Data-Driven Decision Support Framework for Predicting and Mitigating Structural Fire Risks

Fire-related events can result in substantial losses represented by injuries, fatalities, and structural damages. To protect Canadians, there is a real need to identify key risk factors that contribute to the frequency and severity of such events, and subsequently, devise mitigation strategies that prevent structural fire risks. The powerful combination of incident data sources and artificial intelligence technologies has the potential to accurately extract the leading causes of structural fires. In this respect, the objective of the project is to develop a data-driven decision support framework to enhance the decision-making of structural fire quantitative prediction and mitigation. Empowered by the framework, the partner organization can: 1) explore interdependent key fire incident factors and corresponding losses which can enhance the understanding of structural fire risks; and 2) evaluate different structural fire risk levels and their potential high-risk ones can be flagged for ultimately formulating mitigation strategies in a more targeted and proactive manner.

Faculty Supervisor:

Mohamed Ezzeldin;Anas Abdallah

Student:

Partner:

Co-operators (General Insurance)

Discipline:

Engineering

Sector:

Finance and Insurance

University:

McMaster University

Program: