Tab-AML: A Transformer Based Transaction Monitoring Model for Anti-Money Laundering
Authors: Oztas, B., Cetinkaya, D., Adedoyin, F., Budka, M., Aksu, G. and Dogan, H.
Conference: IEEE Conference on Artificial Intelligence (IEEE CAI 2025)
Dates: 5-7 May 2025
Abstract:Money laundering signifies a major challenge and risk in the global economic landscape. We introduce Tab- AML, a deep-learning model for transaction monitoring that achieves high detection accuracy while significantly reducing false positives. Incorporating a dual-masked Transformer encoder with a shared embedding component and Residual Attention Layers, Tab-AML achieved an ROC-AUC of 93.01, a 98% true positive rate, and a 51% false positive rate on the SAML- D dataset, outperforming models such as TabTransformer and XGBoost. These findings highlight the potential of transformer- based models in advancing anti-money laundering efforts.
Source: Manual
