Improving Road and Vehicle Safety Through Administrative Register Data: Sustainable Road Safety Analytics for Romania (2023–2025) via Dual Severity and Context Clustering

Road traffic injuries remain a central challenge for sustainable transport, public health, and mobility governance. The task of monitoring these injuries requires indicators that jointly capture harm severity, road and environmental context, and patterns of vehicle involvement at scale. Using harmonised English-language Romanian police crash exports (2023–2025), we build 92,790 records with 36 variables and estimate two complementary k -means typologies: a severity partition based on the fatality, injury, and vehicle-count fields (a register proxy for involvement, not vehicle-type attributes) and a context partition based on the road, environment, mechanism, and cause fields with one-hot encoding and TruncatedSVD. Reported tables and figures reproduce the archived MiniBatch pipeline for replication; for context, full-batch k -means clustering on the same embedding is the recommended default when cross-year prevalence stability is required (train–test TVD 0.039 versus 0.569 under MiniBatch). We report silhouette-guided choices ( k = 6 severity, k = 4 context), cross-seed stability, feature ablations, and a 2023–2024 versus 2025 prevalence comparison. A Pearson χ 2 test on severity × context labels reveals strong statistical significance, yet Cramér’s V remains small—statistical association with limited practical coupling, consistent with complementary rather than redundant partitions. Limitations include police-reported injury counts; a coarse vehicle proxy; weak context geometry; and large MiniBatch context drift, which binds inference to within-year descriptive profiling unless analysts refit the model, add version labels, or adopt full-batch context clustering. The contribution is an integrated, reproducible profiling and governance workflow for dashboards and follow-on modelling—not a fixed multi-year cluster taxonomy.