DELATOR: Money Laundering Detection via Multi-Task Learning on Large Transaction Graphs

TL;DR

DELATOR introduces a graph neural network-based framework utilizing multi-task learning and data balancing techniques to improve automatic detection of money laundering activities in large, complex transaction graphs, significantly outperforming existing methods.

Contribution

The paper presents DELATOR, a novel multi-task learning framework with graph neural networks and data balancing for effective money laundering detection in large-scale temporal graphs.

Findings

DELATOR outperforms baselines by 23% in AUC-ROC.

Discovered 7 new suspicious cases among 50 analyzed.

Effective in handling heavily imbalanced graph data.

Abstract

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.