Project Description:

This project investigates the underlying causes of fatal traffic crashes in the United States using advanced machine learning (ML) techniques to enhance road safety. Each year, traffic crashes claim over 42,000 lives nationwide, inflicting significant social, economic, and health burdens. Traditional analytical methods have struggled to capture the complex, nonlinear interactions among factors such as driver behavior, vehicle characteristics, roadway design, and environmental conditions. To address this limitation, this project employs data-driven ML models to identify key determinants of fatal crashes and generate actionable insights for evidence-based safety interventions.

The research activities will proceed in four phases. First, comprehensive crash data will be collected from the National Highway Traffic Safety Administration (NHTSA) and integrated across multiple datasets to ensure completeness and consistency. Next, statistical analysis and visualization will be used to identify spatial and temporal trends in crash patterns, revealing geographic disparities and risk concentrations. In the modeling phase, several machine learning algorithms—Balanced Bagging, Balanced Random Forest, and RUSBoost—will be developed and compared against traditional logistic regression models to enhance prediction accuracy in imbalanced datasets. Finally, the top-performing model will be used to assess variable importance and generate policy-relevant recommendations.

The objective of this project is to develop predictive models that accurately identify risk factors associated with fatal crashes and support data-informed decision-making by transportation agencies. The findings will guide targeted interventions such as improved traffic regulations, safer roadway designs, and enhanced vehicle technologies. This research will provide a scalable analytical framework for improving transportation safety and sustainability nationwide.

US DOT Priorities: 

This project aligns with the U.S. DOT priorities by promoting durable, efficient, and safe transportation systems. By identifying key factors contributing to fatal crashes, the project supports better infrastructure planning and targeted safety improvements that extend roadway safety and reduce maintenance needs. The use of advanced machine learning enhances efficiency by enabling transportation agencies to allocate resources strategically, minimize crash-related congestion, and improve traffic flow. Collectively, these efforts contribute to a safer, more reliable, and responsible transportation network.

Outputs:

This project will utilize analytical tools to enhance transportation safety through data-driven methods. It will produce advanced machine learning models specifically designed to predict fatal crashes in imbalanced datasets, providing greater accuracy and interpretability than traditional approaches. The project will also result in a comprehensive, standardized crash database integrating multiple NHTSA sources, along with refined data-processing and model-evaluation techniques that can be applied in future studies. By identifying the most influential factors contributing to fatal crashes, the project will deliver actionable insights for infrastructure planning, policy development, and enforcement strategies. The final technical report will compile all findings, methodologies, and recommendations, offering a replicable framework for improving roadway safety and promoting sustainable transportation systems nationwide.

Outcomes/Impacts:

The project outcomes will directly improve the safety and reliability of the U.S. transportation system through data-driven decision-making. The machine learning models developed in this project will enable transportation agencies to identify high-risk locations and causal factors of fatal crashes with greater precision, guiding targeted infrastructure investments, improved roadway designs, and more effective traffic enforcement strategies. These applications will reduce crash frequencies, lower maintenance and healthcare costs, and enhance the overall performance of transportation networks. By integrating predictive analytics into safety management systems, the project will also modernize operational practices and promote proactive risk mitigation. Furthermore, the findings will inform evidence-based policy and regulatory decisions. Taken together, these impacts will advance the U.S. DOT’s goals of achieving a safer, more efficient, and sustainable transportation system.