用可解释性指导模型集成，提升金融欺诈检测的合规性与准确率。
Shapley Value-Guided Adaptive Ensemble Learning for Explainable Financial Fraud Detection with U.S. Regulatory Compliance Validation
- 基于SHAP值一致性动态调整模型权重，实现自适应集成
- 在59万条交易数据上达AUC-ROC 0.9248，优于其他模型
- 结果直接对应美国监管要求，支持审计与合规验证
金融犯罪每年给美国机构带来超过320亿美元损失。尽管欺诈检测的AI工具日益先进，但其在真实系统中的应用仍面临重大障碍：许多模型为黑箱，无法提供法规（如OCC Bulletin 2011-12和Federal Reserve SR 11-7）所要求的透明、可审计解释。本研究有三大贡献：首先，全面评估了解释质量，包括忠实性（k=5,10,15时的充分性与完备性）与稳定性（30次bootstrap样本下的Kendall's W）。XGBoost+TreeExplainer实现近完美稳定性（W=0.9912），而LSTM+DeepExplainer表现较差（W=0.4962）。其次，提出SHAP-Guided Adaptive Ensemble（SGAE），根据每笔交易的SHAP归因一致性动态调整集成权重，在留出集上取得最高AUC-ROC（0.8837），交叉验证达0.9245。第三，对LSTM、Transformer和GNN-GraphSAGE在完整590,540笔交易的IEEE-CIS数据集上进行三架构评估，其中GNN-GraphSAGE表现最优，AUC-ROC为0.9248，F1=0.6013。所有结果均映射至OCC、SR 11-7及BSA-AML合规要求。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。