Application of Machine Learning Algorithms for Delay Prediction in Civil Engineering Projects: A Simulation-Based Study

Waliullah Zia¹

1) Undergraduate Student, B.Sc. in Civil Engineering, University of Tehran, Tehran, Iran

IOI Code : AAHE-ABGGKD
Publication : National Conference on Civil Engineering, Design and Construction Technologies, Energy, Materials and Advanced Machinery(icaeu.ir)
Abstract :
    Delays in civil engineering projects continue to be a persistent and costly challenge in the construction industry worldwide. Early and accurate prediction of project delays enables proactive managerial interventions and significantly reduces financial and schedule overruns. This study investigates the application of four supervised machine learning algorithms—Random Forest, Gradient Boosting, Logistic Regression, and Support Vector Machine (SVM)—for the prediction of construction project delays. A synthetic simulation dataset comprising 300 civil engineering project records was generated based on ten key project risk factors, including site complexity, weather risk, labor availability, and change order frequency. The models were trained and evaluated using standard performance metrics including accuracy, precision, recall, and F1-score. Results demonstrate that Random Forest achieved the highest predictive performance with an accuracy of 75.00% and an F1-score of 83.52%, outperforming other algorithms. Weather risk score, site complexity, and change order frequency were identified as the most influential predictors of project delay. Findings confirm the viability of machine learning as a decision-support tool for civil engineering project management and highlight the potential for integration with Building Information Modeling (BIM) platforms.

Keywords : machine learning construction delay prediction random forest civil engineering project management risk factors simulation study