You are on page 1of 29

The current issue and full text archive of this journal is available on Emerald Insight at:

www.emeraldinsight.com/1753-8378.htm

Cost overrun in
A review of artificial intelligence construction
based risk assessment projects

methods for capturing


complexity-risk interdependencies
Cost overrun in construction projects Received 22 February 2019
Revised 11 July 2019
Accepted 12 July 2019
Farman Afzal and Shao Yunfei
School of Management and Economics,
University of Electronic Science and Technology of China, Chengdu, China
Mubasher Nazir
University of the Punjab Quaid-i-Azam Campus, Lahore, Pakistan, and
Saad Mahmood Bhatti
University of Engineering and Technology, Lahore, Pakistan

Abstract
Purpose – In the past decades, artificial intelligence (AI)-based hybrid methods have been increasingly
applied in construction risk management practices. The purpose of this paper is to review and compile the
current AI methods used for cost-risk assessment in the construction management domain in order to capture
complexity and risk interdependencies under high uncertainty.
Design/methodology/approach – This paper makes a content analysis, based on a comprehensive
literature review of articles published in high-quality journals from the years 2008 to 2018. Fuzzy hybrid
methods, such as fuzzy-analytical network processing, fuzzy-artificial neural network and fuzzy-simulation,
have been widely used and dominated in the literature due to their ability to measure the complexity and
uncertainty of the system.
Findings – The findings of this review article suggest that due to the limitation of subjective risk data and
complex computation, the applications of these AI methods are limited in order to address cost overrun issues
under high uncertainty. It is suggested that a hybrid approach of fuzzy logic and extended form of Bayesian
belief network (BBN) can be applied in cost-risk assessment to better capture complexity-risk
interdependencies under uncertainty.
Research limitations/implications – This study only focuses on the subjective risk assessment methods
applied in construction management to overcome cost overrun problem. Therefore, future research can be
extended to interpret the input data required to deal with uncertainties, rather than relying solely on
subjective judgments in risk assessment analysis.
Practical implications – These results may assist in the management of cost overrun while addressing
complexity and uncertainty to avoid chaos in a project. In addition, project managers, experts and
practitioners should address the interrelationship between key complexity and risk factors in order to plan
risk impact on project cost. The proposed hybrid method of fuzzy logic and BBN can better support the
management implications in recent construction risk management practice.
Originality/value – This study addresses the applications of AI-based methods in complex construction
projects. A proposed hybrid approach could better address the complexity-risk interdependencies which
increase cost uncertainty in project.
Keywords Construction megaprojects, Fuzzy logic, Project complexity, Project risk,
Project management assessment tool, Risk management techniques
Paper type Literature review

1. Introduction
The complex and dynamic nature of construction projects have been encountered by a International Journal of Managing
Projects in Business
series of cost overrun issues over the years. This cost failure is because of the presence of © Emerald Publishing Limited
1753-8378
complexity and uncertainty in a project system (Pehlivan and Öztemir, 2018). Where there is DOI 10.1108/IJMPB-02-2019-0047
IJMPB uncertainty about ground conditions, accurate project costing cannot be achieved.
Therefore, this baseline cost escalation adheres to the implementation of contingency plans
for project progress in managing complexity and risk within an uncertain environment
(Love et al., 2016). Uncertainty or randomness in project cost behavior is due to system
complexity, which leads to the presence of interdependency network of complexity and risk
factors (Fang and Marle, 2012). While considering a relationship between complexity and
complexity-induced risk factors, it is important to control cost overrun under high
uncertainty because of dynamic, fluid and highly interdependent nature of construction
projects (Liu et al., 2016).
Developing an appropriate risk assessment model for cost overrun has been a challenge
for many years, and different approaches have been adopted to better evaluate the causes of
cost overruns in the form of project complexity and risks under uncertainty (Fan and Yu,
2004; Kardes et al., 2013; Valipour et al., 2015). Cho and Eppinger (2005) presented a process
model and analysis techniques for managing risk of cost escalation in complex design
projects. In order to control cost overrun in construction, Fang et al. (2013) applied an
integrated decision support system (DSS) for risk network and complexity. Similarly,
Liu et al. (2016) explored the potential risk paths interdependencies for the project cost using
international construction risk assessment model. This model is widely adopted in
managing risks interdependencies for managing project cost overrun issues in construction
management. Recently, Qazi et al. (2016) also developed a framework for cost overrun to
capture interdependencies between complexity and risks in construction projects. However,
various other studies have also focused on the complexity and risk interactions in managing
cost overrun under uncertainty (Islam et al., 2017; Islam and Nepal, 2016; Taillandier et al.,
2015). In the past, risk factors have been considered as independent determinants of project
success (Zayed et al., 2008). Since the development in engineering solutions has turned into
complex dynamic systems, which increase the importance of interdependency between risks
and complexity particularly in project cost control (Qazi et al., 2016).
In recent years, a growing number of studies have been found containing hybrid
methods in measuring risk interdependencies to manage cost uncertainties in projects.
Demirkesen and Ozorhon (2017) analyzed the key interdependencies of project risks
for project’ outcomes such as time and cost overrun through structural equation
modeling (SEM) in international construction projects. Fang and Marle (2012) presented a
simulation-based risk assessment approach to study complexity and risk interdependencies
in construction projects. Similarly, Qazi et al. (2016) and Floyd et al. (2017) measured
complexity and risk relationship for cost overrun in complex construction projects by using
an integrated method of Monte Carlo simulation (MCS) and multi-criteria decision model
(MCDM) technique. Subsequently, recent years publications have presented a thorough
overview of the applications of artificial intelligence- (AI) based models (Cárdenas et al.,
2013; Zhang et al., 2017) that can better handle complex, uncertain, and vulnerable
relationships of cost-risk network in construction (Islam et al., 2017).
Previous studies revealed that the soft computational techniques, such as MCDM
(Li et al., 2013), failure mode and effects analysis (FMEA) (Lee and Kim, 2017), fault tree
analysis (Khakzad et al., 2013), event tree analysis (Ferdous et al., 2011), artificial neural
networks (ANNs) (Kim et al., 2009) and Bayesian belief networks (BBNs) (Cárdenas et al.,
2014), have been applied for managing complex risk-networking but failed to address the
presence of uncertainty in project cost behavior. However, current research trends have
accentuated the use of integration of AI methods with other techniques called fuzzy hybrid
methods (FHMs), such as fuzzy-analytical network processing (FANP) (Shafiee, 2015),
fuzzy-BBNs (FBBNs) (Kabir et al., 2016), fuzzy-ANNs (FANNs) (Chan et al., 2009) and
fuzzy-MCS (FMCS) (Sadeghi et al., 2010), over MCDM and probability models alone to evaluate
such complexity-risk interdependencies (Islam et al., 2017; Mehlawat and Gupta, 2016;
Shafiee, 2015) under high cost uncertainty. While addressing these complex interrelationships Cost overrun in
between project cost-risk elements, the applications of risk assessment methods are found to construction
be limited in the literature. No such studies are found which comprise the comprehensive projects
applications of models that address the cost overrun issue in relation with project complexity
and risk interdependencies under high uncertainty. Existing studies are either model-specific
(Valipour et al., 2015) or addressing the complexity and risk independently (Fang and Marle,
2013). Therefore, a comprehensive risk assessment framework is required that can better
address complexity-risk interdependencies in complex and uncertain projects that
encountered cost overrun problems (Islam et al., 2017).
Prior studies have focused on and evaluated project complexity elements and risk factors
independently (e.g. Bu-Qammaz et al., 2009; Dikmen et al., 2007; Hastak and Shaked, 2000;
He et al., 2015; Lee, 2008; Liu et al., 2016; Love et al., 2014; Maurer, 2017), in an attempt to
understand cost overrun behavior in highly uncertain project environments (Taroun et al.,
2011). Recently, Love et al. (2016) addressed the importance of interdependency between the
causes of cost overrun in infrastructure projects but did not consider the potential role of
complexity-driven risk factors in terms of cost. In a similar way, Qazi et al. (2016) also
presented a unique framework on project complexity and risk modeling, and were unable to
derive specific complexity-driven risk factors empirically for cost overrun in large
construction projects. However, studies (i.e. Boateng et al., 2015; Dikmen et al., 2010; Islam
and Nepal, 2016; Ou-Yang and Chen, 2017; Samantra et al., 2017; Tabei et al., 2019) failed to
investigate the important complexity-driven risk interdependencies that have negative
effect on cost overrun. Developing cost-risk assessment methods for the complex nature of
construction projects are a big challenge, and many efforts have been made to design such
methods which are capable of analyzing interdependencies between project complexity and
risk factors. Though, this study intends to present a detailed review of contemporary
research work conducted in developing risk assessment framework which considers
complexity-risk interdependencies and delineates its application in cost overruns. This
study aims to identify potential research gaps in risk analysis tools and guide possible
future research directions in cost-risk assessment. The following sections of this paper are
dedicated to the research methodology, risk assessment techniques capturing complex
interdependencies, applications of such methods in the construction industry, critical
discussion, model limitations, conclusions and future research directions.

2. Research methodology
This study covers a comprehensive content analysis of construction risk management
literature published from the years 2008 to 2018. The contents are mainly based on the
current methods to address the causes of cost overrun and practices being adopted to
mitigate costing issues. Besides the studies of the last ten years, few past papers are also
selected for review to understand the basic idea of research tools used in construction risk
management. The literature is reviewed and retrieved from the top publishers and reputable
journals in the field of construction management, engineering management, project
management, and other related disciplines or sub-disciplines, listed in Scimago Journal &
Country Rank list. Research is drawn through online libraries, i.e. Science Direct, Web of
Science, Sage, Emerald Insight, IEEE Xplore, Wiley, Google Scholar and Springer, including
different databases from top publishers (e.g. IEEE Transactions, ASCE, Elsevier and Taylor
& Francis Group). The content type of this research is based on the journal papers,
conference proceedings and book chapters. Furthermore, few related studies have also been
extracted from the cited bibliography of different published papers.
Initially, a keyword search for “risk assessment,” “risk analysis,” “project complexity,”
“project cost estimation,” “artificial intelligence in construction,” “risk network,” “risk
interdependencies” and “project risk and complexity,” which are often included in
IJMPB construction risk management literature, is drawn to retrieve studies containing AI methods
for risk assessment and complexity-risk network interdependency by using “University
Online Library” search engines. A systematic review has been performed to summarize the
fundamental concepts of available AI methods used in cost-risk assessment in order to
control cost overrun. These risk assessment methods have been classified into major
groups, such as multilevel regression (SEM) (Ebrat and Ghodsi, 2014), MCDM (Li et al.,
2013), probability models (Peleskei et al., 2015), FHM (Cheng et al., 2010) and genetic
algorithm (GA) (Cheng et al., 2010). The application fields of these methods are characterized
into seven main groups: building development, bridge infrastructure, tunnels/subways,
expressways, pipelines, power generation, transmission and other construction projects.
A maximum number of research studies having cost overrun issues and employing
AI methods have been found in a domain of infrastructure transport projects (Beckers et al.,
2013; Flyvbjerg et al., 2004) and building construction (Chang, 2014).
The most frequently cited research journals in this study are: International Journal of
Project Management, Elsevier; Journal of Automation in Construction, Elsevier; Journal
of Decision Support Systems, Elsevier; Expert Systems with Applications, Elsevier;
Transportation Research Part A, Elsevier; Advanced Engineering Informatics, Elsevier;
Transport Policy, Elsevier; Journal of Civil Engineering and Management, Taylor & Francis;
International Journal of Strategic Property Management, Taylor & Francis; Engineering
Management Journal, Taylor & Francis; Structure and Infrastructure Engineering, Taylor &
Francis; Journal of Risk Analysis, Wiley; Project Management Journal, Wiley;
Computer-Aided Civil and Infrastructure Engineering, Wiley; Journal of Management in
Engineering, ASCE; International Journal of Civil Engineering, Springer; and IEEE Systems
Journal. However, a few other papers from different journals and publishers are also cited in
this study. Mostly research work was found from Elsevier, Tayler & Francis, Wiley and
ASCE publishers accordingly. In addition, few books and recent conference proceedings
published in IEEE Transaction journals, Elsevier, Emerald and ASCE are also considered
for detailed discussion.
After the initial review of keywords search, altogether, 129 specific research articles
including research papers, conference proceedings and book chapters on project cost
estimation containing the terms “cost overrun,” “risk interdependency,” “risk network” and
“project complexity” in their titles, abstracts, methodologies and conclusion are identified
and retrieved. However, 100 research articles having AI methods and considering
complexity and uncertainty in cost-risk management are finally sorted for discussion. Out of
these, ten papers are outside the domain of infrastructure construction projects such as
software projects, health and safety, and industrial engineering-related projects. Table I
summarizes the total papers, which explain the current state of knowledge and applications
of popular risk assessment methods related to cost management. Of these, 28 papers related
to cost overrun do not contain the applications of methods measuring risk
interdependencies. This left 87 papers (as shown in Table I) which are related to the
AI methods addressing complex interrelationships between risks network and are reviewed
for detailed cost analysis. Out of total research papers, 73 papers are concerning the hybrid
methods of AI models with some advance computations like fuzzy logic. In addition, few
papers included in the systematic review do not meet any specified criteria of risk
assessment and cost overrun. These listed papers contain different AI methods of
risk assessment, cost estimation, and managing complexity that have been developed over a
period of the last ten years in the construction industry.

