Towards Learning to Discover Money Laundering Sub-network in Massive Transaction Network
Ziwei Chai, Yang Yang, Jiawang Dan, Sheng Tian, Changhua Meng, Weiqiang Wang, Yifei Sun
Abstract
Anti-money laundering (AML) systems play a critical role in safeguarding global economy. As money laundering is considered as one of the top group crimes, there is a crucial need to discover money laundering sub-network behind a particular money laundering transaction for a robust AML system. However, existing rule-based methods for money laundering sub-network discovery is heavily based on domain knowledge and may lag behind the modus operandi of launderers. Therefore, in this work, we first address the money laundering sub-network discovery problem with a neural network based approach, and propose an AML framework AMAP equipped with an adaptive sub-network proposer. In particular, we design an adaptive sub-network proposer guided by a supervised contrastive loss to discriminate money laundering transactions from massive benign transactions. We conduct extensive experiments on real-word datasets in AliPay of Ant Group. The result demonstrates the effectiveness of our AMAP in both money laundering transaction detection and money laundering sub-network discovering. The learned framework which yields money laundering sub-network from massive transaction network leads to a more comprehensive risk coverage and a deeper insight to money laundering strategies.
BibTeX
@article{Chai_Yang_Dan_Tian_Meng_Wang_Sun_2023, title={Towards Learning to Discover Money Laundering Sub-network in Massive Transaction Network}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26656}, DOI={10.1609/aaai.v37i12.26656}, abstractNote={Anti-money laundering (AML) systems play a critical role in safeguarding global economy. As money laundering is considered as one of the top group crimes, there is a crucial need to discover money laundering sub-network behind a particular money laundering transaction for a robust AML system. However, existing rule-based methods for money laundering sub-network discovery is heavily based on domain knowledge and may lag behind the modus operandi of launderers. Therefore, in this work, we first address the money laundering sub-network discovery problem with a neural network based approach, and propose an AML framework AMAP equipped with an adaptive sub-network proposer. In particular, we design an adaptive sub-network proposer guided by a supervised contrastive loss to discriminate money laundering transactions from massive benign transactions. We conduct extensive experiments on real-word datasets in AliPay of Ant Group. The result demonstrates the effectiveness of our AMAP in both money laundering transaction detection and money laundering sub-network discovering. The learned framework which yields money laundering sub-network from massive transaction network leads to a more comprehensive risk coverage and a deeper insight to money laundering strategies.}, number={12}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Chai, Ziwei and Yang, Yang and Dan, Jiawang and Tian, Sheng and Meng, Changhua and Wang, Weiqiang and Sun, Yifei}, year={2023}, month={Jun.}, pages={14153-14160} }