Unsupervised machine learning for identifying key risk factors contributing to construction delays

Aug 4, 2026

Upload by Eden

The study applies unsupervised machine learning, focusing on K-means clustering, to address construction delays by uncovering critical risk factors. Using a large dataset compiled from contracting firms in developing regions, the research identifies influential variables through Likert-scale categorisation into five influence levels. The clustered results organize the complex risk landscape, improving understanding of factors driving schedule slippage. The approach strengthens conventional risk-management practices and supports more informed project decisions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Construction delays and risk management context

Prior research on risk factors in different regions

Emerging use of machine learning in construction management

Original Research Open Access Fuad Al-Bataineh, Ahmed Ali Khatatbeh, Yazan Alzubi* Unsupervised machine learning for identifying key risk factors contributing to construction delays DOI 10.2478/otmcj-2024-0014 Received: August 31, 2023; accepted: June 26, 2024 Abstract: The present study uses unsupervised machine learning capabilities with an emphasis on K-means clustering for addressing the problem of construction delays. The primary objective is to investigate the critical risk factors that contribute to such delays, thereby enabling more efficient risk-management strategies. The study employs a large dataset compiled from contracting firms operating in developing regions. This information is a vital resource for identifying crucial risk variables. These variables are analysed and categorised using the Likert scale into five levels based on their potential influence. This systematic approach permits the development of a comprehensive understanding of the relevant factors. These risk factors are grouped to enhance comprehension of the intricate risk landscape using K-means clustering. This allows for a broader, more comprehensive understanding of the factors contributing to construction delays. The application of K-means clustering demonstrates the potential of machine learning techniques to improve conventional approaches to risk management. This empirical investigation significantly expands the existing body of construction risk-management knowledge. It offers invaluable insights into various project stakeholders, allowing for more informed decision-making. Notably, the clustering analysis results provide a practical, user-friendly tool. This tool can assist project managers in enhancing their risk foresight, drafting more effective plans and developing robust mitigation strategies. Consequently, this research offers the potential for substantial improvements in project timeline adherence, thereby substantially *Corresponding author: Yazan Alzubi, Department of Civil Engineering, Faculty of Engineering Technology, Al-Balqa Applied University, Amman, [Jordan. E-mail: yazan.alzubi@bau.edu.jo](Jordan. E-mail: yazan.alzubi@bau.edu.jo)[ ](Jordan. E-mail: yazan.alzubi@bau.edu.jo)[FuadAl-Bataineh and Ahmed Ali Khatatbeh](FuadAl-Bataineh and Ahmed Ali Khatatbeh), Department of Civil Engineering, Faculty of Engineering, Al-al Bayt University, Mafraq, Jordan reducing the impact of construction delays in developing nations. Keywords: Machine learning, Unsupervised learning, Construction management, Project management, Delays 1 Introduction Indeed, the construction industry is essential to the economy, especially in developing nations. In this industry, delays frequently negatively affect project costs, stakeholder relationships and overall project success. In order to ensure effective risk management and on-time project delivery, it is essential to identify the underlying causes of these delays. The literature on this subject is vast and diverse. Kassem et al. (2020) discussed risk factors affecting Yemen’s oil and gas construction projects. Abd Karim et al. (2012) identified significant risk factors from a contractor’s perspective. Ahmed et al. (2002) conducted an empirical study of construction delays in Florida, whereas Aibinu and Odeyinka (2006) examined the causes of such delays in Nigeria. Akomah and Jackson (2016) investigated road project delays, and Al Zubaidi and Al Otaibi (2008) identified risk factors for time overruns in Kuwait. Alajmi and Ahmed Memon (2022) analysed factors causing delaysin Saudi Arabian projects, whereas Ali et al. (2010) investigated commercial projects in Malaysia. Al-Momani (2000) provided a quantitative analysis, and Alshihri et al. (2022) identified the risk factors contributing to time and cost overruns in Saudi Arabian construction projects. Cheng and Darsa (2021) analysed construction schedule risksin Ethiopia, whereas Buertey et al. (2013) discussed large construction projec

FAQs

What method does the study use to analyze construction delays?

The research uses unsupervised machine learning with an emphasis on K-means clustering to group and interpret risk factors contributing to delays.

How are the risk factors collected and prepared for analysis?

A large dataset from contracting firms in developing regions is used, and risk variables are categorized using a Likert scale into five levels based on their potential influence.

How can the clustering results help project stakeholders?

The clustering analysis produces a practical tool that helps project managers improve risk foresight, draft more effective plans, and develop robust mitigation strategies.

Aug 4, 2026

Upload by Eden