3. Applications of AI methods
Aimed for the selection of appropriate methods for developing a risk assessment model to
avoid cost overrun, numerous AI tools and techniques have already been applied in
Year Author (s) Application Method(s) Project Journal/publisher

2004 Fan and Yu Risk management BBNs Software development JSS/Elsevier


2005 Cho and Eppinger Process modeling MCS Complex design projects TEM/IEEE
2005 Kim et al. Cost estimation NN and GA Residential buildings JCCE/ASCE
2007 Aven et al. Risk and uncertainty Decision framework Oil and gas industry RESS/Elsevier
2007 Dikmen et al. Cost overrun risk assessment FST International construction projects IJPM/Elsevier
2009 Bu-Qammaz et al. Risk assessment process ANP International construction projects CJOCE/NRC Research
Press
2009 Chan et al. Construction management FST Construction projects JCEM/ASCE
2009 Kim et al. Project performance SEM Construction projects JESWA/Elsevier
2010 Sadeghi et al. Risk analysis FMCS Highway overpass project CACIE/Wiley
2010 Alex et al. Cost estimation ANNs Water and sewer installation services JCCE/ASCE
2010 Cheng et al. Cost estimation GA, FST and NN Construction projects JESWA/Elsevier
2010 Jin Risk management NFDSS PPP infrastructure projects JCME/ASCE
2011 Lin and Jianping Risk assessment FANP New campus construction SEP/Elsevier
2011 Lazzerini and Mkrtchyan Risk analysis FCM System or project JSYST/IEEE
2011 Ferdous et al. Quantitative risk analysis ETA, FTA, and FST Process system RA/Taylor & Francis
2011 Marle and Vidal Project complexity and risk CA and DSM Large infrastructure projects RED/Springer
2011 Sonmez Cost estimation ANNs and BBNs Construction projects ESWA/Elsevier
2011 Proon and Jin Project Scheduling Problem GA Construction projects NAV/Willey
2011 Eybpoosh et al. Risk management SEM Construction projects JCEM/ASCE
2012 Fang and Marle Complexity, risk network DSS and MCS Construction projects DSS/Elsevier
2012 Weber et al. Risk analysis BND Safety and maintenance JEAAI/Elsevier
2012 Abdelgawad and Fayek Risk management FMEA and FST Construction projects JCEM/ASCE
2012 Cantarelli et al. Characteristics of cost overrun DA Dutch transport infrastructure projects JTP/Elsevier
2012 Li et al. Human errors BN Organizational factors SSCI/Elsevier
2012 Fouladgar et al. Risk evaluation FTOPSIS Tunneling project ACME/Elsevier
2012 Fang et al. Risk analysis Network theory Engineering project RESS/Elsevier
2013 Khakzad et al. Quantitative risk analysis OBN Offshore drilling operations SS/Elsevier
2013 Marle et al. Risk complexity interactions LPA Construction projects IJPE/Elsevier
2013 Kardes et al. Complexity and risk management IRMA Mega-projects IBR/Elsevier
2013 Cárdenas et al. Risk modeling BBNs Construction project s RA/Willey
2013 Odeyinka et al. Cost flow risk assessment ANNs UK construction contractors CME/Taylor & Francis
2013 Bai and Li Risk assessment BP and NN Software projects ICCSNT/IEEE
2013 Fang et al. Risk response planning DSM and GA Large engineering projects TEM/IEEE
2013 Kuo and Lu Risk assessment FMCDM Metropolitan Construction projects IJPM/Elsevier

(continued )
projects
Cost overrun in

models in construction
Summary of risk
construction

interdependency
Table I.

projects
Table I.
IJMPB
Year Author (s) Application Method(s) Project Journal/publisher

2013 Caron Project risk management, MCS Large engineering projects UULEP/Springer
uncertainty
2013 Chong et al. Risk prioritization FST hydrogen refueling station JZUA/Springer
2013 Fang and Marle Modeling risk interactions MBM Tramway project JED/Taylor & Francis
2013 Špačková et al. Risk analysis DBNs Tunnel construction TUST/Elsevier
2014 Cárdenas et al. Risk modeling BBNs Tunneling project RA/Wiley
2014 Cheng and Hoang Risk assessment FST and LSSVM Bridge construction JCCE/ASCE
2014 Taroun Risk modeling MCDM Construction projects IJPM/Elsevier
2014 Yildiz et al. Risk mapping SEM International construction projects JAC/Elsevier
2014 Lessard et al. Complexity and risk HoPC Infrastructure projects EPOJ/Taylor & Francis
2014 Khodakarami and Abdi Cost-risk analysis BN Complex projects IJPM/Elsevier
2014 Guohui Risk assessment FEM Foreign engineering projects ICMTMA/IEEE
2014 Ebrat and Ghodsi Risk assessment ANFIS Construction projects KSCE JCE/Springer
2015 Qureshi and Kang Project complexity and project risks SEM Engineering projects IJPM/Elsevier
2015 Valipour et al. Risk prioritization FANP PPP projects JCEM/Taylor & Francis
2015 Lu et al. Project complexity SEM Large-scale construction projects IJPM/Elsevier
2015 He et al. Complexity measurement FANP Mega construction projects IJPM/Elsevier
2015 Boateng et al. Risk decision making ANP Mega-projects IJPM/Elsevier
2015 Qureshi and Kang Complexity factors modeling SEM Engineering projects IJPM/Elsevier
2015 Shafiee Risk mitigation FANP Offshore wind farm ESA/Elsevier
2015 Taillandier et al. Simulating project risk MAS Construction projects AUTCON/Elsevier
2015 Peleskei et al. Complexity and risk MCS Construction projects Creativecomm-ns.org
2015 Chandra Project risk SEM Construction projects Procedia/Elsevier
2015 Hossen et al. Risk assessment AHP Nuclear power plant JNET/Elsevier
2015 Pfeifer et al. Risk analysis GA Large-scale projects JIIPE/Elsevier
2015 Isa et al. Project performance PLS-SEM construction firms INCIEC/Springer
2015 Parihar et al. Risk management DTA and AHP Transmission line installation project JJBRR/Sage
2015 Cheng and Lu Risk assessment FMEA Pipe jacking construction JAC/Elsevier
2015 Ji et al. Risk assessment FTOPSIS and Hydropower stations ESWA/Elsevier
MCDM
2016 Qazi et al. Project complexity and risks ProCRiM and BBNs Construction projects IJPM/Elsevier
2016 Liu et al. Risk path SEM Chinese int. contractors JCEM/ASCE
2016 Love et al. Cost overrun, PCM Transportation infrastructure projects JTRA/Elsevier
2016 Zhang et al. Safety risk analysis FBNs Tunnel pipeline project RA/Willey
2016 Valipour et al. Risk allocation FCANP PPP construction projects TSPM/Taylor & Francis

(continued )
Year Author (s) Application Method(s) Project Journal/publisher

2016 Islam and Nepal Risk assessment FBBNs Power plant project PCS/Elsevier
2016 Marle and Vidal Managing complexity and high risk GMBA Construction Project MCHRP/Springer
2016 Kabir et al. Risk assessment FBBN and FTA Oil and gas pipelines SIE/Taylor & Francis
2016 Fang et al. Risk analysis RNM Engineering projects SJ/IEEE
2016 Floricel et al. Complexity, uncertainty CCA and MRA Transportation infrastructure projects IJPM/Elsevier
2016 Garbuzova-Schlifter Risk analysis AHP Energy service projects JENPOL/Elsevier
and Madlener
2016 Wang et al. Risk assessment, uncertainty BN Transportation project JSEREA/Springer
2016 Terstegen et al. Risk assessment MCS Plant construction projects AEDSPP/Springer
2016 Hwang et al. Risk interdependencies DEMATEL information system development projects PMJ/Willey
2016 Camós et al. Prediction of damage BN Metro line tunnel TUST/Elsevier
2017 Islam et al. Risk assessment FBBNs Construction projects AEI/Elsevier
2017 Zhang et al. Risk-based estimate MCS, FMET tailings ponds project ASOC/Elsevier
2017 Prascevic and Prascevic Risk management FAHP Construction project JCEM/Taylor & Francis
2017 Demirkesen and Ozorhon Project performance SEM Construction projects EMJ/Taylor & Francis
2017 Floyd et al. Risk management MCS and TOPSIS Construction projects EMJ/Taylor & Francis
2017 Barakchi et al. Cost estimation ANNs Infrastructure projects PE/Elsevier
2017 Vu et al. Risk analysis SEM Highway projects ECAM/Emerald
2017 Samantra et al. Risk assessment FST Metropolitan construction project JEAAI/Elsevier
2017 Kim and Kang Risk and Cost Analysis RA and DA Plant construction KSCE, JCE/Springer
2017 Maurer Project Complexity DSM and DMM Engineering projects CMED/Springer
2019 Park et al. Risk management AHP and FMEA Construction projects IJCE/Springer
2017 Ou-Yang and Chen Cost-risk assessment MCS Petro-chemical plant TCIE/Taylor & Francis
2017 Ahmadi et al. Risk prioritization FAHP and FFMEA Highway construction projects TCEM/Taylor & Francis
2018 Pehlivan and Öztemir Risk Prioritization MCS Construction project EMJ/Taylor & Francis
2018 Zhao et al. Risk management PLS-SEM Construction industry ECAM/Emerald
2018, Adeleke, Bahaudin and Construction risk SEM Construction company Abuja and Lagos, in JSHAW/Elsevier
2018 Kamaruddeen; Adeleke, Nigeria
Bahaudin, Kamaruddeen,
Bamgbade, Salimon, Khan
and Sorooshian
2018 Xu et al. Risk analysis DDES Bridge construction project JAC/Elsevier
2018 Gupta and Thakkar project risk management JRAP and MCS Infrastructure projects SĀDHANĀ/Springer
2018 Yucelgazi and Yitmen Risk assessment ANP transport infrastructure projects AJSE/Springer
2018 Budayan et al. Risk assessment FST Construction projects KSCE JCE/Springer
2018 Kimiagari and Keivanpour Project risk interdependency FANP Large-scale construction projects TPRS/Taylor & Francis
2018 Sinha et al. Decision support framework MCDM and ANP Highway projects TRR/Sage
2019 Shariat et al. Risk analysis FST and MCDM Urban storm-water systems JSTE/Elsevier
projects
Cost overrun in
construction

Table I.
IJMPB construction industry. These methods can address the project complexity and risk
interdependency networks under high cost uncertainty in the system. These methods
consist of different independent multi-criteria approaches and combination of these
independent methods for the management of uncertainty in project outcomes. However,
several drawbacks and criticism have been encountered and consequently, hybrid methods
consisting on AI techniques have been increasingly used to address the system uncertainty
in a better way (Chan et al., 2009; Xu et al., 2018). Each hybrid method explains the cost
contingency framework of risk assessment on different types of projects and under different
uncertainty levels. Thus, in order to find out an appropriate method for evaluating cost
overrun phenomenon, it is important to address the interrelationship between complexity
and risk in a project.
Construction risks and complexity are still overseen dependent on expert’s judgement
and subsequently the information for risk has been considered as mostly quantitative (Aven
et al., 2007). The measurement of project risk and complexity starts through the likelihood of
occurrence and severity of the risk and then being transformed into quantitative measures
to address the interdependencies for project cost (Ock and Han, 2010). Such quantitative
tools are based on different linear and non-linear approaches (Fang and Marle, 2012). As
mostly infrastructure construction projects show stochastic behavior, therefore, non-linear
probabilistic models of AI are dominant to address this phenomenon of interdependency
(Dekker, 2013). These methods employ ANP (Boateng et al., 2015), network theory (Fang
et al., 2012), BBN, MCS and ANNs (Barakchi et al., 2017; Kabir et al., 2016; Lee and Kim, 2017;
Peleskei et al., 2015).
Such probabilistic techniques alone are not appropriate in evaluating the cost-related
risks under uncertainty and due to lacking risk information (Cheng and Lu, 2015).
Conversely, fuzzy techniques are exceptionally productive in modeling the vulnerabilities
experienced in experts’ decisions and have been often utilized as hybridized strategies for
construction risk assessment, throughout the last decade (Chan et al., 2009). Fuzzy
structured methods include, FANP, FBBNs, FMCS and FANNs. In recent studies, few
optimized algorithms called GA and multi-variate SEM are also found to be useful in
measuring project risk interdependencies for the optimal cost solution under uncertainties
(Fang et al., 2013; Liu et al., 2016; Pfeifer et al., 2015). Independent and hybrid approached of
AI techniques which are most frequently used in the construction industry are briefly
discussed in the following subsections.
Analytical network processing (ANP) risk assessment tools that deal with risk effects
independently have raised some concerns of network interdependency. These methods have
limited applications in construction projects where system complexity and uncertainty is
high. Saaty and Vargas (2013) developed ANP (i.e. a generalized form of paired-wise
analytical hierarchy process) method to address the priority of criteria and sub-criteria
having interdependencies between the higher and lower level elements of the system. Unlike
analytical hierarchy process where decision problems are framed in the hierarchy, however,
ANP network resolves the issues in related network structure (Lu et al., 2008). While
addressing the interdependency, ANP evaluates the project cost risks in complex network
interactions (Valipour et al., 2015). The basic limitation of this approach is that it performs a
pair-wise comparison while assigning a crisp value (Huang et al., 2014) to capture
uncertainty and stochastic behavior in risk data of complex projects (Valipour et al., 2015).
Similarly, this pair-wise comparison requires more complex network links and additional
computation if risk elements increase in the system.
Since 2000, ANP has been increasingly used and proved to be the principal method to
handle many project cost-related problems with subjectivity (Bu-Qammaz et al., 2009;
Taroun, 2014). Besides the use of ANP in different areas of construction management, it has
also become an important tool to address interdependencies among interrelated project
risk network (Fang and Marle, 2012; Qazi et al., 2016). Boateng et al. (2015) adopted ANP and Cost overrun in
combined it with a risk priority index for developing an innovative approach to prioritize construction
risks of cost overrun over a network of the mega construction projects. Different studies projects
(Cerić et al., 2013; Chen et al., 2011; Huang et al., 2014; Khademi et al., 2014) have explained
the recent development of ANP for accessing project performance in infrastructure
construction projects but are not limited to assess the interactions between risk and
complexity under high uncertainty. Table II shows the recent years’ applications of the ANP
approach to address the interdependency network of project risk and complexity for
measuring project performance.

