AI-driven risk identification model for infrastructure project: Utilising past project data
Fredrick Ahenkora Boamah, Xiaohua Jin, Sepani Senaratne, Srinath Perera
Abstract
Infrastructure projects are by nature complicated and vulnerable due to unpredictable risks encountered during their execution. The use of expert opinion and qualitative methodologies in traditional risk identification makes them vulnerable to subjectivity and responsiveness, leading to cost overruns, delays, and, ultimately, project failure. Therefore, to improve the accuracy of risk identification, this study utilises historical data in conjunction with AI approaches to develop a data-driven risk identification model. The model determines risk frequency and consequence by matching them to different risk categories in previous projects, considering word semantics. This model also demonstrates the facilitation of proactive decision-making and allows infrastructure project team members to identify risks early and implement mitigation plans. The study also highlights the practical significance of utilising historical data to make risk management strategies for infrastructure projects more reliable and efficient.