Sanni-Anibire, M O; Zin, R M and Olatunji, S O (2022) Machine learning model for delay risk assessment in tall building projects. International Journal of Construction Management, 22(11), pp. 2134-2143. ISSN 1562-3599
Abstract
Risky projects such as tall buildings have suffered an alarming rate of increase in delays and total abandonment. Though numerous delay studies predominate, what is lacking is constructive research to develop tools and techniques to wrestle the inherent problem. Consequently, this paper presents the development of a machine learning model for delay risk assessment in tall building projects. Initially, 36 delay risk factors were identified from previous literature, and subsequently developed into surveys to determine the likelihood and consequence of the risk factors. Forty-eight useable responses obtained from subject matter experts were used to develop a dataset suitable for machine learning application. K-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Ensemble methods were considered. Feature subset selection revealed that the most relevant independent variables include “slowness in decision making”; “delay in sub-contractors work”; “architects'/structural engineers' late issuance of instruction”; and “waiting for approval of shop drawings and material samples”. The final results showed that the best model for predicting the risk of delay was based on ANN with a classification accuracy of 93.75%. Ultimately, the model developed in this study could support construction professionals in project risk management of tall buildings.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | delays; ensemble methods; k nearest neighbor; neural networks; risk assessment; support vector machines; tall buildings |
| Index terms: | independent variable, project risk management, construction professional, risk assessment, risk factor, architect, machine learning application, tall building, approval, abandonment, drawing, neural network, survey, accuracy, artificial neural network, decision-making, structural engineer, sub-contractor, machine learning, dataset |
| Subjects: | professional development, financial risk, environmental hazards, completion, statistical analysis, data management, decision analysis, practitioner, data collection methods, construction type, contractual role, profession, artificial intelligence, modelling and simulation, technical documentation |
| Topics: | Digital Applications, Design Practice, Contract Administration, Cost Management, Information Management, Project Management, Research Practice, Roles and Professions, Risk Management, Sustainability, Construction Technology |
| Descriptive scope: | 4 PCEA |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here