Risk-Aware Density–Boundary Graph Reweighting for Rare Event Detection in Intelligent Risk Monitoring Systems

Abstract

Rare-event detection is a critical task in intelligent risk monitoring systems, where missed minority events may lead to financial loss, security threats, or operational failures. Existing imbalance-handling methods frequently apply one class-level correction and therefore ignore the heterogeneous geometric roles of minority observations. This study presents density–boundary graph reweighting (DBGR), a unified sample-level weighting framework that combines continuous minority sparsity and majority-boundary exposure and regularizes the resulting scores through a minority-only K-nearest-neighbor graph. Its methodological contribution lies in this joint pre-training formulation and in producing classifier-compatible weights, rather than in claiming novelty for density estimation, graph propagation, or weighting individually. Two variants are considered: DBGR-Safe for sparse and relatively safe minority prototypes and DBGR-Danger for sparse boundary observations. Experiments on financial fraud detection, industrial fault diagnosis, and network intrusion detection show recall-oriented gains with XGBoost and reduced variability for the tested LightGBM setting, while the benefit is limited for Random Forest. On Creditcard, DBGR-Danger improves Recall from 0.8223 to 0.8949 and F2 from 0.8410 to 0.8931. On NSL-KDD U2R, focal loss remains better in Recall, F2, and PR-AUC, whereas DBGR-Safe achieves the best F1. DBGR is therefore positioned as a complementary, classifier-compatible strategy rather than a universally superior imbalance-handling method.