Real-Time Driver Safety Scoring Through Inverse Crash Probability Modeling
This work addresses the need for real-time, interpretable driver safety scoring for applications like ADAS and fleet management, representing an incremental improvement over existing binary models.
The paper tackles the problem of limited actionable insights from binary crash prediction models by introducing SafeDriver-IQ, a framework that transforms these into continuous 0-100 safety scores, achieving strong discriminative performance and revealing that 87% of crashes involve multiple co-occurring risk factors with non-linear compounding effects increasing risk to 4.5x baseline.
Road crashes remain a leading cause of preventable fatalities. Existing prediction models predominantly produce binary outcomes, which offer limited actionable insights for real-time driver feedback. These approaches often lack continuous risk quantification, interpretability, and explicit consideration of vulnerable road users (VRUs), such as pedestrians and cyclists. This research introduces SafeDriver-IQ, a framework that transforms binary crash classifiers into continuous 0-100 safety scores by combining national crash statistics with naturalistic driving data from autonomous vehicles. The framework fuses National Highway Traffic Safety Administration (NHTSA) crash records with Waymo Open Motion Dataset scenarios, engineers domain-informed features, and incorporates a calibration layer grounded in transportation safety literature. Evaluation across 15 complementary analyses indicates that the framework reliably differentiates high-risk from low-risk driving conditions with strong discriminative performance. Findings further reveal that 87% of crashes involve multiple co-occurring risk factors, with non-linear compounding effects that increase the risk to 4.5x baseline. SafeDriver-IQ delivers proactive, explainable safety intelligence relevant to advanced driver-assistance systems (ADAS), fleet management, and urban infrastructure planning. This framework shifts the focus from reactive crash counting to real-time risk prevention.