Model Results Phase 3 ratified

XGBoost + LightGBM trained on Victorian crash dataset (197k crashes, temporal split). Phase 3 ratified.

Model Comparison Speed gradient — exploratory findings Phase 3 ✅

Model	Role	AUC-ROC	AUC-PR	RMSE	MAE-ord	Brier	ECE
XGBoost / LightGBM	Primary	—	—	—	—	—	—
Ordered Logit	Primary	—	—	—	—	—	—
Random Forest	Baseline	—	—	—	—	—	—
Negative Binomial II	Supplementary	—	—	—	—	—	—

Metrics update when PROMETHEUS delivers training results. Primary models shown in blue. Bias toward recall for safety applications (threshold explorer below).

Speed–Severity Gradient Key finding: lower speeds = higher serious/fatal rate Inverted Relationship

Standard intuition: high speed = high risk. Victoria data: serious/fatal rate is 27% higher at 30km/h vs 100km/h. This is not a model error — it reflects urban road reality: more pedestrians, cyclists, conflict points at low speeds. Safety interventions should target urban low-speed zones (30–60km/h), not just high-speed arterials.

Threshold Explorer Precision–Recall tradeoff Safety: bias recall

Recall ↑Threshold: 0.50Precision ↑

Feature Importance Top 10

Speed limit

—

Time of day

—

Road curvature

—

Weather

—

Lighting

—

Surface type

—

Alcohol involvement

—

DCA code

—

Risk Tier Breakdown % of dataset

Tier	Count	Pct	Colour
Loading…

Confusion Matrix

Confusion matrix renders when model is trained