Road traffic accident severity prediction using causal inference and machine learning

The global rise in road traffic accidents presents substantial challenges across economic, societal, and public health domains, leading to millions of injuries and fatalities annually. Current studies on modeling and analyzing traffic accident frequency largely treat the issue as a classification task, primarily utilizing learning-based or ensemble methods. However, these approaches frequently neglect the intricate relationships among the multifaceted factors—such as road complexity, environmental conditions, driver behavior, and contextual elements—that contribute to traffic accidents and hazardous scenarios. We propose an approach that employs causal inference and causal Machine Learning (ML) techniques to predict accident severity and identify key causal factors. We evaluate our proposed approach with two datasets, from Ethiopia and UK. Given the inherent imbalance in these datasets, the Synthetic Minority Oversampling Technique (SMOTE) is utilized to achieve balanced data representation. Uplift modeling and causal inference methods are employed for severity prediction. Individual Treatment Effect (ITE) and Average Treatment Effect (ATE) are used to make interpretations of the predictions. Our research contributes to understanding and mitigating the impact of road traffic accidents through advanced causal analysis techniques, offering actionable insights for policymakers, urban planners, and public health officials globally.