Artificial Intelligence Application for Risk Template Generation in Major Transportation Projects

Recognized as a best practice, risk management offers an effective method to ensure project success under uncertain conditions. Particularly true for major transportation projects, where technical and institutional complexity increases the risk and challenges for collaboration, practitioners implement assessment and tracking. The vast majority of research in the field of risk identification focuses on the expertise, views, and judgments of Subject Matter Experts (SMEs). However, public agencies with limited experience in major transportation projects find themselves in a challenging situation in performing and auditing risk assessments for accuracy and robustness. The need for a comprehensive risk template to facilitate risk assessment grows rapidly. This paper presents a novel data-driven framework for developing typical risk templates for major transportation. The method bases its techniques on a large risk database of more than 70 US major transportation projects. Using natural language processing and deep learning techniques, the model uses different terminology to detect common risks in various projects and provides a summary of the risk consequences based on probability, cost, and schedule impacts. The advantage of this informative risk template not only captures important risks based on the frequency of occurrence in actual project data but also considers the potential consequences of each risk item. Also, the novel data-driven approach customizes risk registers according to specific project characteristics.