3.1 Monte Carlo simulation (MCS)


The development of probability-based AI models and their applications are now better able to
predict and evaluate the propensity of cost overruns and thus provide mitigating strategies to
overcome uncertainty which emerge in mega construction projects. Probabilistic techniques
that better address the interdependencies between complexity and risk elements have been
discussed briefly with their applications in construction projects.
Simulation – a decision-making tool – is based on the probabilistic theory of an event
from historical data. MCS is a useful technique in making better decisions to solve problems
in which uncertainty and variability in information have traditionally distorted forecasts
(Gupta and Thakkar, 2018). It predicts the general outcome of the risks by using random
computation of values that fall inside a predetermined probability distribution regularly by
using three estimates, for example, optimistic, most likely and pessimistic (Low et al., 2009).
Correspondingly, while assuming multiple-iterations within a specified range, MCS gives a
significantly more far-reaching perspective of situation analysis for decision making (Zhang
et al., 2017). In this way, MCS has emerged a promising technique among the various risk
assessment techniques in construction projects (Terstegen et al., 2016) to measure stochastic
behavior of risk while expecting complex interdependencies between project activities and
resources for cost estimation (Ou-Yang and Chen, 2017).
In the past literature, many studies have been found that have recommended an
integrated simulation approach into project risk assessment, as this approach accounts
explicitly for the effects of uncertainty in the project (Fang and Marle, 2012; Peleskei et al.,
2015; Satumtira and Dueñas-Osorio, 2010). In a recent study, Pehlivan and Öztemir (2018)
developed a simulation model to measure the impact of schedule delays on cost overrun.
This model applies a risk integration approach in generating random scenarios and
computes the cost impact of a delayed milestone in the expected budget. A number

Author (s)/year Method (s) Context

Lu et al. (2008) ANP Assessment of construction risk of the urban bridge project
Bu-Qammaz et al. (2009) ANP Risk assessment of international construction projects
Chen et al. (2011) ANP Environmental risk assessment for international hub airports
Cerić et al. (2013) ANP Risk assessment in sustainable ground improvement
Taroun (2014) MCDM Risk assessment in construction projects
Huang et al. (2014) ANP and Exploring the interdependencies in critical infrastructure
DEMATEL projects
Khademi et al. (2014) ANP and AHP Construction risk evaluation in developing countries
Boateng et al. (2015) ANP Risk prioritization in mega construction projects
Qazi et al. (2016) ANP and BBNs Measuring risk paths and modeling project complexity in Table II.
construction projects Applications of ANP
Yucelgazi and ANP Risk assessment in large-scale infrastructure transport in construction risk
Yitmen (2018) projects assessment
IJMPB of studies (Ou-Yang and Chen, 2017; Taillandier et al., 2015) recommend the use of MCS
along with other hybrid techniques in project risk analysis for better forecasting of risk
estimates (see Table III). However, MCS still encounters an issue of recognizing probabilities
in light of the current situation where risk and unpredictability cannot be characterized as
probabilistic nature (Islam et al., 2017; Ock and Han, 2010).

3.2 Artificial neural network (ANN)


A non-parametric model called ANN depends on AI which has been applied for risk analysis
in various kinds of projects. ANN has the ability to learn from the historical record and
produces future outcomes (Kabir et al., 2016). In ANN, the input elements should be prepared
appropriately from past information of similar kind of projects, which occasionally relies on
the performance of the neurons (Sonmez, 2011). ANN frequently produces more precise
results as compare to other traditional techniques (e.g. multi-variate regression analysis).
ANN is perfect in a condition where there is the absence of data within a complex system
(Alex et al., 2010; Odeyinka et al., 2013). Megaprojects are complex in nature, and high
uncertainty exists in risk information (Cheng et al., 2010). Though, ANN models are capable
enough to demonstrate the non-linear relationships exist between the risk factors. But
ANN-based models are appropriate if adequate cost-related information is available.
ANN is extensively used in project risk management process to better estimate the cost
under high complexity and uncertainty. Based on an empirical survey data from 96 UK
construction companies and using the risk theory, Odeyinka et al. (2013) employed ANN
modeling to develop a risk impact assessment model for baseline cost flow forecasting.
Barakchi et al. (2017), in their study of cost estimation methods for transport infrastructure
projects, explained the various applications of ANN as a risk analysis tool in the
construction industry for better cost estimation.
ANN, a probabilistic method, is also integrated with other cost estimation methods in
construction management research for effective forecasting of input risk factors. For
example, ANN is combined with a GA for predicting preliminary cost estimates in complex
construction projects (Cheng et al., 2010; Kim et al., 2005). In a similar way, Kabir et al. (2016)

Author(s)/year Method(s) Context

Low et al. (2009) MCS Risk management practices in Chinese construction firms
Sadeghi et al. (2010) Fuzzy-MCS Risk assessment in construction projects
Ock and Han (2010) Fuzzy-MCS Measurement of risk-related activity durations in projects
Fang and Marle (2012) MCS A risk network model for decision in project risk evaluation
Choudhry et al. (2014) MCS Cost and schedule risk analysis in a bridge construction project
Peleskei et al. (2015) MCS Risk assessment and cost estimation in construction projects
Taillandier et al. (2015) SMACC Multi-agent model for managing risk in a construction project
Saputra and MCS Reliability model considering project scheduling and cost
Latiffianti (2015) trade-off under uncertainty
Alasad and Motawa (2015) MCS Dynamic demand risk assessment framework for toll road
projects
Terstegen et al. (2016) MCS Risk assessment of complex projects under uncertainty
Ou-Yang and Chen (2017) MCS Risk assessment approach for project cost analysis
Zhang et al. (2017) MCS Operational risk and safety estimation in complex projects
under uncertainty
Table III. Islam et al. (2017) MCS Hybrid methods for risk assessment in construction projects
Application areas of Gupta and Thakkar (2018) MCS Quantitative risk assessment methodology for a construction
the MCS method in project
construction risk Pehlivan and MCS Integrated risk of costs and schedule delays in construction
assessment Öztemir (2018) projects
proposed a hybrid method by using ANN in a combination of BBN and fault tree analysis Cost overrun in
for safety risk assessment in energy projects. Additionally, in Table IV, few other studies construction
also suggest the used of ANN in cost-risk analysis in construction management. projects
3.3 Bayesian belief networks (BBNs)
BBN is a graphically designed method, called directed acyclic diagram, where nods denote risk
events and arrows denote the conditional probabilities between the risk events (Liu, 2010). The
arrows signify the dependency between mutually exclusive risk elements inside the risk network
(Weber et al., 2012). In addition, one of the benefits of BBN is that it can update the probabilities
frequently in the system when new information for the input factors become available
(Khodakarami and Abdi, 2014; Wang et al., 2016). BBN has the ability of back-propagation that
helps in measuring the probability of events that may not be observed directly.
The BBN approach explicitly evaluates the vulnerability in project cost, and furthermore
gives a suitable technique to model complex risk interrelationships in any project. Cárdenas
et al. (2013) adopted BBN for risk management in tunnel development and highlight the key
issues of experts’ judgment bias ignored by previous studies. They further suggest the
significance of subjective judgment in BBN to guarantee the reliability of the model’s result.
In another study, Cárdenas et al. (2014) created a probabilistic causal model dependent on
Bayesian network which identifies and evaluates the complex cost-risk network of tunnel
development projects. Khodakarami and Abdi (2014) proposed a quantitative risk
evaluation structure using Bayesian networks for probabilistic risk analysis. Similarly, a
BBN model for the settlement of buildings and other adjacent structures is introduced by
Camós et al. (2016). Qazi et al. (2016) designed a project complexity and risk model by using
BBNs for risk assessment in infrastructure projects. This model characterizes a conditional
path network among complexity and risk interdependencies for cost overrun.
Recently, the effectiveness of BBN in project cost-risk analysis has been found in various
studies ( Johansen and Tien, 2017; Kabir et al., 2016; Zhang et al., 2016) to measure
interdependencies among project complexity and risks factors. In contrast with other risk
evaluation techniques such as ANNs and MCS, BBN has appeared to be a popular technique
in managing cost due to its simplicity for use by experts and its precision of results. Table V
exhibits the use of Bayesian networks in risk assessment of various construction projects.
One of the present constraints in BBN is that it can only deal in discrete functions. Although,
there are few other phenomena which ought to be considered with continuous nature of
functions, for example, operational and environmental factors ( Johansen and Tien, 2017;
Zhang et al., 2016). Because of the absence of adequate information for the risk evaluation in

Author (s)/year Method(s) Context

Kim et al. (2005) ANN and GA A hybrid model for predicting preliminary cost estimates
Chan et al. (2009) Fuzzy sets and Hybrid Fuzzy hybrid methods in construction management
methods research
Alex et al. (2010) ANN Risk modeling for cost estimation
Cheng et al. (2010) GA, fuzzy logic and Fuzzy hybrid neural network for cost estimation in the
ANN construction industry
Sonmez (2011) ANN Construction cost estimation using artificial intelligence
Odeyinka et al. (2013) ANNs Cost flow risk assessment model
Kabir et al. (2016) ANNs, BBNs and FTA Risk assessment in energy projects Table IV.
Valipour et al. (2016) Fuzzy-cybernetic and Hybrid fuzzy cybernetic model to identify shared risks in Application areas of
ANP projects the ANN method in
Islam and Nepal (2016) Fuzzy-Bayesian model Risk assessment in power plant projects construction risk
Barakchi et al. (2017) ANN Cost estimation methods for transport infrastructure projects assessment
IJMPB Author (s)/year Method(s) Context

Liu (2010) BBN Inference on risks of construction schedule-cost


Sonmez (2011) BBN Range estimation of construction costs using artificial
intelligence
Weber et al. (2012) BBN Applications risk analysis and maintenance areas
Fang and Marle (2012) Simulation and BBN A risk model for decision support in project risk management
Khakzad et al. (2013) Object-oriented BN Risk analysis of offshore drilling operations
Khodakarami and BN Modeling dependencies between project cost items
Abdi (2014)
Cárdenas et al. (2014) BBN Risk integration for cost estimation in the tunneling project
Wang et al. (2016) BBN Risk assessment for an infrastructure construction project
Kabir et al. (2016) FBBN Risk assessment in energy projects
Islam and Nepal (2016) Fuzzy logic and BBN Risk assessment in power plant projects
Zhang et al. (2016) Fuzzy logic and BBN Safety risk analysis of tunnel-induced pipeline damage
Table V. Qazi et al. (2016) BBN Project complexity-driven risk paths in construction projects
Application areas of Islam et al. (2017) FHMs Applications of hybrid methods for risk analysis in
BNNs method in construction-related projects
construction risk Johansen and BN Multi-scale modeling of interdependencies between critical
assessment Tien (2017) infrastructures

complex construction projects, BNN can be effective to produce adequate results in limited
experts’ judgment.

3.4 Genetic algorithm (GA)


The complexity underlying the interdependencies among project risks is modeled and
represented in terms of a risk network (Floricel et al., 2016). The challenge of appropriate
risk planning is rendered in difficulty due to resource constraints. In accordance, reliable
analytical methods can help experts to plan risk response activities that optimize the
allocation of resources (Fang et al., 2013). The use of GA with other tools as a hybrid method
is increasingly being used to search for the optimal construction project time and cost trade-
off under different risk levels (Proon and Jin, 2011). This technique helps to find the ideal
balance of the time and costs under different risk levels as characterized by decision makers.
GA is a probabilistic search strategy dependent on Darwin’s principle of “survival of the
fittest,” and has quickly turned into a mainstream evolutionary technique for the solution of
complex combinatorial optimization problems (Pfeifer et al., 2015). Various applications of
GA for cost optimization have been found in literature, and Table VI illustrates the recent
year’s applications of GA in construction risk management.

