AI-Powered Predictive Analytics Risk Assessment in Urban Construction Projects
Paul Anderson
Maricopa County Community College District
Abstract
Urban construction, by nature, is complex, hence susceptible to a variety of risks involving schedule delays, safety, budgetary overflows, and regulatory challenges. Ascertaining risks in cities that are always in flux using expert opinions and fixed models may not be too effective. In the wake of this, this study presents an AI-driven system that has implemented predictive analytics for proactive risk identification and mitigation in urban construction projects. The machine learning algorithms being proposed analyze site-specific characteristics, historical project data, and external variables to forecast on-site occurrences and possible outcomes. A case study conducted on numerous urban construction projects shows that the model can highlight high-risk scenarios and help individuals make better choices. It is observed that proactive risk detection and planning for how to deal with them have come a long way since they were first employed.
Keywords
Risk Assessment, Predictive Analytics, Urban Construction, Machine Learning, AI in Civil Engineering, Construction Risk Management, Data-Driven Decision Making.
References
[1] Aibinu, A. A., & Jagboro, G. O. (2002). The effects of construction delays on project delivery in Nigerian construction industry. International Journal of Project Management, 20(8), 593–599.
[2] Cheng, M. Y., Tsai, H. C., & Sudjono, E. (2010). Predicting construction cost and schedule success using artificial neural networks. Journal of Civil Engineering and Management, 16(4), 475–487.
[3] Kim, G. H., An, S. H., & Kang, K. I. (2004). Comparison of construction cost estimating models based on regression analysis, neural networks, and case-based reasoning. Building and Environment, 39(10), 1235–1242.
[4] Zhang, X., Wang, Y., & Skitmore, M. (2018). An artificial neural network model for project risk prediction. Automation in Construction, 94, 203–216.
[5] Fang, D., Zhao, C., & Zhang, M. (2004). A cognitive model of construction workers’ safety behavior. Journal of Construction Engineering and Management, 130(3), 386–395.
[6] Goh, Y. M., & Chua, D. K. (2010). Neural network forecasting of safety management systems performance. Expert Systems with Applications, 38(2), 1241–1248.
[7] Son, H., Kim, C., Chong, W. K., & Chou, J. S. (2012). Implementing sustainability in the construction industry: Drivers and change agents. Journal of Cleaner Production, 26, 1–10.
[8] Love, P. E. D., Edwards, D. J., & Irani, Z. (2012). Moving beyond optimism bias and strategic misrepresentation: An explanation for social infrastructure project cost overruns. IEEE Transactions on Engineering Management, 59(4), 560–571.
[9] Abioye, S. O., & Oyedele, L. O. (2020). Artificial intelligence for risk management in construction: A review. Journal of Building Engineering, 28, 101070.
[10] Elghaish, F., Abrishami, S., & Hosseini, M. R. (2020). Integrated project delivery with BIM: An automated EVM-based approach. Automation in Construction, 114, 103182.
[11] Li, H., Guo, H., Skitmore, M., & Huang, T. (2013). Assessing construction project risks based on the past performance. Engineering, Construction and Architectural Management, 20(3), 286–302.
[12] Zhang, L., Wu, X., & Shen, G. Q. (2011). Application of Bayesian networks in construction safety management: A case study in Hong Kong. Expert Systems with Applications, 38(6), 7498–7509.
[13] Liu, H., & Wang, Y. (2017). Predictive analytics for construction project risk management using machine learning. Procedia Engineering, 196, 129–136.
[14] Lin, Y. C., & Chang, Y. H. (2006). Exploring project risks associated with construction material supply chains. Journal of Civil Engineering and Management, 12(3), 197–207.
[15] Mahamid, I. (2013). Frequency of change orders in construction projects in Saudi Arabia. International Journal of Project Management, 31(4), 541–547.