Scalable Graph Learning for Anti-Money Laundering: A First Look
This work addresses the problem of anti-money laundering for financial institutions and law enforcement, but it is incremental as it provides a first look and preliminary results.
The paper tackles the challenge of detecting money laundering by applying scalable graph convolutional neural networks to massive, dense, and dynamic financial data, reporting preliminary results on a synthetic graph with 1 million nodes and 9 million edges using a custom simulator called AMLSim.
Organized crime inflicts human suffering on a genocidal scale: the Mexican drug cartels have murdered 150,000 people since 2006, upwards of 700,000 people per year are "exported" in a human trafficking industry enslaving an estimated 40 million people. These nefarious industries rely on sophisticated money laundering schemes to operate. Despite tremendous resources dedicated to anti-money laundering (AML) only a tiny fraction of illicit activity is prevented. The research community can help. In this brief paper, we map the structural and behavioral dynamics driving the technical challenge. We review AML methods, current and emergent. We provide a first look at scalable graph convolutional neural networks for forensic analysis of financial data, which is massive, dense, and dynamic. We report preliminary experimental results using a large synthetic graph (1M nodes, 9M edges) generated by a data simulator we created called AMLSim. We consider opportunities for high performance efficiency, in terms of computation and memory, and we share results from a simple graph compression experiment. Our results support our working hypothesis that graph deep learning for AML bears great promise in the fight against criminal financial activity.