3.5 Structure equation modeling (SEM)


SEM is viewed as: to recognize a causal connection between dependent and independent
variables under observation; and to signify the direct and indirect impacts between

Author (s)/year Method(s) Context

Kim et al. (2005) ANN and GA A hybrid model for predicting preliminary cost estimates
Table VI. Chan et al. (2009) Hybrid methods Fuzzy theory and GA in construction management
Application areas of and GA
GA method in Proon and Jin (2011) GA A tool for the resource-constrained project scheduling problem
construction risk Fang et al. (2013) GA Risk planning under resource constraints in engineering projects
assessment Pfeifer et al. (2015) GA Quantification of risks in project delays
multiple variables (Chandra, 2015; Liu et al., 2016). In a similar way, SEM measures the Cost overrun in
complexity and risk interdependencies through path analysis by using crisp values (Lu construction
et al., 2015). Risk assessment using SEM has been increased in the construction projects
management domain where complex relationships exist (Isa et al., 2015; Qureshi and Kang,
2015; Sambasivan et al., 2017). For example, Eybpoosh et al. (2011) employed SEM to
calculate the interdependency coefficients of risk-related factors and the impact of each risk
path on project cost overrun. Lu et al. (2015) built up an estimation model of project
complexity for mega construction projects from task and organizational point of view.
Likewise, Yildiz et al. (2014) proposed a knowledge-based risk mapping tool to assess
potential risk paths that may generate cost overrun problem in global markets. Moreover,
Liu et al. (2016) also investigated the risk paths in international construction projects and
measured the risk severity for project performance. In addition, various other applications of
SEM in construction risk management are presented in Table VII.
One of the limitations of SEM is that it does not assume the uncertainty and stochastic
behavior of events (Adeleke, Bahaudin, Kamaruddeen, Bamgbade, Salimon, Khan and
Sorooshian, 2018; Adeleke, Bahaudin and Kamaruddeen, 2018). This multi-variate model is
suitable only to find complex interactions of system elements where uncertainty is low.
Alternatively, fuzzy logic can be used as hybrid techniques to predict phenomenon with
high uncertainty. SEM has limited applications for complex projects, under high
uncertainty, and where limited and vague information is available.

3.6 Fuzzy hybrid methods (FHMs)


AI-based hybrid methods have been extensively used for risk assessment in complex
projects. These methods effectively cover the uncertainty and stochastic behavior of project
risk events (Floyd et al., 2017). Fuzzy techniques are exceptionally productive in measuring
the vulnerabilities experienced in complex construction projects and have been widely
adopted as hybridized strategies for construction risk assessment in the previous decade
(Samantra et al., 2017). Fuzzy structured hybrid methods, which are able to capture the
interdependencies in between the complexity and risk factors, are comprised of FANP

Author(s)/year Method(s) Context

Kim et al. (2009) SEM Prediction model of project performance for international
construction projects
Eybpoosh et al. (2011) SEM Identification of risk paths in international construction
projects
Yildiz et al. (2014) SEM Risk mapping tool for cost estimation of international
construction projects
Qureshi and Kang (2015) SEM Analyzing the organizational factors of project complexity
Chandra (2015) SEM Risk factors affecting project success
Lu et al. (2015) SEM Measuring project complexity for large-scale projects
Isa et al. (2015) SEM Factors influencing the performance of Malaysian
construction firms
Liu et al. (2016) SEM Risk assessment in international construction projects
Sambasivan et al. (2017) SEM Risk analysis of construction delays in the Tanzanian
construction industry
Adeleke, Bahaudin and SEM Construction risk management among Nigerian Table VII.
Kamaruddeen (2018) construction companies Application areas of
Adeleke, Bahaudin, Kamaruddeen, SEM Influence of organizational external factors on the SEM method in
Bamgbade, Salimon, Khan and construction risk management construction risk
Sorooshian (2018) assessment
IJMPB (Shafiee, 2015), FBBN (Kabir et al., 2016), FANN (Ebrat and Ghodsi, 2014) and FMCS
(Sadeghi et al., 2010).
3.6.1 Fuzzy set theory (FST). Construction experts are required to manage complex
construction issues under states of uncertainty and vulnerability (Zayed et al., 2008).
A well-recognized decision tool for uncertainty measurement called fuzzy logic allows the
vulnerability of the risk events based on the subjective linguistic assessment. The FST
exclusively addresses an issue in the form of a full or non-membership function.
Construction risks are not normally characterized in this way due to the complex and
uncertain nature of the problems (Lin and Jianping, 2011). Conversely, FST adjusts basic
binary logic to catch vagueness and uncertainty in characterizing risk (Zhang et al., 2017).
Fuzziness is a transformation process of an element in a set from its non-membership to
membership state. This quantitative risk analysis model contains a three-step risk analysis
system representation, i.e.,FST, fuzzy set evaluation of risks and linguistic approximation
(Kabir et al., 2016). The basic limitation of fuzzy models is that they do not consider the
complex interrelationship effects of risks within or beyond the group (Islam et al., 2017).
Consequently, they treat the independent state of risk under high uncertainty in a system.
Thus, other methods are used in combination of fuzzy logic to address the complexity and
uncertainty of interdependent risk events in a system.
3.6.2 Fuzzy-analytical network processing (FANP). ANP and design structure method in
the network theory (Fang et al., 2012) assign absolute values in the pair-wise assessment of
risks and do not consider the vagueness and vulnerability in risk analysis. Accordingly,
applying fuzzy logic with ANP overcomes this limitation of risk measurement (Valipour
et al., 2015). The FANP first recognizes potential risk factors and their interdependencies
and then constructs a network model demonstrating their weighted connections. FANP
consists of multiple step-wise processes, such as a pair-wise comparison between the risks
utilizing an appropriate fuzzy linguistic scale, calculation of consistency ratio, calculation of
priority weights matrix, a creation of super-matrix and ranking of risk scores (Shafiee, 2015;
Valipour et al., 2016).
To overcome the vagueness and vulnerability in cost-risk data of subjective judgments,
different researchers have been trying to integrate fuzzy logic with ANP while addressing
complex issues (He et al., 2015; Islam et al., 2017). Lin and Jianping (2011) employed MCDM
criteria to assess the risks of new campus construction project by consolidating fuzzy theory
and ANP method. Taroun (2014), in his research, examined the effectiveness of FANP in
construction risk assessment. Shafiee (2015) has also proposed a FANP approach to choose
the most appropriate risk analysis tool for offshore wind farms. Valipour et al. (2016)
designed a quantitative risk allocation methodology and characterized potential risk factors
in freeway public–private partnership (PPP) projects using FANP technique. They display a
methodology as an FHM and Cybernetic ANP for identifying shared risks.
3.6.3 Fuzzy Monte Carlo Simulation (FMCS). To overcome the shortcoming of
probabilistic nature of risk in certain circumstances, Sadeghi et al. (2010) presented a novel
approach for risk evaluation comprises of fuzzy logic and simulation. Similarly, Ock and Han
(2010) also presented a schedule and cost-risk measurement strategy while using the FST and
MCS for assessing risk-related activities while considering the uncertainties in risk elements.
The fuzzy-simulation approach is quite helpful to assess the dependencies among risk element
under high uncertainties, exist in complex construction projects (Islam and Nepal, 2016).
However, the fuzzy-simulation method is not simple for mega construction projects because, in
the absence of adequate information, this hybrid technique is also not reliable for decisions
and is unable to present true interdependencies among risk factors (Islam et al., 2017).
3.6.4 Fuzzy-artificial neural network (FANN). Uncertainty in the expert’s judgment is
because of ignorance, ambiguity, and imprecision in assessing the project task
(Valipour et al., 2016). This vulnerability cannot be evaluated through the conventional ANN Cost overrun in
model; therefore, the FST is frequently being adopted to overcome this limitation (Islam construction
et al., 2017; Odeyinka et al., 2013). In their work, Chan et al. (2009) recommended to use an projects
integrated approach of fuzzy logic and ANN for better risk modeling in construction
management. Jin (2010) and Cheng and Lu (2015) developed a synthesized fuzzy inference
model for tasks and cost management in the construction industry, by joining FST and
neural network techniques taken as the core component of the neuro-fuzzy DSS. The DSS
results demonstrate that the system can suggest effective risk assessment strategies for
PPP infrastructure projects with high accuracy. Afterwards, a number of other studies
(Odeyinka et al., 2013; Valipour et al., 2015) also followed this approach for risk assessment
and cost estimation, but failed to address the risk dependencies in network structure with
limited data availability.
3.6.5 Fuzzy-Bayesian belief network (FBBN). Because of the high uncertainty or the
qualitative nature of risk information, it is difficult for experts to make the right decisions
with absolute crisp numbers (Zhang et al., 2017). Fuzzy logic supports in decisions to
measure the likelihood and impact of risk in membership function linguistically.
Subsequently, an integration of fuzzy logic and Bayesian theory presents an important role
in assisting project risk analysis under complex and uncertainty (Kabir et al., 2016).
Špačková et al. (2013) adopted a Bayesian network approach to evaluate the cost and
schedule overrun in tunnel construction and developed the procedure of consistently
updating construction time and cost estimation. Based on fuzzy logic and Bayesian
probability strategy, Camós et al. (2016) presented a reliability-based model for damaging
impact of tunnel construction on the other neighboring infrastructures. Contrasted with
other probabilistic techniques, this technique can adapt to the learning of continues dynamic
changes in parameters and hidden vulnerabilities with limited information. Zhang et al.
(2016) used the fuzzy-BBN approach for the safety of pipeline damage in a tunnel
construction project. Based on the quantitative risk data and subjective judgment of
different risk factors, this model measures the probabilities of pipeline safety risks. Kabir
et al. (2016) developed a safety evaluation model for the failure of oil and gas pipelines by
integrating fuzzy logic with BBN. This proposed hybrid method overtly expresses the
dependencies of events and constantly updates the probabilities under uncertainty. Though,
recent studies show the popularity of similar FBBNs for presenting uncertain information in
probabilistic frameworks to address a range of risk analysis problems in construction
(Wang et al., 2016). In this perspective, the researchers recommend using fuzzy logic for
handling vagueness or uncertainty of cost overrun and Bayesian theory for complexity, if
limited information is available (Islam et al., 2017).
A number of other AI-based hybrid methods except for FBBNs are found in construction
risk assessment for complexity and risk interdependency measurement, for example, GA is
being used as an integrated method with other MCDM methods for optimizing solution in
risk assessment (Cheng et al., 2010; Kim et al., 2005; Proon and Jin, 2011). But, these methods
have limited applications in order to address the complexity and risk dependencies because
of limited risk information and high uncertainty (Arashpour et al., 2017; Cienfuegos, 2013;
Fang and Marle, 2012). Table VIII illustrates the applications of FHM in construction
projects, used to measure project uncertainty and complex relationships of risk factors.

