiers in Built Environment, the author would like to invite colleagues working in either research or practice in related areas to come to share valuable experiences to foster further research and development worldwide. The more contributions from colleagues, the huge impacts that this specialty section can make to the long-term development of the construction management profession at national and international scope.

ACCE (2017). Annual Report 2016–2017 . San Antonio, TX: The American Council for Construction Education (ACCE).

Alarcón, L. (1997). Lean Construction . London: CRC Press.

Google Scholar

Allee, V. (1997). The Knowledge Evolution: The Knowledge Evolution: Expanding Organizational Intelligence . Newton, MA: Butterworth-Heinemann.

Allplan (2018). Intelligent Cost Management . München: Allplan Deutschland GmbH. Available online at: https://www.allplan.com/fileadmin/user_upload/countries/international/pdfs/references/Design2Cost_CaseStudy_Elwert-Grundschule_EN.pdf (accessed September 23, 2018).

Alonso, A., Dallmeier, F., and Servat, G. P. (2013). Monitoring Biodiversity: Lessons from a Trans-Andean Megaproject . Washington, DC: Smithsonian Institution Scholarly Press.

AlSehaimi, A., Koskela, L., and Tzortzopoulos, P. (2013). Need for alternative research approaches in construction management: case of delay studies. J. Manag. Eng. 29:4. doi: 10.1061/(ASCE)ME.1943-5479.0000148

CrossRef Full Text | Google Scholar

Anumba, C. J., Egbu, C. O., and Carrillo, P. M. (2005). Knowledge Management in Construction . Oxford: Blackwell Publishing Ltd.

Arditi, D., and Polat, G. (2010). Graduate education in construction management. J. Profession. Iss. Eng. Edu. Pract. 136:3. doi: 10.1061/(ASCE)EI.1943-5541.0000014

ASCE (2008). Civil Engineering Body of Knowledge for the 21st Century, 2nd Ed . Reston, VA: American Society of Civil Engineers (ASCE).

ASCE (2019). Civil Engineering Database . Reston, VA: American Society of Civil Engineers (ASCE).

PubMed Abstract

Balfour Beatty (2017). Innovation 2050: A Digital Future for the Infrastructure Industry . London: Balfour Beatty plc.

BCA (2016). BIM for DfMA (Design for Manufacturing and Assembly) Essential Guide . Singapore: Building and Construction Authority (BCA).

Bechtel (2018). The Bechtel Report 2018 . Reston, VA: Bechtel Corporation.

BEIS (2018). Industrial Strategy: Construction Sector Deal . London: Department for Business, Energy & Industrial Strategy (BEIS).

Berechman, J. (2018). The Infrastructure We Ride On: Decision Making in Transportation Investment . Berlin: Palgrave Macmillan, Springer.

Bernold, L. E., and AbouRizk, S. M. (2010). Managing Performance in Construction . Hoboken, NJ: John Wiley & Sons, Inc.

BGS (2012). Accessing Subsurface Knowledge—ASK Network . Edinburgh: British Geological Survey (BGS).

BIS (2013). Construction 2025: Industrial Strategy for Construction—Government and Industry in Partnership . London: Department for Business, Innovation & Skills (BIS).

Black, E., and Pettitt, J. (2018). Boston Dynamics is Putting its Robotic Dog, Spot, to Work on Construction Sites . Tokyo: CNBC LLC.

Blanco, J. L., Fuchs, S., Parsons, M., and Ribeirinho, M. J. (2018). Artificial Intelligence: Construction Technology's Next Frontier . New York, NY: McKinsey & Company. Available online at: https://www.mckinsey.com/industries/capital-projects-and-infrastructure/our-insights/artificial-intelligence-construction-technologys-next-frontier (accessed September 23, 2018).

BMUB (2016). Climate Action Plan 2050: Principles and Goals of the German Government's Climate Policy . Berlin: Federal Ministry for the Environment, Nature Conservation, Building and Nuclear Safety (BMUB).

BMWi. (2018). Federal Government Adopts Artificial Intelligence Strategy . Berlin: Federal Ministry for Economic Affairs and Energy (BMWi).

Boateng, P., Chen, Z., and Ogunlana, S. (2017). Megaproject Risk Analysis and Simulation: A Dynamic Systems Approach . Bingley: Emerald Publishing Limited.

Bock, T. (2015). The future of construction automation: technological disruption and the upcoming ubiquity of robotics. Automat. Construct. 59, 113–121. doi: 10.1016/j.autcon.2015.07.022

Bock, T., and Linner, T. (2016). Construction Robots: Elementary Technologies and Single-Task Construction Robots . Cambridge: Cambridge University Press.

Briesemeister, J. K. (2018). Managing Complex Construction Projects: A Systems Approach . New York, NY: Auerbach Publications.

Brookes, N., Chen, Z., and Lo Storto, C. (2012). International Journal of Architecture, Engineering and Construction . Special Issue on Planning and Managing Sustainable Infrastructural Megaprojects: Call for Papers. Available online at: http://www.iasdm.org/journals/download/call-for-papers-pmsim.pdf (accessed September 23, 2018).

Brookes, N., Chen, Z., and Lo Storto, C. (2014). Editorial: Special issue on infrastructure megaprojects. Int. J. Architect. Eng. Construct. 3:2. Available online at: http://www.iasdm.org/journals/index.php/ijaec/issue/view/10

Brookes, N., and Zhang, S. (2014). Call for Papers on Megaprojects: Global Similarities and Global Differences . Available online at: http://blog.sciencenet.cn/blog-307182-823077.html (accessed September 23, 2018).

Browne, A. J. (2015). LAPSSET: The History and Politics of an Eastern African Megaproject . London: The Rift Valley Institute.

Brunn, S. D. (2011). Engineering Earth: The Impacts of Megaengineering Projects . Dordrecht: Springer.

BSI (2006). PD 6079-4:2006 Project Management. Guide to Project Management in the Construction Industry . London: The British Standards Institution (BSI).

BSI (2014). BS EN 60300-1:2014 Dependability Management—Part 1: Guidance for Management and Application . London: The British Standards Institution (BSI).

Campbell, S., De Beer, J., Van der Meulen, M., Mielby, S. B., Van Campenhout, I., and Venvik, G. (2017). COST Action TU1206 Final Achievement Report . Belgium: COST Association.

Cardownie, S. (2017). Witness Statement of Steve Cardownie . Edinburgh: The Edinburgh Tram Inquiry.

Castro-Lacouture, D., Bryson, L. S., Maynard, C., Williams II, R. L., and Bosscher, P. (2007). “Concrete paving productivity improvement using a multi-task autonomous robot,” in Proceedings of the 24th International Symposium on Automation and Robotics in Construction (ISARC) (Kochi), 223–228.

Chen, Q., García de Soto, B., and Adey, B. T. (2018a). Construction automation: research areas, industry concerns and suggestions for advancement. Automat. Construct. 94, 22–38. doi: 10.1016/j.autcon.2018.05.028

Chen, Z. (2007). Multi-criteria Decision-Making for the Sustainable Built Environment. Reading: University of Reading.

Chen, Z. (2017). “The principles of facilities management and case studies,” in Proceedings of ARCOM and BEAM Centre Early Career Researcher and Doctoral Workshop on Building Asset Management, 2017-01-20 . Glasgow: Glasgow Caledonian University.

Chen, Z. (2018). Standards Planning and Approval: Project Management Systems . Internal document. Project no. 9019-02604. London: British Standards Institution (BSI).

Chen, Z., Agapiou, A., and Smith, S. (2016). Themed issue on megaproject management: call for papers. Proc. ICE Manag. Procurement Law 171:2. doi: 10.13140/RG.2.2.32373.37602

CrossRef Full Text

Chen, Z., Agapiou, A., and Smith, S. (2018b). Editorial: Themed issue on megaproject management. Proc. ICE Manag. Procurement Law 171:2. doi: 10.1680/jmapl.2018.171.2.43

Chen, Z., Chen, H., and Wang, C. (1999). An expert system for crack diagnosis in cast-in-place reinforced concrete structures (in Chinese). Construct. Technol. 28, 24–25.

Chen, Z., and Li, H. (2006). Environmental Management in Construction: A Quantitative Approach . London and New York, NY: Taylor & Francis.

Chen, Z., Li, H., Kong, S. C. W., Hong, J., and Xu, Q. (2006a). E-commerce system simulation for construction and demolition waste exchange. Automat. Construct. 15, 706–718. doi: 10.1016/j.autcon.2005.09.003

Chen, Z., Li, H., Kong, S. C. W., and Xu, Q. (2006b). An analytic knowledge network process for construction entrepreneurship education. J. Manag. Dev. 25, 11–27.

Chen, Z., Maiti, S., and Agapiou, A. (2017). “Evidence-based safety management in building refurbishment,” in Proceedings of International Research Conference (11-12/09/2017) (Salford: International Council for Research and Innovation in Building and Construction (CIB) and University of Salford), 119–128.

Chen, Z., and Whitehead, C. (2015). “Call for papers: themed issue on megaproject sustainability,” in Proceedings of the Institution of Civil Engineers—Engineering Sustainability (London, UK).

Chen, Z., and Xu, W. (1996). Intelligent methods in building construction (in Chinese). Build. Construct. 18, 44–47.

Chou, J.-S., Lin, C.-W., Pham, A.-D., and Shao, J.-Y. (2015). Optimized artificial intelligence models for predicting project award price. Automat. Construct. 54, 106–115. doi: 10.1016/j.autcon.2015.02.006

CIOB (2014). Code of Practice for Project Management for Construction and Development, 5th Ed . Oxford: Wiley-Blackwell.

CIOB (2015). Time and Cost Management Contract Suite . Ascot: The Chartered Institute of Building (CIOB).

CIOB (2018a). Overseas Accredited Institutions . Ascot: The Chartered Institute of Building (CIOB).

CIOB (2018b). Improving Quality in the Built Environment . Ascot: The Chartered Institute of Building (CIOB).

CIOB (2018c). Guide to Good Practice in the Management of Time in Major Projects: Dynamic Time Modelling, 2nd Ed . Oxford: Wiley-Blackwell.

CIOB (2018d). Accident Investigation and Root Cause Analysis . Ascot: The Chartered Institute of Building (CIOB).

CIOB. (2010). CIOB's Professionalism: An Inclusive Definition of Construction Management . Ascot: Chartered Institute of Building (CIOB).

Clarivate (2019). Web of Science . London: Clarivate Analytics.

Croft, C., Buck, M., and Adams, S. (2016). Lessons Learned from Structuring and Governance Arrangements: Perspectives at the Construction Stage of Crossrail . London: Crossrail Ltd.

Crossrail (2018). Crossrail Learning Legacy . London: Crossrail Ltd.

CSIC (2017). Annual Review 2017 . Cambridge: The Cambridge Centre for Smart Infrastructure and Construction (CSIC).

Dalkir, K. (2017). Knowledge Management in Theory and Practice, 3rd Ed . Cambridge, MA: The MIT Press.

Davies, A., Gann, D., and Douglas, T. (2009). Innovation in megaprojects: systems integration at London Heathrow Terminal 5. California Manag. Rev. 51, 101–125. doi: 10.2307/41166482

De Laubier, R., Wunder, M., Witthöft, S., and Rothballer, C. (2018). Will 3D Printing Remodel the Construction Industry? Boston, MA: The Boston Consulting Group (BCG).

DHS (2012). Office of Infrastructure Protection Strategic Plan: 2012–2016 . Washington, DC: U.S. Department of Homeland Security (DHS).

DHS (2013). NIPP 2013: Partnering for Critical Infrastructure Security and Resilience . Washington, DC: U.S. Department of Homeland Security (DHS).

Dong, J., Tang, L., Gong, W., Utili, S., and Crosta, G. (2018). Special Issue on Mega Engineering Projects in Challenging Geological Environments—A Modern Perspective: Call for Papers . Elsevier.

DOT (2018). Strategic Plan for FY 2018–2022 . Washington, DC: U.S. Department of Transportation (DOT).

EC (2012). Strategy for the Sustainable Competitiveness of the Construction Sector and its Enterprises . Communication from the Commission to the European Parliament and the Council. Brussels: European Commission (EC).

Elecosoft (2018). Powerproject: The Power Behind Successful Projects . Haddenham: Elecosoft UK Ltd.

EMAP (2017). CN Specialists Index 2017 . London: EMAP Ltd.

EMAP (2018). Construction Industry Company League Tables . London: EMAP Ltd.

ENR (2018). ENR 2018 Top 400 Contractors . New York, NY: Engineering News-Record (ENR).

EPA (2017). Policy on Water Infrastructure Sustainability . Washington, DC: United States Environmental Protection Agency (EPA).

ESRI (2002). GIS Solutions for Community Development . Redlands, CA: ESRI.

ESRI (2007). GIS Solutions for Surveying . Redlands, CA: ESRI.

ESRI (2008). GIS Solutions for Civil Engineering . Redlands, CA: ESRI.

ETI (2018). Edinburgh Tram Inquiry: Evidence . Edinburgh: The Edinburgh Tram Inquiry (ETI).

Eynon, J. (2013). The Design Manager's Handbook . Chichester: John Wiley & Sons Ltd.

Eynon, J. (2016). Construction Manager's BIM Handbook . Chichester: John Wiley and Sons Ltd.

Fadaee, S., and Schindler, S. (2017). Call for Papers on Megaprojects. Environment and Society: Advances in Research . Oxford, UK: Berghahn Books.

