Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation

arXiv cs.LG / 4/6/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces ExSTraQt, a supervised learning framework to extract suspicious or money-laundering transactions using a quasi-temporal graph representation of financial activity.
It argues that conventional AML systems based on predefined risk rules can be costly and produce many false positives, motivating more scalable ML-based detection.
ExSTraQt is designed to be simple (few parameters and straightforward architecture) while remaining efficient in compute and memory footprint.
Evaluation on a real transaction dataset and multiple synthetic datasets shows consistent improvements in F1 score, including up to a 1% uplift on the real data and over 8% on one synthetic dataset.
The authors claim the approach can complement existing bank AML workflows and provide the associated code and datasets via their GitHub repository.

Abstract

Money laundering presents a persistent challenge for financial institutions worldwide, while criminal organizations constantly evolve their tactics to bypass detection systems. Traditional anti-money laundering approaches mainly rely on predefined risk-based rules, leading to resource-intensive investigations and high numbers of false positive alerts. In order to restrict operational costs from exploding, while billions of transactions are being processed every day, financial institutions are investing in more sophisticated mechanisms to improve existing systems. In this paper, we present ExSTraQt (EXtract Suspicious TRAnsactions from Quasi-Temporal graph representation), an advanced supervised learning approach to detect money laundering (or suspicious) transactions in financial datasets. Our proposed framework excels in performance, when compared to the state-of-the-art AML (Anti Money Laundering) detection models. The key strengths of our framework are sheer simplicity, in terms of design and number of parameters; and scalability, in terms of the computing and memory requirements. We evaluated our framework on transaction-level detection accuracy using a real dataset; and a set of synthetic financial transaction datasets. We consistently achieve an uplift in the F1 score for most datasets, up to 1% for the real dataset; and more than 8% for one of the synthetic datasets. We also claim that our framework could seamlessly complement existing AML detection systems in banks. Our code and datasets are available at https://github.com/mhaseebtariq/exstraqt.