4. Discussion and future research directions


Over the years, diversified AI tools have been used for risk and uncertainty analysis in order
to manage cost overrun issues in construction. Among these, AI-based hybrid methods are
predominantly adopted for risk identification, assessment and prioritization in different
sectors of the construction industry (Abdelgawad and Fayek, 2012; Kim et al., 2005).
IJMPB Author(s)/year Method(s) Context

Lin and Hsu (2008) FANP Quantitative techniques to measure the performance of
the project
Chan et al. (2009) Fuzzy sets and Techniques in construction management research
hybrid methods
Sadeghi et al. (2010) FMCS Risk assessment in construction projects
Cheng et al. (2010) GA, fuzzy logic Cost estimates using a fuzzy hybrid neural network in the
and ANN construction industry
Jin (2010) Neuro-fuzzy DSS Efficient risk evaluation in PPP projects
Ock and Han (2010) Fuzzy set and MCDM Measuring risk-related activity's duration
Taroun et al. (2011) TOPSIS, AHP and Risk modeling in project management
simulation
Špačková et al. (2013) Dynamic BNs Risk assessment of tunnel construction project
Odeyinka et al. (2013) FANNs Cost flow risk assessment model
Jato-Espino et al. (2014) FTOPSIS and ANP Applications in project risk management
Valipour et al. (2015) FANP Method for risk prioritization in freeway PPP projects
Shafiee (2015) FANP FANP model to mitigate the risks associated with
offshore wind farms
Ji et al. (2015) Fuzzy-MCDM Risk assessment of hydropower stations
He et al. (2015) FANP Measuring the complexity of mega construction projects
in China
Zhang et al. (2016) FBBN Safety risk analysis of tunnel-induced pipeline damage
Valipour et al. (2016) Fuzzy-cybernetic and Model to identify shared risks in PPP projects
ANP
Kabir et al. (2016) FBBNs Safety assessment of oil and gas pipelines
Islam and Nepal (2016) Fuzzy logic and BBNs Risk assessment in power plant projects
Islam et al. (2017) Fuzzy logic and BBNs Hybrid methods for construction risk assessment
Table VIII. Prascevic and Prascevic FANP Ranking and selection of alternatives in construction
Fuzzy hybrid methods (2017) project management
in construction risk Shariat et al. (2019) FTOPSIS Risk analysis of urban storm-water infrastructure systems
assessment using fuzzy spatial multi-criteria decision making

Similarly, the FST technique is predominantly used along with AI methods to overcome the
issue of uncertainty in risk data (Samantra et al., 2017). However, it has been observed that
in order to address cost overrun issues, a comprehensive risk assessment framework for
complex projects is lacking to capture risk interdependencies under high uncertainty
(Khodakarami and Abdi, 2014). Islam et al. (2017) aptly found some limitations in current
risk evaluation tools which measure the uncertainties in cost estimates, such as the way of
dealing with subjective judgments. Consequently, they have recommended a comprehensive
risk management system that incorporates a risk classification methodology for decision
making but did not propose an explicit methodology to address risk interdependencies in a
complex project network.
To design flexible risk assessment tools for cost overrun under high uncertainty, few
studies have adopted hybrid methods based on the FST and other AI tools (Amiri and
Golozari, 2011; Samantra et al., 2017; Shariat et al., 2019). Because of the additional
advantages of risk evaluation beyond likelihood and impact of risk, these AI-based hybrid
methods are predominating for cost-risk evaluation in mega construction projects, such as
in transport and tunnel construction projects (Amiri and Golozari, 2011). The fuzzy system
deals with the uncertainties and has a limitation of dealing with dependencies, as it
considers risk effects independently (Ahmadi et al., 2017). Therefore, the FST alone in risk
assessment has failed to cope with risk dependencies. Consequently, an integrated approach
to address cost uncertainty and interdependencies is required for risk assessment in mega
construction projects (Cárdenas et al., 2013; Taroun, 2014).
In last decades, studies have shown the progress which has been done to capture the Cost overrun in
interdependencies among risk factors (Marle and Vidal, 2011), for example, ANP allows to construction
measure interdependencies between the project risks through pair-wise comparison matrix projects
(Khademi et al., 2014; Yucelgazi and Yitmen, 2018). The researchers have hybridized the
fuzzy logic methodology with ANP and often used it for uncertainty modeling in bridge
construction, tunnel construction and other construction-related projects (He et al., 2015;
Shafiee, 2015). But these tools have failed to address these interdependencies with limited
data availability (Odeyinka et al., 2013). Furthermore, the pair-wise comparison process in
FANP becomes tedious and lengthy as the number of causal relationships of variables
increase, which appears to be a big hindrance in the computation of super-matrix. Like ANP,
few aforementioned methods such as SEM (Chandra, 2015), ANNs (Barakchi et al., 2017),
BBNs (Špačková et al., 2013) also address the presence of interdependencies between the
complexity and risk factors. The major issue with SEM is that unless there is no hindrance
to explain the multiple interdependencies but, SEM is effective only if the sample size of
subjective observations is large (Liu et al., 2016). In addition, SEM only deals with crisp
values and does not consider the uncertainty in risk assumptions. Historically, cost-risk
assessment in construction projects is heavily relying on the subjective judgment of
construction experts to measure the severity of the risk. Nevertheless, retrieving sufficient
risk data from industry experts is time-consuming, and, in addition to this, ambiguity and
vagueness exist in subjective data.
Similarly, the fuzzy-simulation approach is quite helpful to assess the interdependencies
among risk factors under high uncertainty exists in complex construction projects (Islam
and Nepal, 2016). In the absence of adequate information, this simulation technique is
unrealistic for analysis and is not capable of exhibiting the interrelationship between risk
factors (Islam et al., 2017). Different other hybrid methods except for the use of fuzzy logic
are also applied for risk assessment in construction, but the application of these methods are
limited and they do not consider the uncertainty exists in the complex system (Abdelgawad
and Fayek, 2012; Floyd et al., 2017). Evidently, Bayesian network appears to be an effective
tool which successfully addresses the limitations of ANP, SEM, ANNs and MCS, but
requires an absolute value of probability of each risk factor. However, in case of time
constraints, and the absence of experience and knowledge, it is hard to get the right
information from experts. This limitation of subjective data raises the concern of
uncertainty in risk information (Khodakarami and Abdi, 2014; Weber et al., 2012).
Though a comprehensive risk assessment framework is required that can address the
uncertainty or imprecision of risk and can capture the interdependencies among
complexity and risk factors to control the project cost overrun. The risk is usually
recorded in the form of likelihood and magnitude of the impact of that risk in absolute
value. However, one of the drawbacks of this method is that it does not consider the
uncertainty and vagueness of risk during the experts’ judgment process (Valipour et al.,
2015). The effect of construction risks relies upon various elements, such as
organizational, technical and environmental, with most being recorded in linguistic
judgments (Sadeghi et al., 2010) that require an additional method to measure this
vagueness. The consideration of risk vulnerability in the risk assessment process has
appeared to be an innovative approach while dealing interdependencies (Islam et al., 2017).
Moreover, the level of uncertainty in a project signifies the manageability of project risks
and adheres to implement its role on project progress (Floricel et al., 2016).
Recent studies show that BBN is capable enough to handle the complex relationships
between the risk elements (Kabir et al., 2016). However, due to its limitation of dealing with
absolute probability data for analysis, the vulnerability of risks cannot be evaluated.
However, sometimes, the use of BBN in risk assessment is deemed to be inadequate in
construction risk management. This limitation is needed to address by using a hybrid
IJMPB method which measures the vulnerability of risks in a complex relationship (Shafiee, 2015).
The FST is capable enough in managing the uncertainty of risks (Ahmadi et al., 2017), which
overcomes the limited applications of BBN by addressing the range of probabilities in the
form of membership functions rather in absolute crisp values (Islam and Nepal, 2016;
Kimiagari and Keivanpour, 2018; Taroun, 2014). Therefore, a hybrid risk assessment
framework of fuzzy logic and BBN is appropriate to resolve uncertainty issues and capture
interdependencies between complexity and risks factors. Additionally, credal networking
(Qu and Tang, 2010), an extended version of the Bayesian network, also deals with a range
of probabilities and overcome the limitation of probability inference of single value.
With the fuzzy-BBN hybrid approach, fuzzy logic initially characterizes and measures
assessment criteria (i.e. likelihood and magnitude of risk) as per the subject evaluation of
experts in the pair-wise comparison matrix and then transforms them into fuzzy
membership functions (Kimiagari and Keivanpour, 2018). Then it applies fuzzy logic to
define the links between input function (risk probability) and output function (risk severity
level). Later, a fuzzy arithmetic-mean is used to convert and aggregate the fuzzy
membership results in an absolute value (Mehlawat and Gupta, 2016; Valipour et al., 2015).
While addressing cost overrun issues in construction, Bayesian network has appeared a
popular method for the handling of complex interdependencies between complexity and
risks factors (Khakzad et al., 2013). For an appropriate risk assessment in construction
projects, the FBBN approach may ensure the uncertainty in a range of probabilities and
complexity-risk interdependencies through the conditional Bayesian theory but with the
additional properties of a comparison matrix of judgments and a credal network (Qu and
Tang, 2010). This extended strategy can be exhibited for cost-risk assessment by
considering the risks of various kinds of mega-projects, for example, tunnel construction,
power plants and other construction projects.
In recent studies, Zhang et al. (2016) presented a model based on FBBN for risk analysis
which reveals the cause-effect relationships between the pipeline damage and its influential
variables. Islam and Nepal (2016) used a novel approach of fuzzy logic and BBN, which
resolves the limitations of existing risk models and gives the best result for finding risks in
power plant construction project. Similarly, Kabir et al. (2016) designed a risk assessment
model for oil and gas pipeline failure by combining fuzzy logic into the Bayesian network.
All these models consider an absolute value of probability rather look into a range of
probabilities. Similarly, the proposed expanded FBBN model particularly demonstrates the
interdependencies between complexity and risk factors, updating a range of probabilities
and addressing cost uncertainty. Evidently, FBBN is appeared to be a potential AI-based
hybrid approach that can be extended and applied to a wider scope of cost-risk management
studies in different construction-related projects.
In summary, the findings of this study are different from the previous reviews of
construction industry research (Islam et al., 2017; Kabir et al., 2016; Marle and Vidal, 2016;
Qazi et al., 2016). Previous risk analysis tools have some limitations on probability data
obtained from experts, and require an extensive flow of subjective information, which is
quite impossible in case of construction projects. The findings of this study suggest
different key implications for future research, such as: the assessment and evaluation of
complexity-risk interdependency network for cost-risk analysis in construction project
where cost uncertainty is high; and the study also suggests a new AI-based hybrid tool of
fuzzy logic and BBN for cost-risk assessment that could better address the vulnerability
and complexity in the project system. In most cases, because of the high uncertainty of
subjective risk information, project risk information is unrealistic (Odeyinka et al., 2013;
Yucelgazi and Yitmen, 2018). The extended FBBN processes limited subjective
information of risk into a range of probabilities, and then develops a model to capture
complex risk relationships in the network. Similarly, for a practical point of view, the
study has emphasized that the construction experts and managers should consider the Cost overrun in
existence of interdependency between complexity and complexity-driven risk factors in construction
their project risk planning particularly in order to address the cost overrun problems in projects
construction industry. In addition, the study concludes that extended FBBN has the
potential to solve the complex interdependencies between complexity and risk factors
with limited subjective risk assessment data and under high uncertainty. This proposed
hybrid tool in risk assessment approach has a significance of addressing cost overrun
issues in mega construction projects.

5. Conclusions and limitations


The problem of cost overruns in construction projects is due to the uncertainty of risk
information and the complexity of risk network. So far, many risk assessment models
have adopted the AI-based hybrid methods to solve the complexity and uncertainty of risk
information of construction projects. This paper gives a detailed understanding of risk
assessment tools for cost overrun in order to capture the complex risk interdependencies
in construction management disciplines. Most of the literature has been retrieved from
major journals and top publishers from 2008 to 2018. The content analysis reveals the
popularity of hybrid types of AI methods in construction, such as FANP, FMCS, FANNs
and FBBNs.
In dealing with the uncertainty and complexity of risk relationship, FHMs are regarded
as a practical tool for risk measurement under a condition of cost overrun. Additionally,
fuzzy synthetic assessment has often been applied for risk measurement in different
complex construction projects, such as the construction of infrastructures, buildings
and tunnels. Due to the limitations of the above risk assessment tools (i.e. limited
subjective data, complex calculations, several variables and updating additional
information in existing structure) of risk assessment tools, the extended FBBN has
appeared to be a new method for future studies in the field of construction risk
management. Because fuzzy structured methods can easily measure the uncertainty and
fuzziness in risk information by comparison matrix evaluation process. Without affecting
the reliability of the model, Bayesian network provides an appropriate method for
modeling the interdependence of complexity and risk factors in order to address cost
overrun problem in construction.
However, these FBBN hybrid models also encounter some limitations. Both fuzzy
structured and Bayesian networks have some constraints in risk modeling and uncertainty
measurement while dealing with an extensive number of variables. The way of developing
interdependencies and its reliability depends entirely on the knowledge and experience of
construction experts, which is rather difficult (Hazza et al., 2014; Islam et al., 2017).
Borgonovo (2006) has explained some uncertainty measurement approaches, such as
Spearman or Pearson correlation coefficient and analysis of variance, which can be
effectively used for uncertainty analysis, and subsequently to discover the model validity.
Therefore, in the future, the role of FBBN in risk scoring can be enhanced by applying
recommended reasonable uncertainty estimation techniques.
Limited studies have been found which explicitly address the qualification of subjective
evaluation of risk data, and confirm the reliability of the model due to the stochastic nature
of the results (Kabir et al., 2016). The study can be extended to interpret the input data
required to deal with uncertainties, rather than relying solely on subjective judgments in
risk assessment analysis. BBN only deals with discrete variables, but risk phenomena
should be considered as a continuous nature, such as operational and environmental risks in
the project ( Johansen and Tien, 2017). An important research topic in the future is the
development of hybrid BBN inference algorithms, which can solve the continuous state
problem of risk variables.
IJMPB Glossary
ANFIS Adaptive neuro-fuzzy inference system
ANN Artificial neural network
ANP Analytical network processing
BBN Bayesian belief network
BN Bayesian network
BND Bayesian networks dependability
CA Cluster analysis
CCA Canonical correlation analysis
DA Descriptive analysis
DA Discriminant analysis
DBNs Dynamic Bayesian networks
DDES Dynamics discrete event simulation
DEMATEL Decision making trial and evaluation laboratory
DMM Dependency mapping matrix
DSM Design structure matrix
DSS Decision support system
DST Dempster-shafer theory
DTA Decision tree analysis
ETA Event tree analysis
ETA Event tree analysis
FANN Fuzzy-ANN
FANP Fuzzy-ANP
FBBN Fuzzy-BBN
FCM Fuzzy cognitive maps
FEM Fuzzy evaluation model
FHM Fuzzy hybrid method
FLSSVM Fuzzy least squares support-vector machine
FMCDM Fuzzy multiple criteria decision making
FMCDM Fuzzy-MCDM
FMCS Fuzzy-MCS
FMEA Failure mode and effects analysis
FMET Fuzzy matter-element theory
FST Fuzzy set theory
FTA Fault free analysis
FTOPSIS Fuzzy-TOPSIS
GA Genetic algorithm
GMBA Graph- and matrix-based approaches
HoPC House of project complexity
HRA Hierarchical regression analysis
IRMA Integrated risk management approach,
JRAP Judgmental risk analysis process
LPA Linear programming algorithm
LR Linear regression
LSSVM Least squares support-vector machine
MAS Multi-agent simulation
MBM Matrix-based method
MCDM Multi-criteria decision model
MCS Monte Carlo simulation
MRA Multiple regression analysis
NFDSS Neuro-fuzzy decision support system Cost overrun in
NN Neural network
OBN Object-oriented Bayesian network
construction
PCM Probabilistic causation mechanisms projects
PLS-SEM Partial least square structural equation modeling
ProCRiM Project complexity and risk management
PTA Probabilistic tree analysis
RNM Risk network model
SEM Structural equation modeling

