Predicting the Occurrence of Construction Disputes Using Machine Learning Techniques

Date

2021-04-01

Author

AYHAN, MURAT
Dikmen Toker, İrem
Birgönül, Mustafa Talat

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

367
views

0
downloads

© 2021 American Society of Civil Engineers.The construction industry is overwhelmed by an increasing number and severity of disputes. The primary objective of this research is to predict the occurrence of disputes by utilizing machine learning (ML) techniques on empirical data. For this reason, variables affecting dispute occurrence were identified from the literature, and a conceptual model was developed to depict the common factors. Based on the conceptual model, a questionnaire was designed to collect empirical data from experts. Chi-square tests were conducted to reveal the associations between input variables and dispute occurrence. Alternative classification techniques were tested, and support vector machine (SVM) classifiers achieved the best average accuracy (90.46%). Ensemble classifiers combining the tested classification techniques were developed for enhanced prediction performance. Experimental results showed that the best ensemble classifier, obtained from the majority voting technique, can achieve 91.11% average accuracy. Based on Chi-square tests, the most influential factors on dispute occurrence were found as variations and unexpected events in projects. Other important predictors were all related to the skills of the parties involved. This study contributes to the construction dispute domain in three ways: (1) by proposing a conceptual model that combined the diverse efforts in the literature for identifying variables affecting dispute occurrence; (2) by highlighting the influential factors, such as response rate and communication skills, as indicators for potential disputes; and (3) by providing an empirical ML-based model with enhanced prediction capabilities that can function as an early-warning mechanism for decision-makers.

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85100773707&origin=inward
https://hdl.handle.net/11511/89139

Journal

Journal of Construction Engineering and Management

DOI

https://doi.org/10.1061/(asce)co.1943-7862.0002027

Collections

Department of Civil Engineering, Article

Suggestions

OpenMETU
Core

Development of dispute prediction and resolution method selection models for construction disputes Ayhan, Mura; Birgönül, Mustafa Talat; Department of Civil Engineering (2019) Construction industry is overwhelmed by increasing number and severity of disputes proving that current practices are insufficient in avoidance. This research argues that in order to forestall and mitigate construction disputes, prediction models should be developed by utilizing machine learning algorithms. The research suggests developing three distinct models; (1) dispute occurrence prediction model, (2) potential compensation prediction model, and (3) resolution method selection model. For this reason, a...
Integrated Probabilistic Delay Analysis Method to Estimate Expected Outcome of Construction Delay Disputes Bektas, Sinasi; Birgönül, Mustafa Talat; Dikmen Toker, İrem (2021-02-01) © 2020 American Society of Civil Engineers.Delays are almost inevitable in construction projects. They can have a devastating effects on the project. Therefore, proper analysis of delays and apportionment of liability is of utmost importance. Parties to construction contracts frequently employ various delay analysis methods to find out their entitlement to extension of time, or liquidated and ascertained damages. More often than not, technical analysis of delays performed by the parties yield distinct resul...
Smart contract systems for guaranteed and timely payment of construction projects Ahmadisheykhsarmast, Salar; Sönmez, Rifat; Department of Civil Engineering (2020) Delay in progress payment is a widespread problem in the construction industry which adversely affects the entire processes of the projects. Difficulties in the cashflow of the contracts, and consequently the subcontractors are the main consequences of delayed payments. Despite its significance, few research focused on development of methods guaranteeing timely payments of the participants throughout the project. Recent developments in blockchain and smart contract technologies presents a potential for deve...
Prioritization of risk mitigation strategies with visual based scenario analysis Kuzucuoğlu, Dilşen; Tokdemir, Onur Behzat; Department of Civil Engineering (2019) Unique and complex nature of the construction industry brings a high number of injuries in construction sites. Although the importance given to the health and safety practices increased recently, still there exists inadequacy of preventative practices along with poor risk management policies. One of the reasons that cause a high incidence of injuries is inability to identify scenarios that create injuries effectively, which in turn makes finding optimal risk mitigation strategies difficult. So, the objectiv...
Lean design management – an evaluation of waste items for architectural design process Mazlum, Salih Kaan; Pekeriçli, Mehmet Koray; Department of Building Science in Architecture (2015) Waste is standing as a major problem in the body of construction industry. Lean thinking in construction accepts any inefficiency as waste which results with more usage of equipment, materials, labor, time or capital in larger quantities than those considered as necessary. Although inefficiency of design stages has been identified as a major factor that reduces the efficiency of construction projects, less attention has been paid on the relationship between lean thinking and architectural design process. Th...

Citation Formats

M. AYHAN, İ. Dikmen Toker, and M. T. Birgönül, “Predicting the Occurrence of Construction Disputes Using Machine Learning Techniques,” Journal of Construction Engineering and Management, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85100773707&origin=inward.