[MOVING TOWARDS GREATER SAFETY]
Risk Scoring Engine
QUANTIFY RISKS // PREVENT CRASHES // OPTIMIZE INFRASTRUCTURE
Roadscor’s Risk Scoring Engine bridges the gap between digital traffic models and real-world human consequences. By quantifying severity through a combination of simulated physics, medical outcomes, and economic impact, our process enables a rigorous, evidence-based approach to safety evaluation long before implementation on-site.
Evidence-Based Mapping & Medical Outcomes
Developed in collaboration with VUFO (TU Dresden) and utilizing the GIDAS database, Roadscor anchors risk in observed physics rather than generic assumptions.
- Real-World Mapping: We extract precise kinematic descriptors—including relative speed, impact angle, vehicle mass, and road-user type (including age for VRUs)—to map simulated conflicts to statistically comparable real-world accidents.
- Probabilistic MAIS Outcomes: Using VUFO data, we determine the probability of Maximum Abbreviated Injury Scale (MAIS) outcomes. This provides a distribution of injury levels, from minor to fatal, offering a realistic spectrum of risk rather than a single deterministic guess.
Quantifying Economic Impact
Roadscor translates injury risk into monetary impact, enabling objective cost-benefit analysis. Developed with W2Economics and Wim Wijnen (World Bank, OECD), our methodology aligns with global standards for road-safety appraisal.
- Injury-to-Cost Mapping: We map probabilistic MAIS outcomes to specific costs, including medical expenses, productivity loss, and human suffering.
- Global Localization: Roadscor includes harmonized cost sets for 35 countries in local currencies. For other regions, we apply income-based scaling to ensure the data remains geographically relevant and defensible.
Advanced Weighting & Traceability
To ensure that high-severity risks are never overlooked, the engine utilizes sophisticated scoring logic:
- Probabilistic Modeling: We calculate an “Expected Value” rather than a static figure. By weighting all plausible injury outcomes, we ensure that rare, high-consequence events are accurately represented in the final risk profile.
- Non-Linear Weighting: A Fibonacci-based scheme ensures high-severity risks are appropriately emphasized. This reflects their true societal impact and prevents fatal risks from being “averaged out” by lower-severity interactions.
- Traceable Metrics & Auditability: Each score remains fully traceable to the original route pairing, kinematic inputs, and economic assumptions. This ensures a transparent and defensible audit trail for securing project approvals and budgets.
Roadscor transforms safety data into a clear economic justification. By grounding analysis in real crash outcomes, the Risk Scoring Engine allows planners to prioritize infrastructure investments that protect both lives and public funds.