References
Abdelgawad, M. and Fayek, A.R. (2012), “Comprehensive hybrid framework for risk analysis in the
construction industry using combined failure mode and effect analysis, fault trees, event trees,
and fuzzy logic”, Journal of Construction Engineering and Management, Vol. 138 No. 5,
pp. 642-651.
Adeleke, A.Q., Bahaudin, A.Y. and Kamaruddeen, A.M. (2018), “Organizational internal factors and
construction risk management among Nigerian construction companies”, Global Business
Review, Vol. 19 No. 4, pp. 921-938.
Adeleke, A.Q., Bahaudin, A.Y., Kamaruddeen, A.M., Bamgbade, J.A., Salimon, M.G., Khan, M.W.A. and
Sorooshian, S. (2018), “The influence of organizational external factors on construction risk
management among Nigerian construction companies”, Safety and Health at Work, Vol. 9 No. 1,
pp. 115-124.
Ahmadi, M., Behzadian, K., Ardeshir, A. and Kapelan, Z. (2017), “Comprehensive risk management
using fuzzy FMEA and MCDA techniques in highway construction projects”, Journal of Civil
Engineering and Management, Vol. 23 No. 2, pp. 300-310.
Alasad, R. and Motawa, I. (2015), “Dynamic demand risk assessment for toll road projects”,
Construction Management and Economics, Vol. 33 No. 10, pp. 799-817.
Alex, D.P., Hussein, M., Al, Bouferguene, A. and Fernando, S. (2010), “Artificial neural network model
for cost estimation: city of Edmonton’s water and sewer installation services”, Journal of
Construction Engineering and Management, Vol. 136, July, pp. 745-756.
Amiri, M. and Golozari, F. (2011), “Application of fuzzy multi-attribute decision making in determining
the critical path by using time, cost, risk, and quality criteria”, International Journal of Advanced
Manufacturing Technology, Vol. 54 Nos 1–4, pp. 393-401.
Arashpour, M., Abbasi, B., Arashpour, M., Reza Hosseini, M. and Yang, R. (2017), “Integrated
management of on-site, coordination and off-site uncertainty: theorizing risk analysis within a
hybrid project setting”, International Journal of Project Management, Vol. 35 No. 4, pp. 647-655.
Aven, T., Vinnem, J.E. and Wiencke, H.S. (2007), “A decision framework for risk management, with
application to the offshore oil and gas industry”, Reliability Engineering and System Safety,
Vol. 92 No. 4, pp. 433-448.
Bai, L. and Li, F. (2013), “The model of project risk assessment based on BP neural network algorithm”,
IEEE Proceedings of 2013 3rd International Conference on Computer Science and Network
Technology, pp. 326-329.
Barakchi, M., Torp, O. and Belay, A.M. (2017), “Cost estimation methods for transport infrastructure: a
systematic literature review”, Procedia Engineering, Vol. 196, June, pp. 270-277.
Beckers, F., Silva, E., Chiara, N., Flesch, A., Maly, J. and Stegemann, U. (2013), “A risk-management
approach to a successful infrastructure project”, McKinsey & Company, Singapore.
Boateng, P., Chen, Z. and Ogunlana, S.O. (2015), “An analytical network process model for risks
prioritisation in megaprojects”, International Journal of Project Management, Vol. 33 No. 8,
pp. 1795-1811.
IJMPB Borgonovo, E. (2006), “Measuring uncertainty importance: investigation and comparison of alternative
approaches”, Risk Analysis, Vol. 26 No. 5, pp. 1349-1361.
Budayan, C., Dikmen, I., Talat Birgonul, M. and Ghaziani, A. (2018), “A computerized method for delay
risk assessment based on fuzzy set theory using MS ProjectTM”, KSCE Journal of Civil
Engineering, Vol. 22 No. 8, pp. 2714-2725.
Bu-Qammaz, A.S., Dikmen, I. and Birgonul, M.T. (2009), “Risk assessment of international construction
projects using the analytic network process”, Canadian Journal of Civil Engineering, Vol. 36
No. 7, pp. 1170-1181.
Camós, C., Špačková, O., Straub, D. and Molins, C. (2016), “Probabilistic approach to assessing and
monitoring settlements caused by tunneling”, Tunnelling and Underground Space Technology,
Vol. 51, pp. 313-325.
Cantarelli, C.C., Van Wee, B., Molin, E.J.E. and Flyvbjerg, B. (2012), “Different cost performance:
different determinants? The case of cost overruns in Dutch transport infrastructure projects”,
Transport Policy, Vol. 22, pp. 88-95.
Cárdenas, I.C., Al-jibouri, S.S.H., Halman, J.I.M. and van Tol, F.A. (2013), “Capturing and integrating
knowledge for managing risks in tunnel works”, Risk Analysis, Vol. 33 No. 1, pp. 92-108.
Cárdenas, I.C., Al-Jibouri, S.S.H., Halman, J.I.M. and van Tol, F.A. (2014), “Modeling risk-related
knowledge in tunneling projects”, Risk Analysis, Vol. 34 No. 2, pp. 323-339.
Caron, F. (2013), Managing the Continuum: Certainty, Uncertainty, Unpredictability in Large
Engineering Projects, Springer, Milan, available at: https://doi.org/10.1007/978-88-470-5244-4
Cerić, A., Marčić, D. and Kovačević, M.S. (2013), “Applying the analytic network process for risk
assessment in sustainable ground improvement”, Građevinar, Vol. 65 No. 10, pp. 919-929.
Chan, A.P.C., Chan, D.W.M. and Yeung, J.F.Y. (2009), “Overview of the application of ‘fuzzy techniques’
in construction management research”, Journal of Construction Engineering and Management,
Vol. 135 No. 11, pp. 1241-1252.
Chandra, H.P. (2015), “Structural equation model for investigating risk factors affecting project success
in Surabaya”, Procedia Engineering, Vol. 125, pp. 53-59.
Chang, C.-W. (2014), “Develop a ranking algorithm for the green building project”, Quality & Quantity,
Vol. 48 No. 2, pp. 911-921.
Chen, Z., Li, H., Ren, H., Xu, Q. and Hong, J. (2011), “A total environmental risk assessment model
for international hub airports”, International Journal of Project Management, Vol. 29 No. 7,
pp. 856-866.
Cheng, M. and Hoang, N. (2014), “Risk score inference for bridge maintenance project using
evolutionary fuzzy least squares support vector machine”, Journal of Computing in Civil
Engineering, Vol. 28 No. 3, pp. 1-10.
Cheng, M. and Lu, Y. (2015), “Developing a risk assessment method for complex pipe jacking
construction projects”, Automation in Construction, Vol. 58, pp. 48-59.
Cheng, M.-Y., Tsai, H.-C. and Sudjono, E. (2010), “Conceptual cost estimates using evolutionary fuzzy
hybrid neural network for projects in construction industry”, Expert Systems with Applications,
Vol. 37 No. 6, pp. 4224-4231.
Cho, S.-H. and Eppinger, S.D. (2005), “A simulation-based process model for managing complex design
projects”, IEEE Transactions on Engineering Management, Vol. 52 No. 3, pp. 316-328.
Chong, H., Dahari, M., Yap, H. and Loong, Y. (2013), “Fuzzy-based risk prioritization for a hydrogen
refueling facility in Malaysia”, Journal of Zhejiang University Science A, Vol. 14 No. 8,
pp. 565-573.
Choudhry, R.M., Aslam, M.A., Hinze, J.W. and Arain, F.M. (2014), “Cost and schedule risk analysis of
bridge construction in Pakistan: establishing risk guidelines”, Journal of Construction
Engineering and Management, Vol. 140 No. 7, pp. 040140201-9.
Cienfuegos, I. (2013), “Risk Management theory: the integrated perspective and its application in the
public sector”, Estado, Gobierno, Gestión Pública, Vol. 21, pp. 89-126.
Dekker, S.W.A. (2013), “Drifting into failure: complexity theory and the management of risk”, in Banerjee, S. Cost overrun in
(Ed.), Chaos and Complexity Theory for Management: Nonlinear Dynamics, IGI Global Science construction
Reference, Hershey, PA, pp. 241-253.
projects
Demirkesen, S. and Ozorhon, B. (2017), “Measuring project management performance: case of
construction industry”, Engineering Management Journal, Vol. 29 No. 4, pp. 258-277.
Dikmen, I., Birgonul, M.T. and Han, S. (2007), “Using fuzzy risk assessment to rate cost overrun risk in
international construction projects”, International Journal of Project Management, Vol. 25 No. 5,
pp. 494-505.
Dikmen, I., Talat Birgonul, M., Ozorhon, B. and Egilmezer Sapci, N. (2010), “Using analytic network
process to assess business failure risks of construction firms”, Engineering, Construction and
Architectural Management, Vol. 17 No. 4, pp. 369-386.
Ebrat, M. and Ghodsi, R. (2014), “Construction project risk assessment by using adaptive-network-
based fuzzy inference system: an empirical study”, KSCE Journal of Civil Engineering, Vol. 18
No. 5, pp. 1213-1227.
Eybpoosh, M., Dikmen, I. and Talat Birgonul, M. (2011), “Identification of risk paths in international
construction projects using structural equation modeling”, Journal of Construction Engineering
and Management, Vol. 137 No. 12, pp. 1164-1175.
Fan, C. and Yu, Y.-C. (2004), “BBN-based software project risk management”, Journal of Systems and
Software, Vol. 73 No. 2, pp. 193-203.
Fang, C. and Marle, F. (2012), “A simulation-based risk network model for decision support in project
risk management”, Decision Support Systems, Vol. 52 No. 3, pp. 635-644.
Fang, C. and Marle, F. (2013), “Dealing with project complexity by matrix-based propagation modelling
for project risk analysis”, Journal of Engineering Design, Vol. 24 No. 4, pp. 239-256.
Fang, C., Marle, F. and Xie, M. (2016), “Applying importance measures to risk analysis in engineering
project using a risk network model”, IEEE Systems Journal, Vol. 11 No. 3, pp. 1-9.
Fang, C., Marle, F., Xie, M. and Zio, E. (2013), “An integrated framework for risk response planning
under resource constraints in large engineering projects”, IEEE Transactions on Engineering
Management, Vol. 60 No. 3, pp. 627-639.
Fang, C., Marle, F., Zio, E. and Bocquet, J.C. (2012), “Network theory-based analysis of risk interactions
in large engineering projects”, Reliability Engineering and System Safety, Vol. 106, pp. 1-10.
Ferdous, R., Khan, F., Sadiq, R., Amyotte, P. and Veitch, B. (2011), “Fault and event tree analyses for
process systems risk analysis: uncertainty handling formulations”, Risk Analysis, Vol. 31 No. 1,
pp. 86-107.
Floricel, S., Michela, J.L. and Piperca, S. (2016), “Complexity, uncertainty-reduction strategies, and
project performance”, International Journal of Project Management, Vol. 34 No. 7, pp. 1360-1383.
Floyd, M.K., Barker, K., Rocco, C.M. and Whitman, M.G. (2017), “A multi-criteria decision analysis
technique for stochastic task criticality in project management”, Engineering Management
Journal, Vol. 29 No. 3, pp. 165-178.
Flyvbjerg, B., Skamris Holm, M.K. and Buhl, Sø.L. (2004), “What causes cost overrun in transport
infrastructure projects?”, Transport Reviews, Vol. 24 No. 1, pp. 3-18.
Fouladgar, M.M., Yazdani-Chamzini, A. and Zavadskas, E.K. (2012), “Risk evaluation of tunneling
projects”, Archives of Civil and Mechanical Engineering, Vol. 12 No. 1, pp. 1-12.
Garbuzova-Schlifter, M. and Madlener, R. (2016), “AHP-based risk analysis of energy performance
contracting projects in Russia”, Energy Policy, Vol. 97, pp. 559-581.
Guohui, G. (2014), “Analysis of risk assessment and prevention for foreign project based on fuzzy
comprehensive evaluation method”, 2014 Sixth International Conference on Measuring
Technology and Mechatronics Automation, pp. 99-102.
Gupta, V.K. and Thakkar, J.J. (2018), “A quantitative risk assessment methodology for construction
project”, Sādhanā, Vol. 43 No. 7, p. 116.
IJMPB Hastak, M. and Shaked, A. (2000), “ICRAM-1: model for international construction risk assessment”,
Journal of Management in Engineering, Vol. 16 No. 1, pp. 59-69.
Hazza, M.H.F. Al, Fadel, M. Al and Adesta, E.Y.T. (2014), “Modeling a conceptual framework for
owner-contractor relationship and time-cost trade-off using fuzzy logic techniques”,
Proceedings – 3rd International Conference on Advanced Computer Science Applications and
Technologies, ACSAT 2014, pp. 179-183.
He, Q., Luo, L., Hu, Y. and Chan, A.P.C. (2015), “Measuring the complexity of mega construction
projects in China – a fuzzy analytic network process analysis”, International Journal of Project
Management, Vol. 33 No. 3, pp. 549-563.
Hossen, M.M., Kang, S. and Kim, J. (2015), “Construction schedule delay risk assessment by using
combined AHP-RII methodology for an international NPP project”, Nuclear Engineering and
Technology, Vol. 47 No. 3, pp. 362-379.
Huang, C.N., Liou, J.J.H. and Chuang, Y.C. (2014), “A method for exploring the interdependencies and
importance of critical infrastructures”, Knowledge-Based Systems, Vol. 55, pp. 66-74.
Hwang, W., Hsiao, B., Chen, H.-G. and Chern, C.-C. (2016), “Multiphase assessment of project risk
interdependencies: evidence from a university ISD project in Taiwan”, Project Management
Journal, Vol. 47 No. 1, pp. 59-75.
Isa, C.M.M., Saman, H.M., Nasir, S.R.M., Preece, C.N. and Rani, N.I.A. (2015), “Using PLS-SEM path
modeling to determine factors influencing performance of Malaysian construction firms in
international markets”, in Hassan, R., Yusoff, M., Alisibramulisi, A., Mohd Amin, N. and Ismail, Z.
(Eds), InCIEC 2014, Springer, Singapore, pp. 121-136.
Islam, M.S. and Nepal, M. (2016), “A fuzzy-Bayesian model for risk assessment in power plant projects”,
Procedia Computer Science, Vol. 100, pp. 963-970.
Islam, M.S., Nepal, M.P., Skitmore, M. and Attarzadeh, M. (2017), “Current research trends and
application areas of fuzzy and hybrid methods to the risk assessment of construction projects”,
Advanced Engineering Informatics, Vol. 33, pp. 112-131.
Jato-Espino, D., Castillo-Lopez, E., Rodriguez-Hernandez, J. and Canteras-Jordana, J.C. (2014), “A review
of application of multi-criteria decision making methods in construction”, Automation in
Construction, Vol. 45, pp. 151-162.
Ji, Y., Huang, G.H. and Sun, W. (2015), “Risk assessment of hydropower stations through an integrated
fuzzy entropy-weight multiple criteria decision making method: a case study of the Xiangxi
River”, Expert Systems with Applications, Vol. 42 No. 12, pp. 5380-5389.
Jin, X.-H. (2010), “Neurofuzzy decision support system for efficient risk allocation in public-private
partnership infrastructure projects”, Journal of Computing in Civil Engineering, Vol. 24 No. 6,
pp. 525-538.
Johansen, C. and Tien, I. (2017), “Probabilistic multi-scale modeling of interdependencies between
critical infrastructure systems for resilience”, Sustainable and Resilient Infrastructure, Taylor &
Francis, Vol. 9689, pp. 1-15.
Kabir, G., Sadiq, R. and Tesfamariam, S. (2016), “A fuzzy Bayesian belief network for safety assessment
of oil and gas pipelines”, Structure and Infrastructure Engineering, Vol. 12 No. 8, pp. 874-889.
Kardes, I., Ozturk, A., Cavusgil, S.T. and Cavusgil, E. (2013), “Managing global megaprojects:
complexity and risk management”, International Business Review, Vol. 22 No. 6, pp. 905-917.
Khademi, N., Behnia, K. and Saedi, R. (2014), “Using analytic hierarchy/network process (AHP/ANP) in
developing countries: shortcomings and suggestions”, Engineering Economist, Vol. 59 No. 1,
pp. 2-29.
