Machine Learning–Driven Prediction of Construction Project Delays Using Multi-Factor Risk Indicators in Infrastructure Development
DOI:
https://doi.org/10.51903/g8dtmg04Keywords:
project delay, machine learning, random forest, risk prediction, construction projectAbstract
Construction project delays represent a complex issue driven by multiple interacting risk factors, making them difficult to predict using traditional approaches. This study develops a machine learning–based prediction model by incorporating various risk indicators related to cost, schedule, quality, and operational conditions. Historical project data are used to train multiple algorithms, including Decision Tree, Random Forest, and Support Vector Machine, which are evaluated using classification performance metrics. The results demonstrate that the Random Forest model achieves the highest accuracy among the tested algorithms. Feature importance analysis reveals that work progress deviation and payment delays are the most influential factors contributing to project delays. The proposed approach not only improves predictive performance but also enhances the understanding of critical risk drivers, enabling more proactive decision-making in construction project management.
Downloads
References
[1] S. Alshihri, K. Al‐gahtani, and A. Almohsen, “Risk Factors That Lead to Time and Cost Overruns of Building Projects in Saudi Arabia,” Buildings 2022, Vol. 12, Page 902, vol. 12, no. 7, p. 902, Jun. 2022, doi: 10.3390/BUILDINGS12070902.
[2] A. Rauzana and W. Dharma, “Causes of delays in construction projects in the Province of Aceh, Indonesia,” PLoS One, vol. 17, no. 1, p. e0263337, Jan. 2022, doi: 10.1371/JOURNAL.PONE.0263337.
[3] S. H. ; Khahro et al., “Delay in Decision-Making Affecting Construction Projects: A Sustainable Decision-Making Model for Mega Projects,” Sustainability 2023, Vol. 15, Page 5872, vol. 15, no. 7, p. 5872, Mar. 2023, doi: 10.3390/SU15075872.
[4] E. ; Alenazi et al., “Exploring the Nature and Impact of Client-Related Delays on Contemporary Saudi Construction Projects,” Buildings 2022, Vol. 12, Page 880, vol. 12, no. 7, p. 880, Jun. 2022, doi: 10.3390/BUILDINGS12070880.
[5] S. Melaku Belay, S. Tilahun, M. Yehualaw, J. Matos, H. Sousa, and E. T. Workneh, “Analysis of Cost Overrun and Schedule Delays of Infrastructure Projects in Low Income Economies: Case Studies in Ethiopia,” Advances in Civil Engineering, vol. 2021, no. 1, p. 4991204, Jan. 2021, doi: 10.1155/2021/4991204.
[6] O. P. Giri and O. P. Giri, “Perception-Based Assessment of the Factors Causing Delays in Construction Projects,” Engineering, vol. 15, no. 7, pp. 431–445, Jul. 2023, doi: 10.4236/ENG.2023.157033.
[7] D. B. Chattapadhyay, J. Putta, and P. Rama Mohan Rao, “Risk Identification, Assessments, and Prediction for Mega Construction Projects: A Risk Prediction Paradigm Based on Cross Analytical-Machine Learning Model,” Buildings 2021, Vol. 11, Page 172, vol. 11, no. 4, p. 172, Apr. 2021, doi: 10.3390/BUILDINGS11040172.
[8] A. Mahmoodzadeh, H. R. Nejati, N. Ghazouani, and A. Alghamdi, “Machine Learning approaches for predicting the construction time of drill-and-blast tunnels,” Scientific Reports 2025 15:1, vol. 15, no. 1, pp. 31934-, Aug. 2025, doi: 10.1038/s41598-025-17455-7.
[9] O. Alshboul, A. Shehadeh, R. E. Al Mamlook, G. Almasabha, A. S. Almuflih, and S. Y. Alghamdi, “Prediction Liquidated Damages via Ensemble Machine Learning Model: Towards Sustainable Highway Construction Projects,” Sustainability 2022, Vol. 14, Page 9303, vol. 14, no. 15, p. 9303, Jul. 2022, doi: 10.3390/SU14159303.
[10] D. B. Chattapadhyay, J. Putta, and P. Rama Mohan Rao, “Risk Identification, Assessments, and Prediction for Mega Construction Projects: A Risk Prediction Paradigm Based on Cross Analytical-Machine Learning Model,” Buildings 2021, Vol. 11, Page 172, vol. 11, no. 4, p. 172, Apr. 2021, doi: 10.3390/BUILDINGS11040172.
[11] E. ; Alenazi et al., “Exploring the Nature and Impact of Client-Related Delays on Contemporary Saudi Construction Projects,” Buildings 2022, Vol. 12, Page 880, vol. 12, no. 7, p. 880, Jun. 2022, doi: 10.3390/BUILDINGS12070880.