Faro (2019). BuildIT Construction . Lake Mary, FL: Faro Technologies, Inc.

FHWA (2017). e-Construction and Partnering: A Vision for the Future . Federal Highway Administration (FHWA), U. S. Departments of Transportation (DOT).

Fischer, M., Rajagopal, R., and Nikkhoo, P. (2018). Any Time Data Thinking Prototype for Construction Project Managers . Stanford, CA: Stanford Center for Integrated Facility Engineering (CIFE).

Flyvbjerg, B. (2015). Call for papers—special issue on “Classics in Megaproject Management”. Int. J. Project Manag. 33, 1–2. doi: 10.1016/j.ijproman.2014.08.002

Flyvbjerg, B. (2017). The Oxford Handbook of Megaproject Management . Oxford: Oxford University Press.

Flyvbjerg, B., Bruzelius, N., and Rothengatter, W. (2003). Megaprojects and Risk: An Anatomy of Ambition . Cambridge: Cambridge University Press.

Flyvbjerg, B., and Turner, J. R. (2018). Do classics exist in megaproject management? Int. J. Project Manag. 36, 334–341. doi: 10.1016/j.ijproman.2017.07.006

Frick, K. T. (2016). Remaking the San Francisco–Oakland Bay Bridge: A Case of Shadowboxing with Nature . Abingdon and New York, NY: Routledge.

Future Cities Catapult (2017). Underground Asset Mapping in the UK . London: Urban Innovation Centre.

Galloway, P. D., Nielsen, K. R., and Dignum, J. L. (2012). Managing Gigaprojects: Advice from Those Who've Been There, Done That . Reston, VA: American Society of Civil Engineers (ASCE).

García de Soto, B., Agustí-Juan, I., Hunhevicz, J., Joss, S., Graser, K., Habert, G., et al. (2018). Productivity of digital fabrication in construction: cost and time analysis of a robotically built wall. Automat. Construct. 92, 297–311. doi: 10.1016/j.autcon.2018.04.004

Gil, N., Lundrigan, C., Pinto, J. K., and Puranam, P. (2017). MegaProject Organization and Performance: The Myth and Political Reality . Newtown Square, PA: Project Management Institute, Inc.

Grahovac, D., and Devedzic, V. (2010). COMEX: a cost management expert system. Expert Syst. Appl. 37, 7684–7695. doi: 10.1016/j.eswa.2010.04.073

Greiman, V. A. (2013). Megaproject Management: Lessons on Risk and Project Management from the Big Dig . Hoboken, NJ: John Wiley and Sons, Inc.

Griffith, A. (2010). Integrated Management Systems for Construction: Quality, Environment and Safety . London: Routledge.

Guo, C., and Sheng, Z. (2017). Infrastructure Mega-Project Management: Call for Papers . Beijing: Higher Education Press.

Hagan, G., Baltov, M., and Brookes, N. (2012). Megaproject management: the state of the art. Organ. Technol. Manag. Construct. 4, 567–569.

Hardin, B., and McCool, D. (2015). BIM and Construction Management: Proven Tools, Methods, and Workflows, 2nd Ed . Indianapolis, IN: John Wiley and Sons, Inc.

Hart, L. (2015). Procuring Successful Mega-Projects: How to Establish Major Government Contracts without Ending up in Court . Surrey: Gower Publishing Ltd.

Harty, C. (2005). Innovation in construction: a sociology of technology approach. Build. Res. Info. 33, 512–522. doi: 10.1080/0961321050028860

Hatem, D. J., and Corkum, D. H. (2010). Megaprojects: Challenges and Recommended Practices . Washington, DC: American Council of Engineering Companies.

Hawksworth, J., Berriman, R., and Goel, S. (2018). An International Analysis of the Potential Long Term Impact of Automation . London, UK: PricewaterhouseCoopers LLP.

HSE (2015). Managing health and Safety in Construction: Construction (Design and Management) Regulations 2015 . Bootle: Health and Safety Executive (HSE).

HURD (2017). The 13th Five-Year Plan for Construction Industry Development . Beijing: Ministry of Housing and Urban-Rural Development (HURD) of the People's Republic of China.

ICE (2019). ICE Library . London: Institution of Civil Engineers (ICE).

IPA (2016). Government Construction Strategy: 2016–2020 . London: The Infrastructure and Projects Authority (IPA).

ISO (2008). ISO 22263:2008 Organization of Information about Construction Works—Framework for Management of Project Information . Geneva: International Organization for Standardization (ISO).

ISO (2009a). ISO/TR 16738:2009 Fire-Safety Engineering—Technical Information on Methods for Evaluating Behaviour and Movement of People . Geneva: International Organization for Standardization (ISO).

ISO (2009b). ISO 23601:2009 Safety Identification—Escape and Evacuation Plan Signs . Geneva: International Organization for Standardization (ISO).

ISO (2011). ISO 21542:2011 Building Construction—Accessibility and Usability of the Built Environment . Geneva: International Organization for Standardization (ISO).

ISO (2012). ISO 21500:2012 Guidance on Project Management . Geneva: International Organization for Standardization (ISO).

ISO (2013). ISO 16354:2013 Guidelines for Knowledge Libraries and Object Libraries . Geneva: International Organization for Standardization (ISO).

ISO (2015a). ISO 9001:2015 Quality Management Systems—Requirements . Geneva: International Organization for Standardization (ISO).

ISO (2015b). ISO/TS 22318:2015 Societal Security—Business Continuity Management Systems—Guidelines for Supply Chain Continuity . Geneva: International Organization for Standardization (ISO).

ISO (2017a). ISO and Construction . Geneva: International Organization for Standardization (ISO).

ISO (2017b). ISO 15686-5:2017 Buildings and Constructed Assets—Service Life Planning—Part 5: Life-cycle Costing . Geneva: International Organization for Standardization (ISO).

ISO (2017c). ISO 44001:2017 Collaborative Business Relationship Management Systems—Requirements and Framework . Geneva: International Organization for Standardization (ISO).

ISO (2017d). ISO 20400:2017 Sustainable Procurement—Guidance . Geneva: International Organization for Standardization (ISO).

ISO (2018a). Standards Catalogue: ISO/TC 59/SC 13 Organization and Digitization of Information about Buildings and Civil Engineering Works, Including Building Information Modelling (BIM) . Geneva: International Organization for Standardization (ISO).

ISO (2018b). Standards Catalogue: ISO/TC 59/SC 18 Construction Procurement . Geneva: International Organization for Standardization (ISO).

ISO (2018c). Standards Catalogue: ISO/TC 59/SC 14 Design life . Geneva: International Organization for Standardization (ISO).

ISO (2018d). Standards Catalogue: ISO/TC 59/SC 17 Sustainability in Buildings and Civil Engineering Works . Geneva: International Organization for Standardization (ISO).

ISO (2018e). Standards Catalogue: ISO/TC 267 Facility Management . Geneva: International Organization for Standardization (ISO).

ISO (2018f). The Integrated Use of Management System Standards . Geneva: International Organization for Standardization (ISO).

ISO (2018g). ISO 31000:2018 Risk Management—Guidelines . Geneva: International Organization for Standardization (ISO).

ISO (2018h). ISO 22326:2018 Security and Resilience—Emergency Management—Guidelines for Monitoring Facilities with Identified Hazards . Geneva: International Organization for Standardization (ISO).

ISO (2018i). Standards Catalogue: ISO/TC 92 Fire Safety . Geneva: International Organization for Standardization (ISO).

ISO (2018j). Standards Catalogue: ISO/TC 195 Building Construction Machinery and Equipment . Geneva: International Organization for Standardization (ISO).

ISO (2018k). Standards Catalogue: ISO/TC 260 Human Resource Management . Geneva: International Organization for Standardization (ISO).

ISO (2018l). Standards Catalogue: ISO/TC 46 Information and Documentation . Geneva: International Organization for Standardization (ISO).

ISO (2018m). Standards Catalogue: ISO/TC 207 Environmental Management . Geneva: International Organization for Standardization (ISO).

ISO (2018n). Standards Catalogue: ISO/TC 269 Railway Applications . Geneva: International Organization for Standardization (ISO).

ISO (2018o). Standards Catalogue: ISO/TC 301 Energy Management and Energy Savings . Geneva: International Organization for Standardization (ISO).

ISO (2018p). Standards Catalogue: ISO/TC 258 Project, Programme and Portfolio Management . Geneva: International Organization for Standardization (ISO).

Jia, G., Ni, X., Chen, Z., Hong, B., Chen, Y., Yang, F., et al. (2013). Measuring the maturity of risk management in large-scale construction projects. Automat. Construct. 34, 56–66. doi: 10.1016/j.autcon.2012.10.015

Jones, G. R., and George, J. M. (2016). Essentials of Contemporary Management, 7th Ed . New York, NY: McGraw-Hill Education.

Kajima (2018). Kajima Corporate Report 2018 . Tokyo: Kajima Corporation.

Kim, W. C., and Mauborgne, R. (2004). Blue Ocean Strategy . Brighton, MA: Harvard Business Review Press.

PubMed Abstract | Google Scholar

Kostka, G., and Fiedler, J. (2016). Large Infrastructure Projects in Germany: Between Ambition and Realities . Berlin: Palgrave Macmillan, Springer.

Kwegyir-Afful, C. (2018). Delivering Successful Megaprojects: Key Factors and Toolkit for the Project Manager . Amington: KAPM Services Limited.

Kwon, N., Park, M., Lee, H.-S., Ahn, J., and Kim, S. (2017). Construction noise prediction model based on case-based reasoning in the preconstruction phase. J. Construct. Eng. Manag. 143:04017008. doi: 10.1061/(ASCE)CO.1943-7862.0001291

Laing O'Rourke (2017) Annual Report and Consolidated Financial Statements for the Year Ended 31 March 2017 . Dartford: Laing O'Rourke.

Lehtonen, M., Joly, P. B., and Aparicio, L (2017) Socioeconomic Evaluation of Megaprojects: Dealing with Uncertainties . London: Routledge.

LGA (2018). National Construction Category Strategy 2018 . London: Local Government Association (LGA).

Li, H., Chan, N., Huang, T., Guo, H.L., Lu, W., and Skitmore, M. (2009). Optimizing construction planning schedules by virtual prototyping enabled resource analysis. Automat. Construct. 18, 912–918. doi: 10.1016/j.autcon.2009.04.002

Li, H., Chen, Z., Yong, L., and Kong, S.C.W. (2005). Application of integrated GPS and GIS technology for reducing construction waste and improving construction efficiency. Automat. Construct. 14, 323–331. doi: 10.1016/j.autcon.2004.08.007

Li, H., and Guo, H. L. (2011). Editorial: Special issue on “Complexities in managing mega construction projects”. Int. J. Proj. Manag. 29, 795–796.

Li, Y., Lu, Y., and Cui, Q. (2016). Organizational Behaviour and Governance of Megaprojects: Call for Papers . Reston, VA: American Society of Civil Engineers (ASCE).

Locatelli, G., Gatti, S., van Marrewijk, A., and Pitsis, T. S. (2017). Call for Papers: The Present and Future of Contracting and Megaprojects . London, UK: SAGE Publications.

Love, P. E. D., and Li, H. (1998). From BPR to CPR—conceptualising re-engineering in construction. Business Process Manag. J. 4, 291–305. doi: 10.1108/14637159810238192

Luk, S., and Whitney, J. (1993). Megaproject: Case Study of China's Three Gorges Project . London: M. E. Sharpe, Inc.

Luo, H., Xiong, C., Fang, W., Love, P. E. D., Zhang, B., and Xi, O. (2018). Convolutional neural networks: computer vision-based workforce activity assessment in construction. Automat. Construct. 94, 282–289. doi: 10.1016/j.autcon.2018.06.007

Mascia, S. (2012). Project Psychology . London: Routledge.

MedSolutions (2013). Why Intelligent Cost Management? Bluffton, SC: eviCore healthcare.

Merrow, E. W. (2011). Industrial Megaprojects: Concepts, Strategies, and Practices for Success . Hoboken, NJ: John Wiley and Sons, Inc.

Merrow, E. W., and Nandurdikar, N. S. (2018). Leading Complex Projects: A Data-Driven Approach to Mastering the Human Side of Project Management . Hoboken, NJ: John Wiley and Sons, Inc.

Microsoft (2016). Reimagine Productivity with Microsoft Dynamics 365. Redmond, WA: Microsoft Corporation.

Morris, P. W. G. (2013). Reconstructing Project Management . Chichester: John Wiley and Sons, Inc.

NASEM (2007). Emerging Technologies for Construction Delivery. National Academies of Sciences, Engineering, and Medicine (NASEM) . Washington, DC: The National Academies Press.

NBS Research (2018). Digital Transformation in Architecture . Microsoft Corporation and the Royal Institute of British Architects (RIBA).

Nguyen, L. D., Chih, Y.-Y., and García de Soto, B. (2017). Knowledge areas delivered in project management programs: exploratory study. J. Manag. Eng. 33:1. doi: 10.1061/(ASCE)ME.1943-5479.0000473

Norris, E., Rutter, J., and Medland, J. (2013). Making the Games: What Government can Learn from London 2012 . London: Institute for Government.

Nunamaker, J. Jr, Briggs, R., and Romano, N. Jr. (2014). Collaboration Systems . New York, NY: Routledge.

