LaundroGraph: Self-Supervised Graph Representation Learning for Anti-Money Laundering

TL;DR

LaundroGraph introduces a self-supervised graph neural network approach to improve anti-money laundering systems by encoding financial transactions into meaningful representations, reducing false positives, and aiding analysts in identifying suspicious activities.

Contribution

It presents the first fully self-supervised graph representation learning system for AML, outperforming baselines in link prediction on real-world data.

Findings

Outperforms strong baselines in link prediction by 12 percentage points in AUC

Uses a customer-transaction bipartite graph for meaningful representations

Enhances AML review efficiency with AI-powered insights

Abstract

Anti-money laundering (AML) regulations mandate financial institutions to deploy AML systems based on a set of rules that, when triggered, form the basis of a suspicious alert to be assessed by human analysts. Reviewing these cases is a cumbersome and complex task that requires analysts to navigate a large network of financial interactions to validate suspicious movements. Furthermore, these systems have very high false positive rates (estimated to be over 95\%). The scarcity of labels hinders the use of alternative systems based on supervised learning, reducing their applicability in real-world applications. In this work we present LaundroGraph, a novel self-supervised graph representation learning approach to encode banking customers and financial transactions into meaningful representations. These representations are used to provide insights to assist the AML reviewing process, such as identifying anomalous movements for a given customer. LaundroGraph represents the underlying network of financial interactions as a customer-transaction bipartite graph and trains a graph neural network on a fully self-supervised link prediction task. We empirically demonstrate that our approach outperforms other strong baselines on self-supervised link prediction using a real-world dataset, improving the best non-graph baseline by $12$ p.p. of AUC. The goal is to increase the efficiency of the reviewing process by supplying these AI-powered insights to the analysts upon review. To the best of our knowledge, this is the first fully self-supervised system within the context of AML detection.