[12] Z. M. Yaseen, Z. H. Ali, S. Q. Salih, and N. Al-Ansari, “Prediction of Risk Delay in Construction Projects Using a Hybrid Artificial Intelligence Model,” Sustainability 2020, Vol. 12, Page 1514, vol. 12, no. 4, p. 1514, Feb. 2020, doi: 10.3390/SU12041514.
[13] A. Mahmoodzadeh, H. R. Nejati, N. Ghazouani, and A. Alghamdi, “Machine Learning approaches for predicting the construction time of drill-and-blast tunnels,” Scientific Reports 2025 15:1, vol. 15, no. 1, pp. 31934-, Aug. 2025, doi: 10.1038/s41598-025-17455-7.
[14] E. ; Alenazi et al., “Exploring the Nature and Impact of Client-Related Delays on Contemporary Saudi Construction Projects,” Buildings 2022, Vol. 12, Page 880, vol. 12, no. 7, p. 880, Jun. 2022, doi: 10.3390/BUILDINGS12070880.
[15] Z. M. Yaseen, Z. H. Ali, S. Q. Salih, and N. Al-Ansari, “Prediction of Risk Delay in Construction Projects Using a Hybrid Artificial Intelligence Model,” Sustainability 2020, Vol. 12, Page 1514, vol. 12, no. 4, p. 1514, Feb. 2020, doi: 10.3390/SU12041514.
[16] A. B. Shaik and S. Srinivasan, “A Brief Survey on Random Forest Ensembles in Classification Model,” Lecture Notes in Networks and Systems, vol. 56, pp. 253–260, 2019, doi: 10.1007/978-981-13-2354-6_27.
[17] O. R. Olaniran, A. R. R. Alzahrani, N. M. S. Alharbi, and A. A. Alzahrani, “Random Generalized Additive Logistic Forest: A Novel Ensemble Method for Robust Binary Classification,” Mathematics 2025, Vol. 13, Page 1214, vol. 13, no. 7, p. 1214, Apr. 2025, doi: 10.3390/MATH13071214.
[18] R. G. Leiva, A. F. Anta, V. Mancuso, and P. Casari, “A novel hyperparameter-free approach to decision tree construction that avoids overfitting by design,” IEEE Access, vol. 7, pp. 99978–99987, 2019, doi: 10.1109/ACCESS.2019.2930235.
[19] P. Mahalingam, D. Kalpana, and T. Thyagarajan, “Overfit Analysis on Decision Tree Classifier for Fault Classification in DAMADICS,” Proceedings of the IEEE Madras Section International Conference 2021, MASCON 2021, 2021, doi: 10.1109/MASCON51689.2021.9563557.
[20] E. Halabaku and E. Bytyçi, “Overfitting in Machine Learning: A Comparative Analysis of Decision Trees and Random Forests,” Intelligent Automation & Soft Computing, vol. 39, no. 6, pp. 987–1006, Dec. 2024, doi: 10.32604/IASC.2024.059429.
[21] A. Amro, M. Al-Akhras, K. El Hindi, M. Habib, and B. A. Shawar, “Instance Reduction for Avoiding Overfitting in Decision Trees,” Journal of Intelligent Systems, vol. 30, no. 1, pp. 438–459, Jan. 2021, doi: 10.1515/JISYS-2020-0061/XML.
[22] A. Sazira Bakri, M. Aminudin, A. Razak, A. Saifuza, and A. Shukor, “Identification of Factors Influencing Time and Cost Risks in Highway Construction Projects,” International Journal of Sustainable Construction Engineering and Technology, vol. 12, no. 3, pp. 280–288, Dec. 2021, doi: 10.30880/ijscet.2021.12.03.027.
[23] A. Lapidus, D. Topchiy, T. Kuzmina, and O. Chapidze, “Influence of the Construction Risks on the Cost and Duration of a Project,” Buildings, vol. 12, no. 4, p. 484, Apr. 2022, doi: 10.3390/BUILDINGS12040484/S1.
[24] P. Fernández-Valderrama, C. Ureña-Estrella, J. Moyano, and D. Bienvenido-Huertas, “Cost and time risk factors in construction projects in the Dominican Republic,” Front. Built Environ., vol. 10, p. 1307572, Jul. 2024, doi: 10.3389/FBUIL.2024.1307572/TEXT.
[25] S. Alshihri, K. Al‐gahtani, and A. Almohsen, “Risk Factors That Lead to Time and Cost Overruns of Building Projects in Saudi Arabia,” Buildings 2022, Vol. 12, Page 902, vol. 12, no. 7, p. 902, Jun. 2022, doi: 10.3390/BUILDINGS12070902.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Joseflim Marchel, Budi Hartono, Agustinus Budi Santoso (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
