研究背景
The rapid expansion of digital banking and mobile financial services creates growing challenges for fraud detection, particularly under severe class imbalance and operational constraints.
框架与实验
This study presents an explainable and adaptive machine-learning framework integrating chronological evaluation, leakage-conscious feature engineering, probability calibration, SHAP-based explainability, and adaptive risk prioritization. Experiments use the synthetic PaySim mobile-money benchmark and compare Logistic Regression, Random Forest, XGBoost, and LightGBM.
结果与校准
XGBoost achieved the strongest fixed-threshold performance, with PR-AUC of 0.5658, ROC-AUC of 0.9068, and F1-score of 0.5369. Platt calibration reduced the test Brier score from 0.1141 to 0.0245, improving probability reliability.
SHAP分析
SHAP analysis identified temporal, destination-account, transaction-type, and amount features as important model drivers.
自适应政策与权衡
An adaptive top-1% policy reduced false positives from 192 to 117, but recall declined from 0.4236 to 0.2122, demonstrating a clear alert-capacity trade-off.
可复现性与局限
The results provide a reproducible methodological framework rather than evidence of deployment performance in Bangladesh, since PaySim is synthetic.
未来方向
Validation using governed real-world financial data is therefore an important direction for future research.