Oakland, J., and Marosszeky, M. (2017). Total Construction Management . London: Routledge.

Ochieng, E., Price, A., and Moore, D. (2017). Major Infrastructure Projects: Planning for Delivery . London: Palgrave.

ODA (2011). Lessons Learned from the London 2012 Construction Project . London: Olympic Delivery Authority (ODA).

ODA (2015). Olympic Delivery Authority (ODA) . London: Department for Culture, Media and Sport. Available online at: https://www.gov.uk/government/organisations/olympic-delivery-authority

ONS (2009). UK Standard Industrial Classification of Economic Activities 2007 (SIC 2007): Structure and Explanatory Notes. Hampshire: Palgrave Macmillan.

Osterwalder, A., Pigneur, Y., Bernarda, G., Smith, A., and Papadakos, T. (2014). Value Proposition Design: How to Create Products and Services Customers Want . Hoboken, NJ: John Wiley and Sons.

Pellicer, E., Yepes, V., and Ortega, A. J. (2013). Method for planning graduate programs in construction management. J. Profession. Iss. Eng. Edu. Pract. 139:1. doi: 10.1061/(ASCE)EI.1943-5541.0000120

Pells, D. (2014). Call for Papers on Planning and Managing Infrastructure Megaprojects . Addison, TX: PM World Inc. Available online at: http://promaconafrica.org/index.php/2014/08/30/call-for-papers-on-managing-infrastructure-megaprojects/ (accessed February 27, 2019).

Plotch, P. M. (2015). Politics across the Hudson: The Tappan Zee Megaproject . New Brunswick: Rutgers University Press.

PMI (2016). Construction Extension to the PMBOK ® Guide . Newtown Square, PA: Project Management Institute (PMI).

PMI (2017). A Guide to the Project Management Body of Knowledge (PMBOK ® Guide), 6th Ed . Newtown Square, PA: Project Management Institute (PMI).

PricewaterhouseCoopers. (2014). Successful Capital Project Delivery: The Art and Science of Effective Governance . San Francisco, CA: PricewaterhouseCoopers LLP.

Priemus, H., Flyvbjerg, B., and van Wee, B. (2008). Decision-making on Mega-Projects: Cost–benefit Analysis, Planning, and Innovation . Cheltenham: Edward Elgar Publishing.

Priemus, H., and van Wee, B. (2013). International Handbook on Mega-Projects . Cheltenham: Edward Elgar Publishing.

Pryke, S. (2017). Managing Networks in Project-Based Organisations . Oxford: John Wiley and Sons Ltd.

Rafiei, M. H., and Adeli, H. (2018). Novel machine-learning model for estimating construction costs considering economic variables and indexes. J. Construct. Eng. Manag. 144:04018106. doi: 10.1061/(ASCE)CO.1943-7862.0001570

Ren, H. (2012). Megaproject Management (in Chinese) . Beijing: Science Press.

RIBA (2013). RIBA Plan of Work 2013 Overview . London: The Royal Institute of British Architects (RIBA).

RICS (2018). RICS Accredited Course . London: Royal Institution of Chartered Surveyors (RICS).

Rios, F. C., Chong, W. K., and Grau, D. (2015). Design for disassembly and deconstruction—challenges and opportunities. Procedia Eng. 118, 1296–1304. doi: 10.1016/j.proeng.2015.08.485

Rossi, E., and Stepic, R. (2015). Infrastructure Project Finance and Project Bonds in Europe . Basingstoke: Palgrave Macmillan.

Rumane, A. R. (2018). Quality Management in Construction Projects, 2nd Ed . Boca Raton, FL: CRC Press.

Russell, S., and Norvig, P. (2010). Artificial Intelligence: A Modern Approach, 3rd Ed . Upper Saddle River, NJ: Pearson Education, Inc.

Saaty, T. L. (1996). Decision making with Dependence and Feedback: The Analytic Network Process . Pittsburgh, PA: RWS Publications.

Santamaría, G. C. (2013). Urban Megaprojects: A Worldwide View . Bingley: Emerald Publishing Limited.

Scottish Parliament (2005). Building the Scottish Parliament: The Holyrood Project . Edinburgh: Scottish Parliament.

Shen, L., Zeng, S., and Tam, V. W.Y. (2017). Special edition: social responsibilities for the management of megaprojects. Int. J. Proj. Manag. 35, 1336–1337. doi: 10.1016/j.ijproman.2017.06.001

Sheng, Z. (2018). Fundamental Theories of Mega Infrastructure Construction Management: Theoretical Considerations from Chinese Practices . Cham: Springer.

Singh, A., and Ebeling, K. (1994). Construction process simulation using a standardized configuration and model. Proj. Manag. J. 25, 45–52.

Skanska (2018). Annual Report 2017 . Stockholm: Skanska AB.

Skibniewski, M. J. (1988). Framework for decision-making on implementing robotics in construction. J. Comput. Civil Eng. 2:2. doi: 10.1061/(ASCE)0887-3801(1988)2:2(188)

Smith, D. (2018). Artificial Intelligence Enabling Machines to Learn: Experts Perspectives . London: Arup.

Söderlund, J., Sankaran, S., and Biesenthal, C. (2016). Call for Papers: Special Issue on Megaprojects—Symbolic and Sublime: An Organizational Theory Perspective . Newtown Square, PA: Project Management Institute, Inc.

Sovacool, B. K., and Cooper, C. J. (2013). The Governance of Energy Megaprojects: Politics, Hubris and Energy Security . Cheltenham and Northampton, MA: Edward Elgar Publishing.

Stehr, N., and von Storch, H. (2000). Eduard Brückner—The Sources and Consequences of Climate Change and Climate Variability in Historical Times . Heidelberg: Springer.

Sterman, J. D. (1992). System Dynamics Modeling for Project Management . Cambridge, MA: Massachusetts Institute of Technology.

STI (2017a). Comprehensive Strategy on Science, Technology and Innovation for 2017 . Tokyo: Council for Science, Technology and Innovation (STI).

STI (2017b). Integrated Innovation Strategy . Tokyo: Council for Science, Technology and Innovation (STI).

Taylor, F. W. (1911). The Principles of Scientific Management . New York and London: Harper and Brothers Publishers.

The Press Office (2013). Presidential Policy Directive—Critical Infrastructure Security and Resilience . Washington, DC: The White House Office of the Press Secretary (The Press Office).

Thorpe, B., and Sumner, P. (2004). Quality Management in Construction . Aldershot: Gower Publishing, Ltd.

Tixier, A., Hallowell, M. R, Rajagopalan, B., and Bowman, D. (2016). Automated content analysis for construction safety: a natural language processing system to extract precursors and outcomes from unstructured injury reports. Automat. Construct. 62. 45–56. doi: 10.1016/j.autcon.2015.11.001

Walker, A. (2015). Project Management in Construction, 6th Ed . Chichester: John Wiley and Sons Ltd.

Walker, D. H. T. (2016). Reflecting on 10 years of focus on innovation, organisational learning and knowledge management literature in a construction project management context. Construct. Innovat. 16, 114–126. doi: 10.1108/CI-12-2015-0066

Wang, X., Chong, H.-Y., and Kwak, Y. H. (2017). Special collection announcement: supply chain management in megaprojects. J. Manag. Eng. 33:4. doi: 10.1061/(ASCE)ME.1943-5479.0000516

Wang, Z., Li, H., and Zhang, X. (2019). Construction waste recycling robot for nails and screws: computer vision technology and neural network approach. Automat. Construct. 97, 220–228. doi: 10.1016/j.autcon.2018.11.009

Waziri, B. S., Bala, K., and Bustani, S. (2017). Artificial neural networks in construction engineering and management. Int. J. Architect. Eng. Construct. 6, 50–60. doi: 10.7492/IJAEC.2017.006

Wegrich, K., Kostka, G., and Hammerschmid, G. (2017). The Governance of Infrastructure . Oxford: Oxford University Press.

Whyte, J., and Nikolić, D. (2018). Virtual Reality and the Built Environment, 2nd Ed . Abingdon: Routledge.

Winch, G. M. (2009). Managing Construction Projects, 2nd Ed . Chichester: John Wiley and Sons Ltd.

Womack, J. P., and Jones, D. T. (1996). Lean Thinking: Banish Waste and Create Wealth in Your Corporation . New York, NY: Simon and Schuster.

Wu, C., Chen, D., and Huang, S. (2018). Complexity of Construction Mega Infrastructure Project: Call for Papers . London: Hindawi Publishing Corporation.

Xu, W., and Chen, Z. (1997). Intelligent Methods in Construction . Shanghai: Tongji University Press.

Yang, J. (2017). Environmental Management in Mega Construction Projects . Singapore: Springer.

Yeung, C.L., Cheung, C.F., Wang, W.M., and Tsui, E. (2014). A knowledge extraction and representation system for narrative analysis in the construction industry. Expert Syst. Appl. 41, 5710–5722. doi: 10.1016/j.eswa.2014.03.044

Keywords: abductive reasoning, built environment, construction management, body of knowledge, digital innovation, intelligent system, megaproject management

Citation: Chen Z (2019) Grand Challenges in Construction Management. Front. Built Environ . 5:31. doi: 10.3389/fbuil.2019.00031

Received: 20 July 2018; Accepted: 25 February 2019; Published: 02 April 2019.

Reviewed by:

Copyright © 2019 Chen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

*Correspondence: Zhen Chen, [email protected]

Similar articles being viewed by others

Slider with three articles shown per slide. Use the Previous and Next buttons to navigate the slides or the slide controller buttons at the end to navigate through each slide.

Estimating the volume of civil construction materials by machine learning models

13 March 2023

Vu Hong Son Pham & Ngo Luan Nguyen

A hybrid approach for a cost estimate of residential buildings in Egypt at the early stage

28 February 2020

Mohamed Badawy

Prediction of cost and duration of building construction using artificial neural network

05 July 2022

Jesam Abam Ujong, Elvis Michael Mbadike & George Uwadiegwu Alaneme

Machine learning in project analytics: a data-driven framework and case study

09 September 2022

Shahadat Uddin, Stephen Ong & Haohui Lu

Predicting Performance Measurement of Residential Buildings Using Machine Intelligence Techniques (MLR, ANN and SVM)

15 September 2021

Salah J. Mohammed, Hesham A. Abdel-khalek & Sherif M. Hafez

Cost estimation in road construction using artificial neural network

16 August 2019

Ksenija Tijanić, Diana Car-Pušić & Marija Šperac

Forecasting tunnel geology, construction time and costs using machine learning methods

18 May 2020

Arsalan Mahmoodzadeh, Mokhtar Mohammadi, … Nawzad Kameran Al-Salihi

Predicting the construction projects time and cost overruns using K-nearest neighbor and artificial neural network: a case study from Jordan

13 April 2023

Ahmad Arabiat, Hamza Al-Bdour & Majdi Bisharah

Prediction of TBM cutterhead speed and penetration rate for high-efficiency excavation of hard rock tunnel using CNN-LSTM model with construction big data

29 January 2022

Long Li, Zaobao Liu, … Jianfu Shao

• Review Paper
• Published: 15 September 2020

Cost estimation and prediction in construction projects: a systematic review on machine learning techniques

• Sanaz Tayefeh Hashemi 1 ,
• Omid Mahdi Ebadati   ORCID: orcid.org/0000-0002-2688-9595 2 &
• Harleen Kaur 3  

SN Applied Sciences volume  2 , Article number:  1703 ( 2020 ) Cite this article

22k Accesses

20 Citations

Metrics details

Construction cost predictions to reduce time risk assessment are indispensable steps for process of decision-making of managers. Machine learning techniques need adequate dataset size to model and forecast the cost of projects. Therefore, this paper presents analysis and studied manuscripts that proposed for cost estimation with machine learning techniques for the last 30 years. The impact of this manuscript is deep studied of machine learning techniques and applied an analysis methodology in cost estimation based on direct cost and indirect cost of construction projects, which consists of two parts. In the first part, for study the proposals, we focus on collecting related studied from Google Scholar and Science Direct journals. The interested application areas for project cost estimation are building, highway, public, roadway, water-related constructions, road tunnel, railway, hydropower, power plant and power projects. The second part is regarded to the analysis of the proposals. For cost analysis, there are possibilities to consider two approaches as qualitative and quantitative. However, reflect to the machine learning techniques the quantitative approach is studied. In quantitative approach, we categorized the models in three parts, as statistical, analogues and analytical model and analyse them based on their features. Correspondingly, papers have been thoroughly investigated based on the application area, method applied, techniques implemented, journals, which have been published in, and the year of publication. The most important outcome of this study is to find out the different analytics methods and machine learning algorithms to predict the cost estimation of construction and related projects and aid to find out the suitable applied methods.

Working on a manuscript?

1 introduction.

