A quantitative methodological framework for traffic accident risk estimation using the Swiss Cheese Model.

A quantitative framework for estimating traffic accident risk based on the Swiss Cheese Model is proposed. While the Swiss Cheese Model is widely recognized for explaining accident causation, its applications have remained qualitative and descriptive. To address this limitation, the proposed framework operationalizes Swiss Cheese Model deficiencies as measurable risk factors and models their multi-layered interactions in the form of system-level trajectories. The framework derives representative values under normal and hazardous conditions, constructs system-level trajectories, and estimates traffic accident risk using machine learning. An empirical analysis demonstrates the framework's ability to identify high-risk configurations. The highest-risk configuration was associated with increased predicted accident risk relative to baseline conditions. The findings indicate that the framework can advance the Swiss Cheese Model from a post-hoc explanatory tool to a system-level framework, providing a methodological foundation for data-driven identification of high-risk configurations to support proactive traffic safety management and policy development.