Shapley Value-Guided Adaptive Ensemble Learning for Explainable Financial Fraud Detection with U.S. Regulatory Compliance Validation

TL;DR

This paper proposes a SHAP-guided adaptive ensemble method for explainable financial fraud detection that aligns with U.S. regulatory standards, demonstrating superior performance and explanation quality.

Contribution

It introduces the SGAE model that dynamically adjusts ensemble weights based on SHAP explanations, enhancing detection accuracy and compliance.

Findings

XGBoost with TreeExplainer shows near-perfect stability (W=0.9912).

SGAE achieves the highest AUC-ROC of 0.9245 in experiments.

GNN-GraphSAGE attains AUC-ROC 0.9248 and F1=0.6013 on the IEEE-CIS dataset.

Abstract

Financial crime costs U.S. institutions over $32 billion each year. Although AI tools for fraud detection have become more advanced, their use in real-world systems still faces a major obstacle: many of these models operate as black boxes that cannot provide the transparent, auditable explanations required by regulations such as OCC Bulletin 2011-12 and Federal Reserve SR 11-7. This study makes three main contributions. First, it offers a thorough evaluation of explanation quality across faithfulness (sufficiency and comprehensiveness at k=5, 10, and 15) and stability (Kendall's W across 30 bootstrap samples). XGBoost paired with TreeExplainer achieves near-perfect stability (W=0.9912), while LSTM with DeepExplainer shows weak results (W=0.4962). Second, the paper introduces the SHAP-Guided Adaptive Ensemble (SGAE), which dynamically adjusts per-transaction ensemble weights based on SHAP attribution agreement, achieving the highest AUC-ROC among all tested models (0.8837 held-out; 0.9245 cross-validation). Third, a complete three-architecture evaluation of LSTM, Transformer, and GNN-GraphSAGE on the full 590,540-transaction IEEE-CIS dataset is provided, with GNN-GraphSAGE achieving AUC-ROC 0.9248 and F1=0.6013. All results are mapped directly to OCC, SR 11-7, and BSA-AML regulatory compliance requirements.