DELATOR: Money Laundering Detection via Multi-Task Learning on Large Transaction Graphs
This addresses the costly and labor-intensive detection of money laundering for governments and financial institutions, though it is an incremental improvement on existing graph-based methods.
The paper tackles the problem of detecting money laundering activities in large transaction graphs by proposing DELATOR, a framework using graph neural networks with multi-task learning, which outperforms baselines by 23% in AUC-ROC and identified 7 new suspicious cases in real experiments.
Money laundering has become one of the most relevant criminal activities in modern societies, as it causes massive financial losses for governments, banks and other institutions. Detecting such activities is among the top priorities when it comes to financial analysis, but current approaches are often costly and labor intensive partly due to the sheer amount of data to be analyzed. Hence, there is a growing need for automatic anti-money laundering systems to assist experts. In this work, we propose DELATOR, a novel framework for detecting money laundering activities based on graph neural networks that learn from large-scale temporal graphs. DELATOR provides an effective and efficient method for learning from heavily imbalanced graph data, by adapting concepts from the GraphSMOTE framework and incorporating elements of multi-task learning to obtain rich node embeddings for node classification. DELATOR outperforms all considered baselines, including an off-the-shelf solution from Amazon AWS by 23% with respect to AUC-ROC. We also conducted real experiments that led to the discovery of 7 new suspicious cases among the 50 analyzed ones, which have been reported to the authorities.