What is it about?
The research advances the SOTA (state-of-the-art) for effectively detecting money laundering activities in banks' transaction data. The main contributions are as follows: 1. A rich set of graph-based features for a downstream supervised learning task 2. Massively parallelizable implementation of complex subgraph metrics 3. A novel method for quantifying (temporal) flow-based money laundering activities Our method, ExSTraQt, quite comfortably outperforms the most advanced SOTA models.
Featured Image
Photo by J K on Unsplash
Why is it important?
Money laundering presents a persistent challenge for financial institutions worldwide, while criminal organizations constantly evolve their tactics to bypass detection systems.
Read the Original
This page is a summary of: Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation, March 2026, ACM (Association for Computing Machinery),
DOI: 10.1145/3748522.3779790.
You can read the full text:
Resources
Contributors
The following have contributed to this page
