# Clue-Guided Money Laundering Group Discovery

Source: [Clue-Guided Money Laundering Group Discovery](<https://www.sota2.com/research/paper/6a3e0788206542251d7cb45d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-27T05:00:04.727Z

Authors: Boyang Wang, Jianing Cao

Published: 2026-06-24T13:57:22.000Z

## Abstract

Money Laundering Group Discovery (MLGD) aims to identify hidden criminal groups and recover their complete structures in large-scale financial networks. Existing graph anomaly detection methods mainly produce node-level risk alerts, while global group discovery methods passively search for suspicious groups over the whole network. Both are mismatched with real Anti-money-laundering (AML) investigations, where analysts usually start from a concrete clue and gradually expand the investigation to recover the responsible group. To address this gap, we propose Clue-Guided Group Discovery (CGGD), where a laundering group is progressively recovered from an initial clue set through analyst interaction. We further propose Clue2Group, a framework that first constructs a compact local investigation context to reduce noise and preserve chain-like and cycle-like laundering structures. It then estimates a clue-conditioned local risk field with a multi-semantic local-temporal GNN, and finally integrates risk, structural, and prior-pattern evidence to recover a coherent laundering group. Experiments on two large-scale AML benchmarks show that Clue2Group provides a practical clue-driven analysis framework for AML investigations, offering a feasible step toward bridging the gap between graph-based AML research and real investigation workflows.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Money Laundering Risk Ranking on HI Small](<https://www.sota2.com/research/sota/money-laundering-risk-ranking-on-hi-small.md>): Money Laundering Risk Ranking; HI-Small; AUC: 78.79.

- [Money Laundering Risk Ranking on HI Medium](<https://www.sota2.com/research/sota/money-laundering-risk-ranking-on-hi-medium.md>): Money Laundering Risk Ranking; HI Medium; AUC: 0.7699.

- [Group recovery on HI Small](<https://www.sota2.com/research/sota/group-recovery-on-hi-small.md>): Group recovery; HI-Small; Precision: 30.3.

- [Group Recovery on HI Medium](<https://www.sota2.com/research/sota/group-recovery-on-hi-medium.md>): Group recovery; HI Medium; Precision: 35.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.26189>)

[PDF](<https://arxiv.org/pdf/2606.26189.pdf>)