Cost prediction is a vital process for every business in that it is a predecessor for budget prices and resource allocation in a project life cycle. Actually, it is hard to obtain input data for cost estimation process, while the scope of work is barely known in that it might lead to poor and rough estimates. The more, the project scope is known there are more chances to generate estimates that are more accurate in that more specifications of the project are defined. However, it should be taken into account that, on the other hand, by the progressive elaboration, the process of cost control becomes more difficult if the project is based on inaccurate cost estimates. Furthermore, construction industry due to its characteristics and large amounts of capital needed to initiate and continue the project, are the project types which need more attention because they are high-risk [ 1 ]. Either overestimating or underestimating the cost of these projects will lead to future deviations in budget vs. realized cost. Hence, the methods used in this realm, their respective accuracy, and even their gaps have shown growing interest. Methods with more consistent results can facilitate and smooth the path for cost estimators provided that their related gaps can be investigated and overcome in order to acquire better results. In conventional methods, by knowing work packages and their prices and how they are distributed along the project lifetime; the total project cost can be estimated. Which this will be an input for project resource allocation and further budget calculations. The conventional methods have shown that they are not merely enough. Thereby the lack of a systematic approach in order to reduce the error of the estimation process has entailed in studies that most of all have tried to take advantage of mathematical models, machine learning techniques, and so on to overcome inaccurate or may even erroneous predictions. What is estimated as project construction cost is different from tender price in that the tender price contains other amounts, including company profit and contingency reserve. Contingency reserve is the amount allocated to known risks during the project execution, which is an estimated amount of reserve. The components of project cost are depicted in Fig.  1 due to the contractor’s viewpoint [ 2 ].

Bid structure and analysis in projects

As shown in Fig.  1 [ 3 ], the project cost includes the project indirect cost and direct cost. The project direct cost itself is composed of costs directly spent in the project and the indirect part, which is mainly the overhead of the project, incurred either in the project itself or on the staff side.

This classification is described as follows:

Direct costs Direct costs can be defined as costs that are directly spent in the project and its production activities, which can be well estimated, while adequate information is available about site condition, construction method used, and the resources utilized. In fact, direct costs are composed of several items such as cost of the labor assigned to the project, equipment used, materials and crews and the subcontractors, which the work packages are assigned to, on behalf of the general contractor.

Indirect costs Indirect costs are classified into the following categories:

Project overheard These costs are mainly the costs, which are indirectly incurred in the project and are in charge of the project work packages, but cannot be directly assigned to them such as utilities, supervisory, etc.

General overheard These costs, in contrary to project overhead, cannot be attributed to each project individually and are mainly the staff side costs, such as an amount of money spent in the head office, personnel cost, and so on, which can be attributed to projects proportionate to their costs toward the total costs of the contractor’s organization.

Markup The company bid price is the summation of project’s cost, and an amount regarded as markup which itself is comprised of the following amounts of money:

Profit The amount of money attributed to company’s profit, which depends on the business objectives, the industry competition level, and also how much the contractor wills to win the project over its rivals.

Risk contingency Usually known as identified risks or known unknown, which is also considered in markup and is the amount of money, set aside for uncertain situations, which can affect the project performance, including unexpected events, labor issues, etc. [ 3 ].

Aims and objectives

The objectives of this systematic review include:

Investigating the criteria for construction projects cost estimation.

Determine the criteria of construction projects based on application area, method applied, techniques implemented, journals, and the year of publication.

Reviewing the existing models of machine learning techniques in cost estimation of construction projects.

Assessing the methods, techniques and criteria for construction project cost estimation.

The rest of the paper is structured as follows; Sect.  2 , explores the research methodology, the way to retrieve data, cost estimation techniques and analytics models. Section  3 , concisely deliberates about the results and related discussion and distribution methods, and the paper is concluded in Sect.  4 , and brief about the final results and methods, limitations and future work.

2 Research methodology

2.1 types of studies.

This research investigates the available models and criteria in the field of the smart-grid project for cost estimation from the past 30 years. This is to emphasize that the present review paper does not include all the articles done in this scope and just the ones with the defined keywords and in the domain of construction projects. This study will impose no restriction on the type of proposal work conducted on the subject and no limitations on the date of publication of the documents as well.

2.2 Information sources and search strategy

Databases such as Google Scholar and Science Direct will be searched to access the relevant documents. These two main sources of academic database are totally included more than 400 million documents. Database will be searched using following keywords to obtain relevant papers: “Construction”, “Cost estimation”, “Cost Prediction”, “Regression Analysis”, “Case Based Reasoning”, “Analogy”, “Artificial Intelligence Techniques”. The used keywords in this study are the most important guidelines in this area, which can help to reach to relevant papers. For such, no limitations impose on the publication status of the extracted studies.

Google Scholars

All fields from 1985–2020 ((((Cost Estimation AND Construction) OR (Cost Prediction AND Construction) OR (Cost Estimation AND Regression Analysis) OR (Construction AND Regression Analysis) OR (Case Based Reasoning) OR (Analogy) OR (Construction AND Artificial Intelligence Techniques) OR (Cost Prediction AND Artificial Intelligence Techniques) OR (Cost Prediction AND Analogy) OR (Regression Analysis)))) AND ((Machine Learning Techniques OR forecasting)).

Science Direct

All Article Types in journals or books, years 1985–2020 ((((Cost Estimation AND Construction) OR (Cost Prediction AND Construction) OR (Cost Estimation AND Regression Analysis) OR (Construction AND Regression Analysis) OR (Case Based Reasoning) OR (Analogy) OR (Construction AND Artificial Intelligence Techniques) OR (Cost Prediction AND Artificial Intelligence Techniques) OR (Cost Prediction AND Analogy) OR (Regression Analysis)))) AND ((Machine Learning Techniques OR forecasting)).

2.3 Selection process

We briefly investigate the papers to identify relevant manuscripts based on the title and abstract. The results entered into the EndNote and remove the duplicates. Following determining the relevant headlines used to consider eligibility of the manuscript criteria to study the full-texts of any potentially related discussions identified so far. To find other theoretically relevant articles, the references of the extracted papers also are examined. Using the comments made by specialists of this field, key journals of the field identified and the relevant articles have been reviewed in details in terms of the following sections, which are embedded in a form used to retrieve data from paper (Table 1 ).

2.4 Cost estimation techniques

The total number of 92 papers have been studied thoroughly, in terms of application area, applied methods, techniques implemented, journal published in, and the year of publication.

In cost estimation scope, many methods and techniques are used, out of which Artificial Neural Networks (ANNs), hybrid models of ANN with secondary artificial intelligence or meta-heuristic methods, Radial Basis Function Neural Network (RBFNN); Case-Based Reasoning (CBR), Regression Analysis (RA), Particle Swarm Optimization (PSO), Decision Tree (DT), and Expert Systems are investigated here.

Artificial neural networks are one of the many algorithms, which are modelling biological learning processes by computers. They are classified under a major classification named machine learning. In fact, machine learning is the process of programming the computers to optimize a performance based on a past available data or experience [ 4 ].

The first mathematical model of an artificial neural network model was formulated by McCulloch and Pitts in 1943 [ 5 ]. Artificial neural networks known as neural networks are analogy-based, non-parametric information-processing systems that have inspired their functionality and structure from the brain’s biological neural networks [ 6 ]. The most challenging problems, which neural networks are used for, are pattern recognition, clustering/categorization, and prediction/forecasting [ 7 ]. In forecasting problems, neural networks are trained based upon past data and depending upon their generalization ability; they can provide forecasting for novel cases.

Neural networks have several advantages, including their capability to perform predictions with less required developed statistical trainings, ability to detect intricate nonlinear relationships among variables, ability to discover all possible interrelations between variables, and the capacity to be developed through the use of numerous training algorithms. However, like any other subject, there remain some disadvantages, including their “black box” mechanism leading to discouragement in finding the origin of the results, their difficult applicability to some problems, their need for high computational resources, and their vulnerability in overfitting and experimental construction, which are highly in need of resolving several matters such as their topology and other methodological matters [ 8 ].

On the other hand, ANN is extremely data driven and will show low prediction performance, while being fed with a small number of data, leading to over specification, which means that they can perform well with the available data, but are incapable of predicting novel cases [ 9 ]. In their point of view, the application of heuristic rules such as preventing the model from being further trained, while there seems to be no more improvement in the network MSE and also using fewer numbers of nodes in hidden layers can mitigate this possibility.

Despite the black box mechanism of neural networks, they have been widely used in prediction problems demonstrating reasonable results as scrutinized in the literature. Developing hybrid model of back propagation neural networks and genetic algorithm will lead to more accurate predictions and prevent the model from presenting erroneous performance hence can overcome the encapsulated shortcomings [ 10 ]. The use of hybrid models of ANN with secondary artificial intelligence or meta-heuristic methods such as genetic algorithms, bee colony algorithm, and artificial immune systems have been proposed in numerous articles in order to cover the drawbacks of ANNs and thus enable them to be applied in diverse problems [ 11 ]. Genetic Algorithm (GA), one of these meta-heuristic methods and a family of evolutionary computation models, was first invented by John Holland in 1960s [ 12 ]. As the optimization problems are occurring in dynamic settings, they require a kind of feedback from the environment, which the problem is taking place regarding the success or even failure of the current applied strategy, that will exploit the earned knowledge in order to evolve the applied strategies and recombine the best pieces of competing strategies to reproduce much more fitting individuals [ 13 ].

Furthermore, CBR is a data mining technique, which remembers the information and also uses the solutions implemented for the similar past cases in solving new problems [ 2 ]. The main source of this information and knowledge is the case, which is reused though through matching by some kind of tolerance [ 14 ].

On the other hand, RA can be classified as a data oriented technique that deals with just the data in hand and not the characteristics behind them and is divided to two linear and nonlinear models [ 15 ]. In addition, decision trees are widely used for solving classification problems. Decision tree is constructed continuously based on the feature that best satisfies the branching rule. This process is then performed iteratively for each branch [ 16 ]. Classification and regression decision trees deal with predicting a dependent variable based upon a predictor variable. The response variable in the former includes a finite set of values, while in the latter contains continuous or discrete set of variables [ 17 ]. Regression trees are good substitution for basic regression methods. Decision tree is mainly constructed based on those attributes in the dataset that are pertinent to the classification case, thus it can be mostly regarded as a feature selection problem [ 18 ].

Besides expert systems are well known by their application of knowledge, facts and methods elicited from human experts that have been affirmed to be effective in solving the cases of the similar domain [ 19 ].

Furthermore, the papers are categorized by the year of publication and the journals within, which papers have been published. In addition, the papers are studied in terms of the area within, which the cost estimation method has been applied. The current fields are as followings: building projects, highway projects, public projects, road way projects water-related construction projects, road tunnel projects, railway projects, hydropower projects, and power plant projects. Besides, the cost estimation methods in these papers are investigated from the applied technique's viewpoint.

Cost estimating methods are classified into two main categories: qualitative and quantitative methods, which will be described in detail later. The total view of cost estimation modelling techniques is depicted in Fig.  2 (Modification of [ 20 ]).

(Modification of [ 20 ])

Cost estimation modelling techniques.

2.4.1 Qualitative approaches

Qualitative approaches are based on estimator’s knowledge of the project, the scope of work, and influencing factors and are divided into two classes: expert judgment and heuristic rules. Expert judgment depends on the good or bad results of the past estimations based on judgment. According to [ 21 ], expert judgment technique is mainly taking advice from the more experienced experts and peers to check the validity of the estimating results. This technique is, in fact, intuition-based and mainly relies on unspoken yet not well documented extrapolation techniques, which are the power in hands of experienced experts that can professionally assure the reliability of estimations [ 21 ].

On the other hand, the heuristic rules in cost estimating are due to intuitive judgments and are done as a rule of thumb to ease the process of estimating and are extracted from relative similar projects.

2.4.2 Quantitative approaches

Quantitative approaches can be defined as methods relying on the process of collecting and analysing historical data and applying quantitative models, techniques, and tools to estimate the project’s cost. Quantitative cost estimating approaches are classified into three main categories: statistical, analogous, analytical ones.

2.4.3 Statistical methods in cost estimation

Statistical methods, on the other hand, are based on formulas or other alternative approaches to establish a causal correlation between final costs and its corresponding characteristics [ 20 ].

Parametric cost estimating methods evaluate the cost through regarding characterizing parameters like mass, volume, and cost without considering little details [ 22 ]. In fact, in this way, the project cost is estimated based on defining its causal link with these parameters, and the result will be a mathematical function of the corresponding variables. This approach is efficient at early stage of a project, where there is little information available about the project [ 23 ], however, it suffers from the minimal necessary result justification [ 22 ]. There are three types of parametric cost estimation methods as follows [ 24 ]:

The method of scales This method is applicable in prevailing technologies, which simple products of different sizes are produced. Evaluating the most influencing technical parameters is the prerequisite of this method. Thereafter, this evaluation is compared with those of finished projects, which makes this method a combination of analogous and parametric approaches. The main disadvantage of this method is assuming that the cost and considered parameters are interrelated through a linear function [ 24 ].

Statistical models In this method, the activities are divided into major different scopes through, which the final mathematical formulae is constructed. This model is composed of three main data types [ 24 ]:

Technical specifications

Relationships between the data and final variables

Cost estimation formulae (CEF) CEF is a mathematical relationship between the final cost and a limited set of technical parameters. The major parameter categories are as follows [ 24 ]:

Physical values According to functional description

Dimensioning values According to solution description

The most probably prevailing parametric methods are regression analysis and optimization techniques [ 20 ].

Parametric cost estimation methods are faced with different drawbacks, which some of them are described as follows; through application of these methods, different results are the sole issue without giving a vision about the origin of them. On the other hand, lack of necessary parameters during early stages will result in uncertainty of the results. In addition, the designer should be aware of the influence of each parameter on the final cost. CEFs in particular, are incapable of solving specific cases. Sometimes also, there is a need to obtain results of regression analysis in four or five similar cases to reach to the most reliable cost. Despite all these disadvantages, they are considered as useful cost estimation methods due to their rapidity of execution [ 24 ].