Khakzad, N., Khan, F. and Amyotte, P. (2013), “Quantitative risk analysis of offshore drilling
operations: a Bayesian approach”, Safety Science, Vol. 57, pp. 108-117.
Khodakarami, V. and Abdi, A. (2014), “Project cost risk analysis: a Bayesian networks approach for
modeling dependencies between cost items”, International Journal of Project Management,
IPMA and Elsevier Ltd, Vol. 32 No. 7, pp. 1233-1245.
Kim, D.Y., Han, S.H., Kim, H. and Park, H. (2009), “Structuring the prediction model of project Cost overrun in
performance for international construction projects: a comparative analysis”, Expert Systems construction
with Applications, Vol. 36 No. 2, pp. 1961-1971.
projects
Kim, G.H., Seo, D.S. and Kang, K.I. (2005), “Hybrid models of neural networks and genetic algorithms
for predicting preliminary cost estimates”, Journal of Computing in Civil Engineering, Vol. 19
No. 2, pp. 208-211.
Kim, Y.-S. and Kang, H.-W. (2017), “Development of a model for risk and cost analysis in overseas plant
construction projects focusing on petrochemical plant construction projects”, KSCE Journal of
Civil Engineering, Vol. 21 No. 5, pp. 1549-1562.
Kimiagari, S. and Keivanpour, S. (2018), “An interactive risk visualisation tool for large-scale and
complex engineering and construction projects under uncertainty and interdependence”,
International Journal of Production Research, Taylor & Francis, pp. 1-29.
Kuo, Y.C. and Lu, S.T. (2013), “Using fuzzy multiple criteria decision making approach to enhance risk
assessment for metropolitan construction projects”, International Journal of Project
Management, Vol. 31 No. 4, pp. 602-614.
Lazzerini, B. and Mkrtchyan, L. (2011), “Analyzing risk impact factors using extended fuzzy cognitive
maps”, IEEE Systems Journal, Vol. 5 No. 2, pp. 288-297.
Lee, J.-K. (2008), “Cost overrun and cause in korean social overhead capital projects: roads, rails,
airports, and ports”, Journal of Urban Planning and Development, Vol. 134 No. 2, pp. 59-62.
Lee, J.S. and Kim, Y.S. (2017), “Analysis of cost-increasing risk factors in modular construction in Korea
using FMEA”, KSCE Journal of Civil Engineering, Vol. 21 No. 6, pp. 1999-2010.
Lessard, D., Sakhrani, V. and Miller, R. (2014), “House of project complexity – understanding
complexity in large infrastructure projects”, Engineering Project Organization Journal, Vol. 4
No. 4, pp. 170-192.
Li, F., Phoon, K.K., Du, X. and Zhang, M. (2013), “Improved AHP method and its application in
risk identification”, Journal of Construction Engineering and Management, Vol. 139 No. 3,
pp. 312-320.
Li, P.-C., Chen, G.-H., Dai, L.-C. and Zhang, L. (2012), “A fuzzy Bayesian network approach to improve
the quantification of organizational influences in HRA frameworks”, Safety Science, Vol. 50
No. 7, pp. 1569-1583.
Lin, L.-Z. and Hsu, T.-H. (2008), “The qualitative and quantitative models for performance
measurement systems: the agile service development”, Quality and Quantity, Vol. 42 No. 4,
pp. 445-476.
Lin, Z. and Jianping, Y. (2011), “Risk assessment based on fuzzy network (F-ANP) in new campus
construction project”, Systems Engineering Procedia, Vol. 1, pp. 162-168.
Liu, J. (2010), “Bayesian network inference on risks of construction schedule-cost”, IEEE 2010
International Conference of Information Science and Management Engineering, Vol. 2, pp. 15-18.
Liu, J., Zhao, X. and Yan, P. (2016), “Risk paths in international construction projects: case study from
Chinese contractors”, Journal of Construction Engineering and Management, Vol. 142 No. 6,
pp. 050160021-11.
Love, P.E.D., Ahiaga-Dagbui, D.D. and Irani, Z. (2016), “Cost overruns in transportation infrastructure
projects: sowing the seeds for a probabilistic theory of causation”, Transportation Research Part
A: Policy and Practice, Vol. 92, pp. 184-194.
Love, P.E.D., Sing, C.-P., Wang, X., Irani, Z. and Thwala, D.W. (2014), “Overruns in transportation
infrastructure projects”, Structure and Infrastructure Engineering, Vol. 10 No. 2, pp. 141-159.
Low, S.P., Liu, J. and He, S. (2009), “External risk management practices of Chinese construction firms
in Singapore”, KSCE Journal of Civil Engineering, Vol. 13 No. 2, pp. 85-95.
Lu, S.T., Lin, C.W. and Ko, P.H. (2008), “Application of Analytic Network Process (ANP) in assessing
construction risk of urban bridge project”, Second International Conference on Innovative
Computing, Information and Control, ICICIC 2007, pp. 1-4.
IJMPB Lu, Y., Luo, L., Wang, H., Le, Y. and Shi, Q. (2015), “Measurement model of project complexity for
large-scale projects from task and organization perspective”, International Journal of Project
Management, Vol. 33 No. 3, pp. 610-622.
Marle, F. and Vidal, L.-A. (2011), “Project risk management processes: improving coordination using a
clustering approach”, Research in Engineering Design, Vol. 22 No. 3, pp. 189-206.
Marle, F. and Vidal, L.-A. (2016), Managing Complex, High Risk Projects, Springer, London, available at:
https://doi.org/10.1007/978-1-4471-6787-7
Marle, F., Vidal, L.A. and Bocquet, J.C. (2013), “Interactions-based risk clustering methodologies and
algorithms for complex project management”, International Journal of Production Economics,
Vol. 142, pp. 225-234.
Maurer, M. (2017), “Classification of complexity management approaches in engineering”, Complexity
Management in Engineering Design – A Primer, Springer Vieweg, Berlin and Heidelberg, pp. 89-111.
Mehlawat, M.K. and Gupta, P. (2016), “A new fuzzy group multi-criteria decision making method with
an application to the critical path selection”, International Journal of Advanced Manufacturing
Technology, Vol. 83 Nos 5–8, pp. 1281-1296.
Ock, J.H. and Han, S.H. (2010), “Measuring risk-associated activity’s duration: a fuzzy set theory
application”, KSCE Journal of Civil Engineering, Vol. 14 No. 5, pp. 663-671.
Odeyinka, H.A., Lowe, J. and Kaka, A.P. (2013), “Artificial neural network cost flow risk assessment
model”, Construction Management and Economics, Vol. 31 No. 5, pp. 423-439.
Ou-Yang, C. and Chen, W.-L. (2017), “Applying a risk assessment approach for cost analysis and
decision-making: a case study for a basic design engineering project”, Journal of the Chinese
Institute of Engineers, Vol. 40 No. 5, pp. 378-390.
Parihar, S., Bhar, C. and Srivastava, N.K. (2015), “A project risk management methodology based on
probabilistic and non-probabilistic approach: a study on transmission line installation projects”,
Jindal Journal of Business Research, Vol. 4 Nos 1–2, pp. 27-45.
Park, K., Lee, H.W., Choi, K. and Lee, S.-H. (2019), “Project risk factors facing construction management
firms”, International Journal of Civil Engineering, Vol. 17 No. 3, pp. 305-321.
Pehlivan, S. and Öztemir, A.E. (2018), “Integrated risk of progress-based costs and schedule delays in
construction projects”, Engineering Management Journal, Vol. 30 No. 2, pp. 108-116.
Peleskei, C.A., Dorca, V. and Munteanu, R.A. (2015), “Risk consideration and cost estimation in
construction projects using Monte Carlo simulation”, Management, Vol. 10 No. 2, pp. 163-176.
Pfeifer, J., Barker, K., Ramirez-Marquez, J.E. and Morshedlou, N. (2015), “Quantifying the risk of
project delays with a genetic algorithm”, International Journal of Production Economics,
Vol. 170, pp. 34-44.
Prascevic, N. and Prascevic, Z. (2017), “Application of fuzzy AHP for ranking and selection of
alternatives in construction project management”, Journal of Civil Engineering and
Management, Vol. 23 No. 8, pp. 1123-1135.
Proon, S. and Jin, M. (2011), “A genetic algorithm with neighborhood search for the
resource-constrained project scheduling problem”, Naval Research Logistics (NRL), Vol. 58
No. 2, pp. 73-82.
Qazi, A., Quigley, J., Dickson, A. and Kirytopoulos, K. (2016), “Project complexity and risk management
(ProCRiM): towards modelling project complexity driven risk paths in construction projects”,
International Journal of Project Management, Vol. 34 No. 7, pp. 1183-1198.
Qu, Y. and Tang, X.L. (2010), “Software project risk assessing model based on credal networks”, 2010
International Conference on Machine Learning and Cybernetics, IEEE, Qingdao, pp. 1976-1979.
Qureshi, S.M. and Kang, C.W. (2015), “Analysing the organizational factors of project complexity
using structural equation modelling”, International Journal of Project Management, Vol. 33
No. 1, pp. 165-176.
Saaty, T.L. and Vargas, L.G. (2013), Decision Making with the Analytic Network Process, Vol. 195,
Springer, Boston, MA, available at: https://doi.org/10.1007/978-1-4614-7279-7
Sadeghi, N., Fayek, A.R. and Pedrycz, W. (2010), “Fuzzy Monte Carlo simulation and risk assessment in Cost overrun in
construction”, Computer-Aided Civil and Infrastructure Engineering, Vol. 25 No. 4, pp. 238-252. construction
Samantra, C., Datta, S. and Mahapatra, S.S. (2017), “Fuzzy based risk assessment module for projects
metropolitan construction project: an empirical study”, Engineering Applications of Artificial
Intelligence, Vol. 65, May, pp. 449-464.
Sambasivan, M., Deepak, T.J., Salim, A.N. and Ponniah, V. (2017), “Analysis of delays in Tanzanian
construction industry”, Engineering, Construction and Architectural Management, Vol. 24 No. 2,
pp. 308-325.
Saputra, Y.A. and Latiffianti, E. (2015), “Project reliability model considering time–cost–resource
relationship under uncertainty”, Procedia Computer Science, Vol. 72, pp. 561-568.
Satumtira, G. and Dueñas-Osorio, L. (2010), “Synthesis of modeling and simulation methods on critical
infrastructure interdependencies research”, in Gopalakrishnan, K. and Peeta, S. (Eds), Sustainable
and Resilient Critical Infrastructure Systems, Springer-Verlag, Berlin and Heidelberg, pp. 1-51.
Shafiee, M. (2015), “A fuzzy analytic network process model to mitigate the risks associated with
offshore wind farms”, Expert Systems with Applications, Vol. 42 No. 4, pp. 2143-2152.
Shariat, R., Roozbahani, A. and Ebrahimian, A. (2019), “Risk analysis of urban stormwater
infrastructure systems using fuzzy spatial multi-criteria decision making”, Science of the Total
Environment, Vol. 647, pp. 1468-1477.
Sinha, A., Strong, K.C., Ozbek, M.E. and Shane, J. (2018), “A decision support framework for assessing
the contextual factors for complex highway projects”, Transportation Research Record: Journal
of the Transportation Research Board, Vol. 2672 No. 26, pp. 77-87.
Sonmez, R. (2011), “Range estimation of construction costs using neural networks with bootstrap
prediction intervals”, Expert Systems with Applications, Vol. 38 No. 8, pp. 9913-9917.
Špačková, O., Šejnoha, J. and Straub, D. (2013), “Probabilistic assessment of tunnel construction
performance based on data”, Tunnelling and Underground Space Technology, Vol. 37, pp. 62-78.
Tabei, S.M.A., Bagherpour, M. and Mahmoudi, A. (2019), “Application of fuzzy modelling to predict
construction projects cash flow”, Periodica Polytechnica Civil Engineering, pp. 1-13.
Taillandier, F., Taillandier, P., Tepeli, E., Breysse, D., Mehdizadeh, R. and Khartabil, F. (2015),
“A multi-agent model to manage risks in construction project (SMACC)”, Automation in
Construction, Vol. 58, pp. 1-18.
Taroun, A. (2014), “Towards a better modelling and assessment of construction risk: insights from a
literature review”, International Journal of Project Management, Vol. 32 No. 1, pp. 101-115.
Taroun, A., Yang, J.B. and Lowe, D. (2011), “Construction risk modelling and assessment : insights from
a literature review”, The Built & Human Environment Review, Vol. 4 No. 1, pp. 87-97.
Terstegen, S., Petz, A., Schlick, C.M. and Duckwitz, S. (2016), “Simulation-based scheduling and risk
assessment of complex projects under uncertainty”, in Deml, B., Stock, P., Bruder, R. and
Schlick, C.M. (Eds), Advances in Ergonomic Design of Systems, Products and Processes, Springer,
Berlin and Heidelberg, pp. 411-429.
Valipour, A., Yahaya, N., Md Noor, N., Kildienė, S., Sarvari, H. and Mardani, A. (2015), “A fuzzy analytic
network process method for risk prioritization in freeway PPP projects: an Iranian case study”,
Journal of Civil Engineering and Management, Vol. 21 No. 7, pp. 933-947.
Valipour, A., Yahaya, N., Md Noor, N., Mardani, A. and Antuchevičienė, J. (2016), “A new hybrid fuzzy
cybernetic analytic network process model to identify shared risks in PPP projects”,
International Journal of Strategic Property Management, Vol. 20 No. 4, pp. 409-426.
Vu, H.A., Cu, V.H., Min, L.X. and Wang, J.Q. (2017), “Risk analysis of schedule delays in international
highway projects in Vietnam using a structural equation model”, Engineering, Construction and
Architectural Management, Vol. 24 No. 6, pp. 1018-1039.
Wang, X., Zhu, J., Ma, F., Li, C., Cai, Y. and Yang, Z. (2016), “Bayesian network-based risk assessment
for hazmat transportation on the middle route of the South-to-North water transfer project in
China”, Stochastic Environmental Research and Risk Assessment, Springer Berlin Heidelberg,
Vol. 30 No. 3, pp. 841-857.
IJMPB Weber, P., Medina-Oliva, G., Simon, C. and Iung, B. (2012), “Overview on Bayesian networks
applications for dependability, risk analysis and maintenance areas”, Engineering Applications
of Artificial Intelligence, Vol. 25 No. 4, pp. 671-682.
Xu, X., Wang, J., Li, C.Z., Huang, W. and Xia, N. (2018), “Schedule risk analysis of infrastructure
projects: a hybrid dynamic approach”, Automation in Construction, Vol. 95, pp. 20-34.
Yildiz, A.E., Dikmen, I., Birgonul, M.T., Ercoskun, K. and Alten, S. (2014), “A knowledge-based risk
mapping tool for cost estimation of international construction projects”, Automation in
Construction, Vol. 43, pp. 144-155.
Yucelgazi, F. and Yitmen, İ. (2018), “An ANP model for risk assessment in large-scale transport
infrastructure projects”, Arabian Journal for Science and Engineering, available at: https://doi.
org/10.1007/s13369-018-3314-z
Zayed, T., Amer, M. and Pan, J. (2008), “Assessing risk and uncertainty inherent in Chinese highway
projects using AHP”, International Journal of Project Management, Vol. 26 No. 4, pp. 408-419.
Zhang, L., Huang, Y., Wu, X. and Skibniewski, M.J. (2017), “Risk-based estimate for operational safety
in complex projects under uncertainty”, Applied Soft Computing Journal, Vol. 54, pp. 108-120.
Zhang, L., Wu, X., Qin, Y., Skibniewski, M.J. and Liu, W. (2016), “Towards a fuzzy Bayesian network
based approach for safety risk analysis of tunnel-induced pipeline damage”, Risk Analysis,
Vol. 36 No. 2, pp. 278-301.
Zhao, X., Wu, P. and Wang, X. (2018), “Risk paths in BIM adoption: empirical study of China”,
Engineering, Construction and Architectural Management, Vol. 25 No. 9, pp. 1170-1187.

