Amatriciana: Exploiting Temporal GNNs for Robust and Efficient Money Laundering Detection

2024-12-09

2024 IEEE International Conference on Data Mining Workshops (ICDMW)

AI Summary

Detecting dynamic money laundering activities on financial transaction graphs remains challenging due to the need for fine-grained temporal modeling over evolving, large-scale graphs. Method: This paper proposes an end-to-end whole-graph temporal graph neural network (T-GNN) framework that, unlike mainstream time-slicing approaches, directly incorporates fine-grained timestamp information across the entire transaction graph to model global temporal dependencies. It employs a lightweight whole-graph temporal encoding scheme coupled with node-level anomaly detection to ensure both computational efficiency and robustness. Contribution/Results: Experiments demonstrate that the model achieves an F1-score of 0.76—significantly outperforming state-of-the-art methods—while reducing false positive rates by 55%. Moreover, it exhibits strong generalization under few-shot settings, enabling real-time anti-money laundering (AML) monitoring with minimal labeling effort. This work establishes a new paradigm for low-cost, high-accuracy AML in dynamic financial networks.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Money laundering is a financial crime that poses a serious threat to financial integrity and social security. The growing number of transactions makes it necessary to use automatic tools that help law enforcement agencies detect such criminal activity. In this work, we present Amatriciana, a novel approach based on Graph Neural Networks to detect money launderers inside a graph of transactions by considering temporal information. Amatriciana uses the whole graph of transactions without splitting it into several time-based subgraphs, exploiting all relational information in the dataset. Our experiments on a public dataset reveal that the model can learn from a limited amount of data. Furthermore, when more data is available, the model outperforms other State-of-the-art approaches; in particular, Amatriciana decreases the number of False Positives (FPs) while detecting many launderers. In summary, Amatriciana achieves an F1 score of 0.76. In addition, it lowers the FPs by 55% with respect to other State-of-the-art models.

Problem

• Detect money laundering using temporal Graph Neural Networks
• Improve detection accuracy while reducing false positives
• Handle large transaction graphs without time-based splitting

Innovation

• Uses Temporal GNNs for money laundering detection
• Exploits entire transaction graph without splitting
• Reduces false positives by 55% over benchmarks