Analogous models

Analogous models are based on similar past cases, which are reused and adjusted in different cases [ 25 ]. This similarity is due to functional or geometrical homogeny between cost structures, which are alike [ 20 ].

According to [ 21 ], analogous methods are known to be the simplest method of estimating through. The cost of projects is estimated in compared to their similar completed projects that are available as a historical database. Thus, project managers have to consider the most available parameters to include in their process of estimating to reach better results; however, this method is a kind of rough estimate, which is easy to use, but with lower levels of complexity and accuracy as well [ 21 ].

Analytical models

Analytical models instead, are the process of estimating costs by accurately defining the cost corresponding to each processing phase attribute in details, and afterwards using a bottom-up approach for aggregating the project total cost, thus this approach is leading to a more accurate result [ 25 ].

3 Results and discussion

This section discusses the findings of this study. Initially, an overview of the data analysis describes. Then, it presents the report and discussion of the study findings according to the research methodology in the separate subsections. Furthermore, illustrate the result of comparison of different models within the context.

3.1 Data analysis

The present study explores the existing methods and techniques for the cost estimation of projects and extracts approaches components. A classify analysis is conducted using the existing methods and tools and comparison made for different models. The components extracted from all the studied papers classified in terms of application area, methods, techniques, journals and year of publications. The results are discussed in the following sub-sections.

The total studied proposal papers are 92, which based on the considered features, they categorized for different approaches. The sum of 69 of articles are directly reviewed in the field of cost estimation in construction projects and 48 of them have focused on machine learning techniques. Elfaki et al. [ 26 ] have also reviewed the application of intelligent techniques in the construction cost estimation field. All these results have been summarized in “Appendix 1 ”. This Appendix shows; the total view of the present reviewed papers, in terms of the reference, year of publication, first author, area within which the method(s) has/have been applied and the method(s) in order of superiority of performance.

3.2 Application area

Table 2 shows an overall view of the reviewed papers applied in different areas. As it is shown in this table, most of the articles have studied building projects in general and less than half have scrutinized specific construction projects.

Cost estimation in building projects has been studied in a wide range of studies. In fact, building projects in this paper is meant the projects related to constructing buildings and such cases. The aforementioned projects' distributions are shown in the time horizon in Fig.  3 . As it is shown in this figure, the most studies are done in the year 2011 and 2017 with building project standing on the top; on the other hand, hydropower projects, own the least number of studies in this spectrum.

Distributions of different projects studies in years

3.3 Methods

Machine learning techniques have been defined as a system that can learn from data. In general, the main strong point of machine learning techniques can be identified as: the ability of handle uncertainty in methods, the ability to manage and perform with incomplete data, and the ability to decide and conclude the new cases based on experiences from analogous cases.

Khalaf et al. [ 27 ] have applied PSO in estimating cost and duration of 60 construction projects at the early stage. What has been inferred from this study is that PSO has been well performed with high accurate results, while it is encountering parameters with a wide range of variability. The other strength of this model is that it is based on existing projects and is more reliable than the projects based on judgement and experimental cases. However, this paper tries to examine the model with a wider range of parameters and also apply it to green buildings. On the other hand, [ 28 ] have studied the application of ANN in cost estimation of building projects, and it compared the results with RBFNN paper methods, and showed the ANN outperforms. Then, the study followed by optimizing the model accuracy, and applying it to other types of projects, and using other methods for cost factors' screening. In addition, [ 1 ] have proposed a cost model, which is a quantity based one, through which the results will be finally multiplied by the desired prices. Although the recommended model outperforms the CBR method is compared to it, there is a need to conduct more researches to compare the results with further parametric methods to validate the reliability of the current model. This study also, takes advantage of a parameter making process, which its role is to summarize many effective cost factors into a package of influential parameters. On the other hand [ 29 ] have investigated the capability of multilayer feed forward neural network model with a backpropagation learning algorithm for estimating the cost of 78 building projects in India, along with testing the effectiveness of either the early stopping or Bayesian regularization approach on the generalization competency of the network and on the overfitting error as well; where the later approach surpasses. Furthermore, [ 30 ] have implemented fuzzy logic to predict the cost of building projects. As their model is not dynamic in response to market prices, the need for more agile model is felt. Furthermore, [ 31 ] have used an integration of BP neural network and genetic algorithm to estimate the cost of residential buildings. The role of GA is to improve the ANN performance by preventing it from falling into local maximum point and increasing the convergence speed. Besides, [ 32 ] it takes the advantage of multiple regression analysis to estimate the cost of residential buildings. In the research point of view, 92% of the cost of residential building is affected by the land area and building area, and the remaining 8% is stemmed from other factors.

Cost estimation of residential buildings with the use of multifactor linear regression has been considered in [ 33 ], which has reached an accuracy around 92% in the end. The research has recommended to compare the results with those researches that implemented neural network technique to see the differences. Actually, the study is highly advocated the use of cost estimation models in construction projects instead of conventional methods. In [ 34 ], application of Back-Propagation Artificial Neural Network (BPANN) in order to predict the cost of building projects in Nigeria can be seen, however, the model can only be implemented in institutional type of buildings and no other types of buildings or any other projects cannot be estimated by this method. Also, the criterion for the model performance is the prediction errors and other means of evaluations have not been taken into account. Furthermore, [ 35 ] have conducted a survey to investigate the most influencing factors on the cost estimating process, then developed the ANN model, and eventually conducted a sensitivity analysis. They have reached remarkable results with MLP neural network, while applying it at the very early stage of the project. Furthermore, [ 36 ] have implemented ANN for cost prediction of building projects in Philippines. They have concluded that ANN oftentimes can show an acceptable performance despite the incomplete available datasets; however, the enriched datasets is highly recommended. Besides, [ 37 ] have implemented a hybrid model of ANN and GA in order to overcome some drawbacks of ANN, including the slow convergence and being trapped in local minimums. Also, [ 38 ] have applied a hybrid method of CBR and GA in early stages of high-rise building projects to estimate the cost, in a less erroneous way. The application of GA has successfully improved the process of the estimation model by defining the weights of cost factors, though, they recommend to include other cost categories for these types of buildings such as engineering fees and contingencies, considering indexes for different locations, applying other algorithms, instead of GA in order to improve the weights, implementing the model with larger projects dataset, and determining other different cost factors that are effective on the cost estimation process.

On [ 39 ], has comprehensively studied different possible ANN architectures with different learning rates and eventually has compared them, and it is concluded that the best one is an MLP neural network with two hidden layers. It has reached to key findings in the research such that, the number of neurons in the hidden layer, and the learning parameters have more effects on the network generalization ability rather than on its accuracy ability. In addition, the number of hidden neurons is more effective than the learning parameters. On the other hand, the network is highly sensitive to the number of inputs, so that the more inputs; the more the possibility of overlearning in the network. Finally, the study suggests to implement the model in other types of buildings and to compare the current results with other cost estimation methods such as multiple linear regression. Moreover, the development of ANN and Support Vector Machine (SVM) for predicting the cost of building projects and schedule is presented in [ 40 ], out of which, SVM has shown superior performance; therefore, ANN is more applicable in nonlinear sample data. The paper also recommends using an ensemble of ANN and SVM, while it should be taken into account that early planning is considered a key factor in project success. In addition, [ 41 ] have conducted a survey and implemented data analysis in order to extract the main influencing input parameters of their fuzzy model. They have mentioned that the use of two-sided membership function has shown better results than other studied models. They also suggest that comparing the result with other single or combined methods can also be useful. Besides, [ 42 ] have taken advantage of Multiple Regression Analysis (MRA) capabilities to revise CBR in order to enhance the prediction accuracy. They suggest considering also nominal variables and investigating the origins of the increase in the error rate. Son et al. [ 43 ] have also applied a hybrid model of principal component analysis and Support Vector Regression (SVR) and compared them with SVR, ANN, Decision Tree, and Multiple Linear Regression (MLR) out of which eventually, they presented that SVR algorithm is outperformed.

In another research, [ 44 ], the authors have successfully applied case adaptation in order to enhance CBR performance. They suggest that implementing this model in other types of projects as a future research. Also, they proposed the uses of qualitative factors are effective on the model and highly recommend considering the bias resulted from data originated from different regions. In addition, [ 45 ] in their study, have studied BPANN model and compared it with regression in cost estimation of building projects. The best architecture of the neural network is chosen after a process of trial and error out of which eventually, the neural network showed a better performance in compared to regression analysis. In this research, it has been recommended that larger dataset with more accurate information can be used in the future researches. Application of a hybrid model (Modified PSO and fuzzy neural network) in cost estimation of construction projects has also been scrutinized in [ 46 ] as a novel approach within, which the model is capable of being applied to other new cases. Further, [ 47 ] have investigated a BP-ANN model to predict cost of building projects. The best promising architecture is generated after several trials. They also called for larger dataset as an input for the network, in order to improve its performance. Cheng et al. [ 48 ] have integrated neural network with fuzzy logic in order to handle uncertainties as a novel approach. They claim that the hybrid neural network is more effective than the mere neural network in predicting cost of construction projects at very early stage of the project. In addition, there is a concrete evidence that the hybrid neural network is able to address both linear and nonlinear connections in the hidden layer. Cheng et al. [ 49 ] have also taken simultaneous advantage of GA, fuzzy logic, and ANN for global optimization, approximate reasoning, and input–output mapping, respectively. Their cost estimation method is applicable to early stages of the project for project manager’s decision-making process.

A combination of the AHP-based and simulation-based cost model can be seen in [ 50 ] for a single project. They have reached to reasonable results, and they suggest that a wider range of data be fed to their model will be better results. In addition, they recommend a cash allocation system for multiple projects can be developed with a user interface to work around. Their model can be applied to other construction projects as well, and they provided that a modification in weights and evaluation criteria are considered. On the other hand, a combination of rough set (RS) theory and artificial neural network (ANN) is implemented in [ 51 ]. In fact, rough set theory is used to filter the main effective factors in a cost estimation process. They recommend that this hybrid network be implemented in construction projects in that it surpasses the mere ANN results. In their point of view, the less input data can cause, less overfitted network. They recommended combining their model with cost control methods, dealing with data and project cost index in a more scientific way as their future work. An et al. [ 52 ] have used CBR to estimate construction cost of residential buildings. What makes their method worth of use is the application of AHP method in order to interfere with expert’s knowledge in the estimation process. In addition, [ 53 ] have compared three models of NN to predict project’s cost, including BPANN, BPANN adjusted with GA, and NN modified with GA, where the second one outperforms the others. The future of this research is needed to more adjustment of the GA parameters rather than determining them manually.

In [ 54 ], the researchers have used regression analysis to estimate cost of building projects in Singapore and have selected principal components, while being encountered with a large amount of independent variables towards dependent variables. Thus, this will render a regression model with few uncorrelated principals that will eventually produce a better performance. Li et al. [ 55 ] also have investigated the application of regression analysis to estimate the cost of building projects, while incorporating a step-wise variable selection in order to scrutinize the relationship between the available independent variables and the cost of a project as a dependent one. This wise is noted by the authors that the accuracy of the model has improved towards the classic model. Comparison between MRA, ANN and CBR is delicately performed in [ 56 ] out of which, ANN outperforms in terms of accuracy, while CBR outperforms in terms of time spent for cost estimation process. In fact, in this study, three approaches for cost estimation consisting of multiple regression analysis, CBR and ANN have been compared, which finally CBR and ANN outperform MRA, and error associated with ANN is smaller. Also, CBR is the most appropriate model, due to fewer time-consuming features. The use of a BP ANN can be seen in [ 57 ], which is delicately applied to estimate the cost of structural systems of buildings and eventually the results have been compared with regression-based estimations, where the BPANN outweighs the other. Kim et al. [ 58 ] have also implemented BP-ANN, which has been improved through the application of GA algorithm. They have also compared the results of applying GA in order to omit the trial-and-error process of selecting the best ANN architecture with those of the model in the absence of GA, out of which, GA has shown an effective role in improving the model results.

Sonmez [ 59 ] have implemented RA and ANN in cost estimation of building care retirement community projects. They believe that there is not a distinct line between these two methods, and none of them can be called superior to the other; however, they have investigated the for and against of both methods in their case study. Again, Multivariate regression analysis has been implemented in [ 60 ], while accompanied with factor analysis in order to select the best promising factors in the cost estimation process. They believe that the factors effective on cost model accuracy should be more explored. Besides, additional analysis is needed for circumstances, where new projects with new specifications and technologies are added to the project portfolio. In their point of view, different project factors can be taken into consideration, such as regional factors, project categorization, and so on to improve the model performance. Future research shall be conducted to study the cost factor’s behaviour throughout the project lifetime. Emsley et al. [ 61 ] have also implemented ANN in addition to MRA and again factor analysis is implemented to help the process of retaining the best influencing factors in predicting construction cost. Setyawati et al. [ 62 ] have fully compared different situations under which, an ANN may perform better by including different inputs, different structures, data transformation, data preparation, size of dataset. Eventually, ANOVA Footnote 1 test has been implemented to investigate significant difference among four different input sets.

