Hybrid Data can Enhance the Utility of Synthetic Data for Training Anti-Money Laundering Models
This work addresses data scarcity for financial institutions developing automated AML systems, offering an incremental improvement over purely synthetic data approaches.
The paper tackles the problem of training anti-money laundering models with limited real data due to privacy concerns by proposing hybrid datasets that combine synthetic data with publicly available real-world features, resulting in improved model utility while preserving privacy.
Money laundering is a critical global issue for financial institutions. Automated Anti-money laundering (AML) models, like Graph Neural Networks (GNN), can be trained to identify illicit transactions in real time. A major issue for developing such models is the lack of access to training data due to privacy and confidentiality concerns. Synthetically generated data that mimics the statistical properties of real data but preserves privacy and confidentiality has been proposed as a solution. However, training AML models on purely synthetic datasets presents its own set of challenges. This article proposes the use of hybrid datasets to augment the utility of synthetic datasets by incorporating publicly available, easily accessible, and real-world features. These additions demonstrate that hybrid datasets not only preserve privacy but also improve model utility, offering a practical pathway for financial institutions to enhance AML systems.