Rare-Event Road-Traffic Fatality Prediction: A Reproducible Machine-Learning Benchmark with Time-Aware Validation, Calibration, and Interpretability
This study develops a reproducible machine-learning benchmark for rare-event road-traffic fatality prediction using an urban incident registry from Medellín, Colombia and clarifies the limits of registry-based prediction when exposure, traffic-flow, roadway, infrastructure, weather, and post-crash response variables ar...