Besides, [ 63 ] have implemented BPANN for predicting the construction cost of school buildings by considering two proposed architectures, where the one, with more inputs outperforms the other. They claim that results that are more accurate stem from more data fed to the network in that neural networks are highly data driven. Boussabaine et al. [ 64 ] have presented an ANN approach developing 6 networks for different n(1 to 6) intervals of the project cash flow as completed intervals throughout the project and m(2 to 7 up to the end of the project) outputs as the remaining m intervals of the project, up to the completion of the project. Khosrowshahi et al. [ 65 ], have also implemented pure MRA to predict cost and time of housing projects in U.K. In this regard, they hope to generate a model, which is more general and can be applied to more diverse cases in terms of type, location, and so forth.

Cost estimation in highway projects has also been the main concern of some studies, which are scrutinized as follows. Mahalakshmi et al. [ 66 ] have estimated the cost of highway projects with the application of a multi perceptron neural network with the back-propagation learning algorithm. The model is composed of significant common cost factors such as topological index and project duration. In [ 67 ], a hybrid model of CBR and AHP is investigated in order to enhance the capabilities of CBR in many aspects, such as improving the accuracy of the results, saving the time, and improving the performance of the model. They claim that, the use of more comprehensive dataset will lead to higher accuracy in results. In addition, the application of indexes related to geographical locations and cost factors should be taken into consideration. On the other hand, [ 68 ] have considered an expert system based upon a regression model in order to facilitate the process of transportation cost estimation. The novel approach in this study is the process of separating quantity from price for removing the need for considering regional factors. Thereafter, when the quantity is estimated, it’ll be applied to unit price retrieved from an up-to-date database. Furthermore, [ 69 ] have implemented ANN in order to improve the estimation accuracy over conventional methods such as EVM. Footnote 2 They have considered several factors out of which, traffic volume, topography, weather conditions, evaluating date, contract duration, construction budget, percent of planned completion, and percent of actual completion, are assumed as the most effective parameters in the project cost. Wilmot and Mei [ 70 ] have also implemented and compared two models, including ANN model and Regression based model for forecasting highway construction cost and the associated escalation in a future, which finally shows the out-performance of the ANN model. In their point of view, factors such as facility (i.e. labour and price of equipment and material), the contract’s characteristics (i.e. terms of payment, duration, geographical location), and overall contract terms (i.e. changes in specifications, amendments and so forth) are the most influencing factors on a cost estimation process.

Sodikov [ 71 ] have successfully implemented ANN in forecasting cost of highway construction and strongly advocate the ANN capabilities in being applied in uncertain circumstances and is used in early stages in projects. Further research is also needed to apply a hybrid of ANN with fuzzy logic, case-based reasoning, and so forth. Hegazy and Ayed [ 23 ] have developed an ANN model in this scope and optimized the corresponding weight through three different methods, including back-propagation training, simplex optimization, and applying genetic algorithm, out of which, simplex optimization surpasses the others. Their model is adaptive to new cases and can be compatible based on new circumstances. Adeli and Wu [ 72 ] have taken into consideration a regularization neural network, while a cost function composed of a standard error is applied and regularization error in order to simultaneously improve the network performance and prevent the network from being overfitted.

They defined public projects for their model as, whatever projects that are related to public sector, such as, schools, warehouses, hospitals, highways, bridges, water-related projects, and so on. In fact, the projects with such cases have been considered in this category.

Alshamrani [ 73 ] have considered cost estimation in building projects by taking advantage of regression analysis. Hyari et al. [ 74 ] in their work, they have developed an ANN model for cost estimation of engineering services through which, the influencing factors on a cost estimation process are selected via interview and literature review and further the best architecture of network is chosen after a process of trial and error. They desired to expand their model by feeding it with diverse datasets from different places worldwide; and also applying it to specific projects like bridges and schools that may increase its accuracy by confining the inherent variance in the input variables. Besides, [ 75 ] present a new method called Principal Item Ratios Estimating Method (PIREM), including parametric estimating, ratio’s estimating, and cost significant model, which is capable of estimating costs under high fluctuations in prices, and it even can predict with least data available equal to only 20% of all cost factors.

Skitmore and Ng [ 76 ] have used a forward cross validation regression analysis to estimate time and cost in construction projects. They claim that, when the cost estimation model needs data such as the total amount of a contract, the accuracy of the cost estimation stems is derived from the accuracy of the total contract. Despite these limitations, the model can surpass the current risks and provide a practical tool in this scope. Bowen and Edwards [ 77 ] can also be regarded as a move from black-box mechanisms toward more logical and understandable methods like expert systems in the late twentieth century. They remind that the importance of historical data and expert’s knowledge in cost estimation scope should not be disregarded. In addition, they desired to integrate a resource allocation system with the current cost model in the future.

Roadway projects are related to projects in the scope of paving roads, asphalt, and road-related works such as constructing bridges over roads, and mainly earth works. Few studies are done in this realm, which are as follows. In [ 78 ] the comparison of applying three different ANNs, including Multi-Layer Perceptron (MLP), General Regression Neural Network (GRNN), and RBFNN, has shown that GRNN is capable of estimating the cost of roadway projects with higher accuracy towards the two others. This type of neural network has shown outstanding performance, while encountering with incomplete datasets. They believe that a homogeny in data set will also lead to better results in future researches in which, they have considered roadway projects with diverse specifications.

Swei et al. [ 79 ] have applied an integration of a Maximum Likelihood (ML) and Least Angle Regression (LAR) to estimate the cost of road pavement. They suggest that more cost inputs can be taken into consideration, in the model for the future. They also recommend that their model can be implemented by using actual cost rather than a bid price for further studies. Besides, the use of other methods such as regression analysis is also proposed.

Peško et al. [ 80 ] have considered comparing ANN and SVM capabilities in cost estimation for construction of urban roads out of which, SVM has shown superior result compared to ANN. They claim for more expanded database in the future researches. Also, they raise the need for a cost model that is capable of estimating at very early stage of the project for management purposes.[ 81 ], for instance, have taken advantage of simulation in management with the use of stochastic models and Monte Carlo simulation. On the other hand, [ 82 ], have applied CBR and GA for cost estimation of bridge construction projects. On the other hand, [ 83 ] have probed the application of ANN in cost estimation of bridge repair and maintenance projects compared to work package methods, which finally the results of ANN are more outstanding. A conclusion is drawn that the model performs well at the early stages of the project, and a hybrid of the current method with up-to-date techniques in general, and fuzzy logic in particular are recommended.

Water-related projects, here are referred to whatever project beyond the scope of water, sewer installation services, and so on. Cost estimation in this type of projects is less investigated, which are studied as follows. Marzouk and Elkadi [ 84 ] have determined variables effective on cost estimation process and conducted a survey to implement a factor variable reduction through Exploratory Factor Analysis (EFA). Eventually, the best ANN is selected from different architectures with an error almost equal to 22%. ANN has also been the main concern for cost estimation in [ 85 ], since it is capable of tackling non-linearity in early stages of projects. Furthermore, [ 86 ] have used ANN model to predict water and sewer services construction cost and selected the best network architecture based on trial and error through, which have reached an accuracy of 80%. They claim that one of the drawbacks of their model is the lack of regional factors, which can be effective in improving the performance and accuracy of the current model.

In roads, tunnels project area, two types of neural networks have been implemented in [ 87 ], and the results have been compared with those of multiple regression analysis, out of which neural networks show better performance. Their model can be implemented in other types of buildings as well. However, as they claim, the model needs to be updated to be compatible to newly complete and added projects to their database. Petroutsatou and Lambropoulos [ 88 ], on the other hand, have approached the construction cost estimation via application of a Structural Equation Model (SEM) and compared the results with ANN and RA models, which SEM performs better. They try to follow their research in future to be able to predict the project profit and schedule programming as well as project cost.

On the other hand, in railway project’s scope, comparison between MRA and ANN in estimating the cost of light rail transit and metro track works can be seen in [ 89 ] out of which, the MRA result is superior to the other due to the small number of available instances. This shows that the higher the number of the cases the higher will be the ANN results' accuracy. Besides, the work of [ 90 ] has depicted the effect of GA on optimizing CBR attributes weights for estimating the cost of railway bridge projects.

Recently, [ 15 ] have investigated forecasting hydroelectric power plant project’s cost via ANN through which, three different architectures have been generated and examined, while seeking the best performance. The results have been compared with those of RA and concluded that the ANN shows better promising results. They set forth that, the model can be used for different parts of hydroelectric power plant projects as well. Singal et al. [ 91 ] probe RA in their study and compared the results with actual cases to validate their model.

Hashemi et al. [ 92 ] have thoroughly investigated effective parameters in cost estimation of power plant projects, while simultaneously considering risk in these projects by embedding PERT technique. The sensitivity analysis conducted in this research shows that the type of power plant is the most influencing factor in the model inputs. This data is finally fed into the hybrid of ANN and GA, to estimate the cost of these types of projects with an accuracy equal to 94.71%.

Hence, the determinative role of ANNs is highlighted again in Fig.  4 . Afterwards, as it is mentioned before, RA is the most powerful method applied in cost estimation studies. As it can be seen, SVM, PSO, RBFNN, and Fuzzy ANN have been used only in building projects.

Application area versus method applied

Figure  5 shows the distribution of these methods and as it is depicted so, ANNs have the first ranking among all methods. This strongly shows the power of Neural Networks as the artificial intelligence tool to deal with estimating problems. Further, Regression Analysis stands on the second step as an outstanding tool in the field of parametric methods.

Applications of different methods in construction cost estimation studies

3.4 Distributions and techniques

Studies on the distribution of the cost estimation techniques suggest the need for categorization. These techniques are based on the studied papers considered as an analogous, analytical, parametric and intuitive approach. To continue analysing the reviewed papers, based on these criteria, the results have been represented in “Appendix 2 ”. The summary of “Appendix 2 ” is illustrated in Fig.  6 . As the result shown in Fig.  6 , most of the adopted techniques belong to the analogous category, and the least one is the analytical one, which is the decision tree method adopted in [ 43 ].

Distributions of articles by approach types

In the construction cost estimation, the qualitative model confides in the specialist judgment or heuristic and mathematical rules. The qualitative models can classify into statistical, intuitive, and analytical models. On the other hand, quantitative models can categorize into three main techniques of analogous, parametric, and analogy-based models. Among all the methods applied to the proposal techniques, only 2% of them are qualitative, which belong to intuitive methods such as AHP. Therefore, based on this result, the rests of the studies are done based on quantitative approaches (Fig.  7 ).

Approach type distribution

One step further, the sub domains of each approach type are shown in Fig.  8 i.e. intuitive, analytical, analogous, and parametric. As shown in this figure, analytical methods such as decision trees have the least proportion of all methods applied. These categories are also shown in each application area and presented in Fig.  8 .

Approach types applied in different areas

Moreover, the distribution of these approaches in the time spectrum is shown in Fig.  9 , As it is presented analogous approaches have the most portion of studies conducted. Total categories of cost estimation methods applied in cost estimation of construction projects can also be seen in “Appendix 3 ”.

Approaches implemented in time horizon

3.5 Journals

Table 3 also summarizes the papers reviewed by their journals, and the journal’s portion of total.

As shown in the above table, the Journal of Construction Engineering and Management, Building and environment, Construction Management and Economics, Expert System with Applications are the top journals with the most published papers in construction cost estimation scope.

3.6 Year of publication

Figure  10 has also depicted the distribution of cost estimation studies in years. As shown in this figure, a smooth growth has been occurred in years 2009 until 2011, and 2017 until 2019, after a decline in years 2006, and 2007. However, again a diminution has been observed afterwards until 2016. Furthermore, as it presents, the most studies have been done via ANN as a powerful machine learning technique.

Distributions of applied cost estimation methods in years

As it has been contemplated more in diverse applied methods, the ANNs’ contribution to cost estimation problems observed in Fig.  11 . Cost models, expert systems, AHP, Footnote 3 CBR, Monte Carlo, fuzzy logic, and decision tree methods are all summarized as other methods in this diagram.

Proportions of each method studied in time horizon

4 Conclusion

Cost estimation in construction projects has been reviewed in articles published within years from 1985 to 2020. A conclusion is drawn that in almost all the cases, estimating at the very early stage of the project is of a great concern. Most of the proposed estimation techniques tried to meet the expectation by generating models to be applied at even tendering level to help process of decision-making of managers. Fundamentally, effective cost factors shall be explored and scrutinized exactly. Not only, the effective cost factors should be studied, but also the factors affecting the cost model accuracy must be reviewed in deep. One of the cost factors that have been noted repeatedly is the regional factor, which shows the importance of differentiating between projects with diverse geographical origin. Additionally, the ability of the model to expand generally and the applicability to novel cases has the high degree of importance.

As shown by results, among the various methods (ANN, Fuzzy NN, SVM, PSO, RBF, RA, CBR, PSO, Decision Tree, AHP, Monte Carlo, fuzzy logic) used by researchers, the most popular machine learning techniques that used in the reviewed papers are ANN and RA respectively. In contrast to other methods, the ANN and RA are the most popular and successful methods implemented in these studies respectively. However, the hybrid models of ANN with fuzzy logic, CBR, GA and so forth have surpassed the mere ANN applied. The point that shall be considered in ANN application is its sensitivity to input data. Since this machine learning technique is data driven, it will perform more accurately, if a large amount of data and homogenous dataset exists to extract relations between available data. On the other hand, the number of input neurons (known as cost factors), has a direct effect on system malfunction. Accordingly, when the number of input cost factors increases, the complexity of the system will increase and in case of construction cost estimation, it showed the accuracy of the estimation will decrease. This study finds out in the hidden layer, the number of neurons and the corresponding weights have a direct effect on the generalization ability of the model. Indeed, the number of factors is important rather than learning parameters, and it directly affects the estimation model accuracy. In addition, ANN is known as a powerful model in tackling with nonlinear problems. Tuning the ANN parameters, such as the number of hidden factors and weights have also been the concern of many studies, which have been overcome by combining it with GA algorithm. Nevertheless, the expert knowledge to select cost factors in the estimation models has a valuable influence. Furthermore, the building and highway projects assign the most attention of the researchers to themselves in cost estimation studies. Among these studies, the methods have been categorized based on their approach, including intuitive, parametric, analogous, and analytical, which the most studies belong to the analogous group.