Further reading
Abd El-Karim, M.S.B.A., Mosa El Nawawy, O.A. and Abdel-Alim, A.M. (2017), “Identification
and assessment of risk factors affecting construction projects”, HBRC Journal, Vol. 13 No. 2,
pp. 202-216.
Al-Harbi, K.M.A.S. (2001), “Application of the AHP in project management”, International Journal of
Project Management, Vol. 19 No. 1, pp. 19-27.
Darko, A., Chan, A.P.C., Ameyaw, E.E., Owusu, E.K., Pärn, E. and Edwards, D.J. (2018), “Review of
application of analytic hierarchy process (AHP) in construction”, International Journal of
Construction Management, Vol. 19 No. 5, pp. 436-452.
Gładysz, B., Skorupka, D., Kuchta, D. and Duchaczek, A. (2015), “Project risk time management – a
proposed model and a case study in the construction industry”, Procedia Computer Science,
Vol. 64, pp. 24-31.
Hollmann, J.K. (2015), “Risk analysis at the edge of chaos”, Cost Engineering, Vol. 57 No. 1, pp. 28-38.
Idrus, A., Fadhil Nuruddin, M. and Rohman, M.A. (2011), “Development of project cost contingency
estimation model using risk analysis and fuzzy expert system”, Expert Systems with
Applications, Vol. 38 No. 3, pp. 1501-1508.
Jung, W. and Han, S.H. (2017), “Which risk management is most crucial for controlling project cost?”,
Journal of Management in Engineering, Vol. 33 No. 5, pp. 040170291-13.
Kangari, R. and Riggs, L.S. (1989), “Construction risk assessment by linguistics”, IEEE Transactions on
Engineering Management, Vol. 36 No. 2, pp. 126-131.
Karimiazari, A., Mousavi, N., Mousavi, S.F. and Hosseini, S. (2011), “Risk assessment model selection in
construction industry”, Expert Systems with Applications, Vol. 38 No. 8, pp. 9105-9111.
Li, J. and Zou, P.X.W. (2011), “Fuzzy AHP-based risk assessment methodology for PPP projects”,
Journal of Construction Engineering and Management, Vol. 137 No. 12, pp. 1205-1209.
Martinelli, R.J. and Milosevic, D.Z. (2016), “Risk and stakeholder management tools”, Project
Management ToolBox, 2nd ed., Vol. 182 No. 2, pp. 351-373.
Munier, N. (2014), Risk Management for Engineering Projects, Springer International Publishing, Cham,
available at: https://doi.org/10.1007/978-3-319-05251-9
Muriana, C. and Vizzini, G. (2017), “Project risk management: a deterministic quantitative technique Cost overrun in
for assessment and mitigation”, International Journal of Project Management, Vol. 35 No. 3, construction
pp. 320-340.
Rodney, E., Ducq, Y., Breysse, D. and Ledoux, Y. (2015), “An integrated management approach of the
projects
project and project risks”, IFAC-PapersOnLine, Vol. 28 No. 3, pp. 535-540.
Russo, R.D.F.S.M. and Camanho, R. (2015), “Criteria in AHP: a systematic review of literature”, Procedia
Computer Science, Vol. 55, pp. 1123-1132.
Saaty, T.L. (2003), The Analytic Hierarchy Process (AHP) for Decision Making and the Analytic Network
Process (ANP) for Decision Making with Dependence and Feedback, Creative Decisions
Foundation, RWS Publications, Pittsburgh, PA, available at: www.rwspublications.com/books/
Sangaiah, A.K., Samuel, O.W., Li, X., Abdel-Basset, M. and Wang, H. (2017), “Towards an efficient risk
assessment in software projects – fuzzy reinforcement paradigm”, Computers and Electrical
Engineering, Vol. 71, pp. 833-846.
Senouci, A., Ismail, A. and Eldin, N. (2016), “Time delay and cost overrun in Qatari public construction
projects”, Procedia Engineering, Vol. 164, pp. 368-375.
Szymański, P. (2017), “Risk management in construction projects”, Procedia Engineering, Vol. 208,
pp. 174-182.
Taylan, O., Bafail, A.O., Abdulaal, R.M.S. and Kabli, M.R. (2014), “Construction projects selection and
risk assessment by fuzzy AHP and fuzzy TOPSIS methodologies”, Applied Soft Computing
Journal, Vol. 17, pp. 105-116.
Thomas, A.V., Kalidindi, S.N. and Ganesh, L.S. (2006), “Modelling and assessment of critical risks in
BOT road projects”, Construction Management and Economics, Vol. 24 No. 4, pp. 407-424.
Tsavdaroglou, M., Al-Jibouri, S.H.S., Bles, T. and Halman, J.I.M. (2018), “Proposed methodology for risk
analysis of interdependent critical infrastructures to extreme weather events”, International
Journal of Critical Infrastructure Protection, Vol. 21, pp. 57-71.
Vidal, L.-A., Marle, F. and Bocquet, J.-C. (2011), “Using a Delphi process and the analytic hierarchy
process (AHP) to evaluate the complexity of projects”, Expert Systems with Applications, Vol. 38
No. 5, pp. 5388-5405.
Zegordi, S.H., Rezaee Nik, E. and Nazari, A. (2012), “Power plant project risk assessment using a fuzzy-
ANP and fuzzy-TOPSIS method”, International Journal of Engineering, Transactions B:
Applications, Vol. 25 No. 2, pp. 107-120.

Corresponding author
Farman Afzal can be contacted at: farmanafzal@gmail.com

For instructions on how to order reprints of this article, please visit our website:
www.emeraldgrouppublishing.com/licensing/reprints.htm
Or contact us for further details: permissions@emeraldinsight.com

You might also like