This study provides several guidelines for applying machine learning models in construction projects as follows: (1) understand the fundamental and validation of machine learning models and cooperate with existing applications and models; (2) select the best models, which ability is well matched with the research impacts and goals; (3) construct the dataset priority for proposal machine learning models and check the sufficiency and efficiency of the dataset; (4) parallel use of machine learning models with current or ordinary models at the early stage of a project; and (5) find the project priority of factors and required datasets in the research association.

The limitations of this research paper can be summarised as: (a) data is collected from Google Scholars and Science Direct scientific database, therefore, the articles did not cite in these two databases did not consider in the study as well; (b) the study had the limitation of exploring the English language papers in the cost estimation for construction projects domain only and not considered the other languages.

Based on this study, deep-learning techniques did not get attention of researchers in the field of cost estimation for construction projects; therefore, this systematic review suggests these techniques and models for future propose work and study.

Analysis of variance.

Earned value management.

Analytical hierarchy process.

Ji S-H et al (2019) Cost estimation model using modified parameters for construction projects. Adv Civ Eng 2019:1–10

Google Scholar  

Aamodt A, Plaza E (1994) Case-based reasoning: foundational issues, methodological variations, and system approaches. AI Commun 7(1):39–59

Hegazy T (2002) Computer-based construction project management. Prentice Hall, Upper Saddle River

Alpaydin E (2014) Introduction to machine learning. MIT Press, Cambridge

MATH   Google Scholar  

Graupe D (2013) Principles of artificial neural networks, vol 7. World Scientific, Singapore

Anderson D, McNeill G (1992) Artificial neural networks technology. Kaman Sci Corp 258:1–83

Hsu KL, Gupta HV, Sorooshian S (1995) Artificial neural network modeling of the rainfall-runoff process. Water Resour Res. 31(10):2517–2530

Tu JV (1996) Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 49(11):1225–1231

Bjornson C, Barney DK (1999) Identifying significant model inputs with neural networks: tax court determination of reasonable compensation. Expert Syst Appl 17(1):13–19

Bai Z et al (2014) Predictive model of energy cost in steelmaking process based on BP neural network. In: 2nd international conference on software engineering, knowledge engineering and information engineering (SEKEIE). Singapore

Tkáč M, Verner R (2016) Artificial neural networks in business: two decades of research. Appl Soft Comput 38:788–804

Mitchell M (1998) An introduction to genetic algorithms. MIT Press, Cambridge

Back T, Fogel DB, Michalewicz Z (1997) Handbook of evolutionary computation. IOP Publishing Ltd., Bristol

Yang J-B, Yau N-J (1996) Applications of case-based reasoning in construction engineering and management. In: Computing in civil engineering, vol 15. ASCE, pp 663–669

Gunduz M, Sahin HB (2015) An early cost estimation model for hydroelectric power plant projects using neural networks and multiple regression analysis. J Civ Eng Manag 21(4):470–477

Djukova EV, Peskov N (2007) A classification algorithm based on the complete decision tree. Pattern Recognit Image Anal 17(3):363–367

Loh WY (2008) Classification and regression tree methods. In: Encyclopedia of statistics in quality and reliability. Wiley, pp 1–13

Perner P (2015) Decision tree induction methods and their application to big data. In: Xhafa F, Barolli L, Barolli A, Papajorgji P (eds) Modeling and processing for next-generation big-data technologies. Springer, Cham, pp 57–88

Dym CL, Levitt RE (1991) Knowledge-based systems in engineering. McGraw-Hill Book Company, New York

Layer A et al (2002) Recent and future trends in cost estimation. Int J Comput Integr Manuf 15(6):499–510

Rad PF (2002) Project estimating and cost management. Management Concepts Incorporated, Virginia

Qian L, Ben-Arieh D (2008) Parametric cost estimation based on activity-based costing: a case study for design and development of rotational parts. Int J Prod Econ 113(2):805–818

Hegazy T, Ayed A (1998) Neural network model for parametric cost estimation of highway projects. J Constr Eng Manag 124(3):210–218

Duverlie P, Castelain J (1999) Cost estimation during design step: parametric method versus case based reasoning method. Int J Adv Manuf Technol 15(12):895–906

Caputo AC, Pelagagge PM (2008) Parametric and neural methods for cost estimation of process vessels. Int J Prod Econ 112(2):934–954

Elfaki AO, Alatawi S, Abushandi E (2014) Using intelligent techniques in construction project cost estimation: 10-year survey. Adv Civ Eng 2014:1–11

Khalaf TZ et al (2020) Particle swarm optimization based approach for estimation of costs and duration of construction projects. Civ Eng J 6(2):384–401

Jiang Q (2019) Estimation of construction project building cost by back-propagation neural network. J Eng Des Technol 18(3):601–609

Chandanshive V, Kambekar AR (2019) Estimation of building construction cost using artificial neural networks. J Soft Comput Civ Eng 3(1):91–107

Wang X (2017) Application of fuzzy math in cost estimation of construction project. J Discrete Math Sci Cryptogr 20(4):805–816

Du Z, Li B (2017) Construction project cost estimation based on improved BP Neural Network. In: 2017 international conference on smart grid and electrical automation (ICSGEA). IEEE

Amin M (2017) Development of cost estimation model for residential building. Int J Civ Struct Eng Res 5(1):1–4

MathSciNet   Google Scholar  

Alshemosi AMB, Alsaad HSH (2017) Cost estimation process for construction residential projects by using multifactor linear regression technique. Int J Sci Res 6(6):151–156

Bala K, Ahmad Bustani S, Shehu Waziri B (2014) A computer-based cost prediction model for institutional building projects in Nigeria: an artificial neural network approach. J Eng Des Technol 12(4):519–530

El-Sawalhi NI, Shehatto O (2014) A neural network model for building construction projects cost estimating. KICEM J Constr Eng Proj Manag 4(4):9–16

Roxas CLC, Ongpeng JMC (2014) An artificial neural network approach to structural cost estimation of building projects in the Philippines. In: DLSU Research Congress, vol 2, no 2, pp 1–8

Feng GL, Li L (2013) Application of genetic algorithm and neural network in construction cost estimate. In: Advanced materials research. Trans Tech Publ 756:3194–3198

Kim S, Shim JH (2013) Combining case-based reasoning with genetic algorithm optimization for preliminary cost estimation in construction industry. Can J Civ Eng 41(1):65–73

Jafarzadeh R et al (2013) Application of artificial neural network methodology for predicting seismic retrofit construction costs. J Constr Eng Manag 140(2):04013044

Wang Y-R, Yu C-Y, Chan H-H (2012) Predicting construction cost and schedule success using artificial neural networks ensemble and support vector machines classification models. Int J Project Manag 30(4):470–478

El Sawalhi NI (2012) Modelling the parametric construction project cost estimate using fuzzy logic. Int J Emerg Technol Adv Eng Website 2(4) ISSN 2250-2459

Jin R et al (2012) MRA-based revised CBR model for cost prediction in the early stage of construction projects. Expert Syst Appl 39(5):5214–5222

Son H, Kim C, Kim C (2012) Hybrid principal component analysis and support vector machine model for predicting the cost performance of commercial building projects using pre-project planning variables. Autom Constr 27:60–66

Ji S-H, Park M, Lee H-S (2011) Case adaptation method of case-based reasoning for construction cost estimation in Korea. J Constr Eng Manag 138(1):43–52

Tatari O, Kucukvar M (2011) Cost premium prediction of certified green buildings: a neural network approach. Build Environ 46(5):1081–1086

He X et al (2011) Cost estimation of construction project using fuzzy neural network model embedded with modified particle optimizer. In: Advanced materials research. Trans Tech Publ 243:6296–6301

Arafa M, Alqedra M (2011) Early stage cost estimation of buildings construction projects using artificial neural networks. J Artif Intell 4(1):63–75

Cheng M-Y, Tsai H-C, Sudjono E (2010) Conceptual cost estimates using evolutionary fuzzy hybrid neural network for projects in construction industry. Expert Syst Appl 37(6):4224–4231

Cheng M-Y, Tsai H-C, Hsieh W-S (2009) Web-based conceptual cost estimates for construction projects using Evolutionary Fuzzy Neural Inference Model. Autom Constr 18(2):164–172

Lai Y-T, Wang W-C, Wang H-H (2008) AHP-and simulation-based budget determination procedure for public building construction projects. Autom Constr 17(5):623–632

Shi H, Li W (200) The integrated methodology of rough set theory and artificial neural-network for construction project cost prediction. In: Second international symposium on intelligent information technology application, 2008. IITA’08. IEEE

An S-H, Kim G-H, Kang K-I (2007) A case-based reasoning cost estimating model using experience by analytic hierarchy process. Build Environ 42(7):2573–2579

Kim G, Seo D, Kang KI (2005) Hybrid models of neural networks and genetic algorithms for predicting preliminary cost estimates. J Comput Civ Eng 19(2):208–211

Chan SL, Park M (2005) Project cost estimation using principal component regression. Constr Manag Econ 23(3):295–304

Li H, Shen Q, Love PE (2005) Cost modelling of office buildings in Hong Kong: an exploratory study. Facilities 23(9/10):438–452

Kim G-H, An S-H, Kang K-I (2004) Comparison of construction cost estimating models based on regression analysis, neural networks, and case-based reasoning. Build Environ 39(10):1235–1242

Günaydın HM, Doğan SZ (2004) A neural network approach for early cost estimation of structural systems of buildings. Int J Proj Manag 22(7):595–602

Kim G-H et al (2004) Neural network model incorporating a genetic algorithm in estimating construction costs. Build Environ 39(11):1333–1340

Sonmez R (2004) Conceptual cost estimation of building projects with regression analysis and neural networks. Can J Civ Eng 31(4):677–683

Trost SM, Oberlender GD (2003) Predicting accuracy of early cost estimates using factor analysis and multivariate regression. J Constr Eng Manag 129(2):198–204

Emsley MW et al (2002) Data modelling and the application of a neural network approach to the prediction of total construction costs. Constr Manag Econ 20(6):465–472

Setyawati BR, Sahirman S, Creese RC (2002) Neural networks for cost estimation. AACE International Transactions, Durham, p ES131

Elhag T, Boussabaine A (1998) An artificial neural system for cost estimation of construction projects. In: Proceedings of the 14th ARCOM annual conference

Boussabaine A, Kaka A (1998) A neural networks approach for cost flow forecasting. Constr Manag Econ 16(4):471–479

Khosrowshahi F, Kaka AP (1996) Estimation of project total cost and duration for housing projects in the UK. Build Environ 31(4):375–383

Mahalakshmi G, Rajasekaran C (2019) Early cost estimation of highway projects in India using artificial neural network. In: Das B, Neithalath N (eds) Sustainable construction and building materials. Springer, Singapore, pp 659–672

Kim S (2013) Hybrid forecasting system based on case-based reasoning and analytic hierarchy process for cost estimation. J Civ Eng Manag 19(1):86–96

Chou J-S (2009) Generalized linear model-based expert system for estimating the cost of transportation projects. Expert Syst Appl 36(3):4253–4267

Pewdum W, Rujirayanyong T, Sooksatra V (2009) Forecasting final budget and duration of highway construction projects. Eng Constr Arch Manag 16(6):544–557

Wilmot CG, Mei B (2005) Neural network modeling of highway construction costs. J Constr Eng Manag 131(7):765–771

Sodikov J (2005) Cost estimation of highway projects in developing countries: artificial neural network approach. J East Asia Soc Transp Stud 6:1036–1047

Adeli H, Wu M (1998) Regularization neural network for construction cost estimation. J Constr Eng Manag 124(1):18–24

Alshamrani OS (2017) Construction cost prediction model for conventional and sustainable college buildings in North America. J Taibah Univ Sci 11(2):315–323

Hyari KH, Al-Daraiseh A, El-Mashaleh M (2015) Conceptual cost estimation model for engineering services in public construction projects. J Manag Eng 32(1):04015021

Yu WD (2006) PIREM: a new model for conceptual cost estimation. Constr Manag Econ 24(3):259–270

Skitmore RM, Ng ST (2003) Forecast models for actual construction time and cost. Build Environ 38(8):1075–1083

Bowen P, Edwards P (1985) Cost modelling and price forecasting: practice and theory in perspective. Constr Manag Econ 3(3):199–215

Tijanić K, Car-Pušić D, Šperac M (2020) Cost estimation in road construction using artificial neural network. Neural Comput Appl 32:9343–9355

Swei O, Gregory J, Kirchain R (2017) Construction cost estimation: a parametric approach for better estimates of expected cost and variation. Transp Res Part B Methodol 101:295–305

Peško I et al (2017) Estimation of costs and durations of construction of urban roads using ANN and SVM. Complexity 2017:1–13

Chou J-S (2011) Cost simulation in an item-based project involving construction engineering and management. Int J Proj Manag 29(6):706–717

Kim KJ, Kim K (2010) Preliminary cost estimation model using case-based reasoning and genetic algorithms. J Comput Civ Eng 24(6):499–505

Bouabaz M, Hamami M (2008) A cost estimation model for repair bridges based on artificial neural network. Am J Appl Sci 5(4):334–339

Marzouk M, Elkadi M (2016) Estimating water treatment plants costs using factor analysis and artificial neural networks. J Clean Prod 112:4540–4549

Ahiaga-Dagbui DD, Smith SD (2012) Neural networks for modelling the final target cost of water projects. In: Smith SD (ed) Procs 28th Annual ARCOM Conference, vol 2, no 1, pp 307–316

Alex DP et al (2009) Artificial neural network model for cost estimation: City of Edmonton’s water and sewer installation services. J Constr Eng Manag 136(7):745–756

Petroutsatou K et al (2011) Early cost estimating of road tunnel construction using neural networks. J Constr Eng Manag 138(6):679–687

Petroutsatou K, Lambropoulos S (2010) Road tunnels construction cost estimation: a structural equation model development and comparison. Oper Res Int J 10(2):163–173

Gunduz M, Ugur LO, Ozturk E (2011) Parametric cost estimation system for light rail transit and metro trackworks. Expert Syst Appl 38(3):2873–2877

Kim BS (2011) The approximate cost estimating model for railway bridge project in the planning phase using CBR method. KSCE J Civ Eng 15(7):1149–1159

Singal S, Saini R, Raghuvanshi C (2010) Analysis for cost estimation of low head run-of-river small hydropower schemes. Energy Sustain Dev 14(2):117–126

Hashemi ST, Ebadati EOM, Kaur H (2017) A hybrid conceptual cost estimating model using ANN and GA for power plant projects. Neural Comput Appl 31:2143–2154

Download references

Author information

Authors and affiliations.

Department of Information Technology Management, Kharazmi University, Tehran, Iran

Sanaz Tayefeh Hashemi

Department of Mathematics and Computer Science, Kharazmi University, Tehran, Iran

Omid Mahdi Ebadati

Department of Computer Science and Engineering, Jamia Hamdard, New Delhi, India

Harleen Kaur

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Omid Mahdi Ebadati .

Ethics declarations

Conflict of interest.

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix 1: Reviewed articles by methods used

Appendix 2: reviewed articles by approach type implemented, appendix 3: categorization of cost estimation methods applied in construction projects.

Rights and permissions

Reprints and Permissions

About this article

Cite this article.

Tayefeh Hashemi, S., Ebadati, O.M. & Kaur, H. Cost estimation and prediction in construction projects: a systematic review on machine learning techniques. SN Appl. Sci. 2 , 1703 (2020). https://doi.org/10.1007/s42452-020-03497-1

Download citation

Received : 27 December 2019

Accepted : 06 September 2020

Published : 15 September 2020

DOI : https://doi.org/10.1007/s42452-020-03497-1

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Cost estimation
• Construction project
• Machine learning
• Systematic review

Advertisement

We use cookies to enhance our website for you. Proceed if you agree to this policy or learn more about it.

• Essay Database >
• Essays Samples >
• Essay Types >
• Literature Review Example

Construction Literature Reviews Samples For Students

42 samples of this type

If you're seeking a workable way to streamline writing a Literature Review about Construction, WowEssays.com paper writing service just might be able to help you out.

For starters, you should browse our extensive directory of free samples that cover most various Construction Literature Review topics and showcase the best academic writing practices. Once you feel that you've figured out the major principles of content presentation and taken away actionable insights from these expertly written Literature Review samples, composing your own academic work should go much smoother.

However, you might still find yourself in a situation when even using top-notch Construction Literature Reviews doesn't allow you get the job done on time. In that case, you can get in touch with our writers and ask them to craft a unique Construction paper according to your individual specifications. Buy college research paper or essay now!

Antigone Argumentative Essay

Example of creative writing on fashion industry a models life not as glamorous as it looks from the outside.

Password recovery email has been sent to [email protected]

Use your new password to log in

You are not register!

By clicking Register, you agree to our Terms of Service and that you have read our Privacy Policy .

Now you can download documents directly to your device!

Check your email! An email with your password has already been sent to you! Now you can download documents directly to your device.

The sample is NOT original!

Short on a deadline?

Don't waste time. Get help with 11% off using code - GETWOWED

No, thanks! I'm fine with missing my deadline

Academia.edu no longer supports Internet Explorer.

To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to  upgrade your browser .

Enter the email address you signed up with and we'll email you a reset link.

• We're Hiring!
• Help Center

A Comprehensive Literature Review on Construction Project Risk Analysis

2016, International Journal of Risk and Contingency Management

The purpose of this paper is to present the chronological development of risk assessment techniques and models undertaken in construction project for the past two decades. This research used a systematic review and meta-analysis on risk assessment of construction project literatures. This includes browsing relevant researches and publications, screening articles based on the year of publication, identifying the domains and attributes. Accordingly, findings of major results achieved have been presented systematically based on the chronology of the research and research gaps are identified. From the review, it is found out that the dominant risk assessment tools used for the past twenty years is statistical analysis and fuzzy expert system.

Related Papers

International Journal of Risk and Contingency Management

Tiziana Guzzo

Communication plays an essential role in risk awareness when the gap between the risk perception and the actual risk depends on correct knowledge. This study investigates public risk awareness and public participation, as part of the European project Integrative flood risk governance approach for improvement of risk awareness and increased public participation (IMRA). The focus is on perceptions of flood risk awareness in the river basin of Chiascio (Umbria-Italy). The survey method is used to analyze flood risk awareness perception before and after an experimental communication intervention with school students. First, the authors examine flood risk awareness of school student families and friends across the population sample region. Then the authors use a unique combination of exercises – a role play game, an exhibition, and a public competition – to improve risk awareness in school children and their families. Finally, the authors test the effectiveness of this intervention in te...

Nediljka Gaurina-Međimurec

Lost circulation presents one of the major risks associated with drilling. The complete prevention of lost circulation is impossible but limiting circulation loss is possible if certain precautions are taken. Industry experience has proved that is often easier and more effective to prevent the occurrence of loss than to attempt to stop or reduce them once they have started. The problem of lost circulation was magnified considerably when operators began drilling deeper and/or depleted formations. A strategy for successful management of lost circulation should include preventative (best drilling practices, drilling fluid selection, and wellbore strengthening materials) and remedial measures when lost circulation occurs through the use of lost circulation materials. In this paper the authors present lost circulation zones and causes, potential zones of lost circulation, excessive downhole pressures causes, preventive measures, tools and methods for locating loss zones and determining t...

Benish Javed

The purpose of the study was to measure the risk the return relationship of inflation and industrial production as macroeconomic variables against stock returns. The study extends the literature by using the GARCH model instead of the traditional Arbitrage Pricing Theory or the Capital Asset Pricing Model. The sample consisted of 50 companies listed on the Karachi Stock Exchange (KSE) in Pakistan. The data collection encompassed the period from July 1998 to December 2008. The macro economic indicators were inflation rate and growth rate of industrial production. The techniques included regression and first order Augmented Dick Fuller test (since it was a time series). The authors found a significant relationship between the macro economic indicators of inflation and industrial production against the sampled KSE returns. The sensitivity coefficients of industrial production and inflation were negative which indicated real sector risk and inflation unfavorably impacted the sampled KSE...

International Journal of Enterprise Information Systems

Obaid Khattak

Carrying with itself the most effective, efficient & cross-functional integrative capabilities, the importance in adoption & usage of ERP systems has significantly increased in vibrant and dynamically responding business settings of today. This study attempts to present the ERP system’s implementation success in terms of organizational impact, on time and under allocated budget by qualitatively examining relationship of each of the identified critical success factors (CSFs) to project’s implementation success in enterprises of a developing country, China, by using validated responses from 12 organizations, using a questionnaire survey approach. Summary of survey’s results are then presented in a tabular form to get a clearer view of the impact of CSFs during ERP system implementation. Findings confirm that 10, 9 and 1 out of the 20 proposed factors that are identified from the literature are critical, least critical & not critical respectively. Findings are then compared, in brief, ...

International Journal of Software Science and Computational Intelligence

International Journal of Knowledge-Based Organizations

Sercan Demir

International Journal of Operations Research and Information Systems

Ghaleb Abbasi

Repetitive construction activities have the same activities which are performed repeatedly. Repetitive projects include: pipelines, highways, and multi-story buildings. Repetitive projects have been modelled widely using the traditional network techniques although, they have some disadvantages. Furthermore, different approached have been developed for repetitive activities including the graphical and analytical techniques. The objective of this research is to add new enhancements on an approach called Repetitive Project Model (RPM) which is related to the repetitive construction projects. The enhancements incorporating the incentives and penalties within the RPM. This model incorporates a network technique, a graphical technique, and an analytical technique. A numerical example was demonstrated in this research paper to aid on using the suggested model in the real-life application.

International Journal of Sustainable Economies Management

Zouhayer Ali Salah MIGHRI

TheobjectiveofthispaperistomeasurethedegreeofHomeBiaswithintheholdingsofportfolio andtoidentifytheirdeterminingfactors.Byfollowinganintuitivereasoning,theauthorshavechosen anumberofsusceptiblefactorsthathaveanimpactonHomeBias.Infact,theyhavedevelopedan internationalCAPM(CapitalAssetPricingModel).Thismodelisestimatedfor20countries,with theuseofcross-sectioneconometrics.Theauthors'resultsshowthatallcountrieshaverecordeda highlevelofHomebiasintheirholdingsofportfolio.InordertostudywhethertheHomeBiasof thenewlyemergingmarketsandthatofthedevelopedmarketsreactdifferentlytothedetermining factorsornottheauthorshaveevaluatedthemodelsomuchjointlyforallmarketsasseparatelyfor thedevelopedandthenewlyemergingones.Inthecaseofclassificationofthesample,theresults havepermittedustodrawanimportantconclusionandtohavecognizancethatthevolatilityofthe exchangerateisstatisticallysignificantconcerningthenewlyemergingeconomiesatathresholdof 1%,whileitishardlyremarkableforthedevelopedcountries.Thismeansthatthisvariableprevents theAmericaninvestorsfrominvestingintheformercountries.Samely,forbothvariablesofjoint- varianceandsize.

International Journal of Information Security and Privacy

Rob Totterdale

Global organizations operate in multiple countries and are subject to both local and federal laws in each of the jurisdictions in which they conduct business. The collection, storage, processing, and transfer of data between countries or operating locations are often subject to a multitude of data privacy laws, regulations, and legal systems that are at times in conflict. Companies struggle to have the proper policies, processes, and technologies in place that will allow them to comply with a myriad of laws which are constantly changing. Using an established privacy management framework, this study provides a summary of major data privacy laws in the U.S., Europe, and India, and their implication for businesses. Additionally, in this paper, relationships between age, residence (country), attitudes and awareness of business rules and data privacy laws are explored for 331 business professionals located in the U.S and India.

RELATED PAPERS

Moshe Zviran

International Journal of E-Entrepreneurship and Innovation

prity kumari

International Journal of Human Capital and Information Technology Professionals

Antoine Trad

International Journal of Service Science, Management, Engineering, and Technology

International Journal of Green Computing

Namrata Das

Andy Novobilski

Frank Lefley

International Journal of …

mehedi hasan

Information Resources Management …

susan crichton

International Journal of Knowledge Society Research

Journal of Cases on Information Technology

Semih Bilgen

International Journal of Strategic Information Technology and Applications

Sharon Dill

International Journal of Electronic Government Research

Hasmiah Kasimin

International Journal of Game-Based Learning

Aristidis Protopsaltis

International Journal of Information Systems in the Service Sector

Ida Kukliansky

International Journal of Strategic Decision Sciences

Sarojini Jajimoggala

Shariful Shikder

Analyzing the Role of Risk Mitigation and Monitoring in Software Development

Samiksha Sharma

International Journal of Information Systems and Supply Chain Management

Ahmad Syamil

Theories, Concepts, and Methodologies

Lemma Lessa

sima ghayebloo

International Journal of Information Systems for Crisis Response and Management

Marc Erlich

International Journal of e-Collaboration

Cleber Duranti

International Journal of Actor-Network Theory and Technological Innovation

Liesbeth HUYBRECHTS

International Journal of Standardization Research

Sabrina Weithmann

International Journal of IT/Business Alignment and Governance

Martha Corrales Estrada

Francis McGuire

Evon Abu-Taieh

International Journal of Corporate Finance and Accounting

KONSTANTINOS VASILEIOU

Jayanta Chatterjee

International Journal of Gaming and Computer-Mediated Simulations

Thomas C Reeves

Chris Walsh , Karen Kenny , Alexander Schmoelz , Elias Stouraitis

International Journal of Secure Software Engineering

Samia OUKEMENI

International Journal of Knowledge and Systems Science

Maurizio Massaro

International Journal of Artificial Life Research

Christian Saliwonczyk

Felice Corona

International Journal of Information Technology Project Management

Leif Marcusson

International Journal of Cloud Applications and Computing

Stein W. Wallace

•   We're Hiring!
•   Help Center
• Find new research papers in:
• Health Sciences
• Earth Sciences
• Cognitive Science
• Mathematics
• Computer Science
• Academia ©2023