TransXion: A High-Fidelity Graph Benchmark for Realistic Anti-Money Laundering

TL;DR

TransXion introduces a realistic, large-scale benchmark dataset for anti-money laundering that incorporates rich entity profiles and non-template illicit activity, challenging existing detection models.

Contribution

It presents a novel, realistic transaction graph benchmark with profile-aware simulation and stochastic illicit subgraph generation for AML research.

Findings

TransXion reproduces key structural properties of real payment networks.

Detection models perform significantly worse on TransXion than on traditional benchmarks.

The dataset enables evaluation of context-aware AML detection methods.

Abstract

Money laundering poses severe risks to global financial systems, driving the widespread adoption of machine learning for transaction monitoring. However, progress remains stifled by the lack of realistic benchmarks. Existing transaction-graph datasets suffer from two pervasive limitations: (i) they provide sparse node-level semantics beyond anonymized identifiers, and (ii) they rely on template-driven anomaly injection, which biases benchmarks toward static structural motifs and yields overly optimistic assessments of model robustness. We propose TransXion, a benchmark ecosystem for Anti-Money Laundering (AML) research that integrates profile-aware simulation of normal activity with stochastic, non-template synthesis of illicit subgraphs.TransXion jointly models persistent entity profiles and conditional transaction behavior, enabling evaluation of "out-of-character" anomalies where observed activity contradicts an entity's socio-economic context. The resulting dataset comprises approximately 3 million transactions among 50,000 entities, each endowed with rich demographic and behavioral attributes. Empirical analyses show that TransXion reproduces key structural properties of payment networks, including heavy-tailed activity distributions and localized subgraph structure. Across a diverse array of detection models spanning multiple algorithmic paradigms, TransXion yields substantially lower detection performance than widely used benchmarks, demonstrating increased difficulty and realism. TransXion provides a more faithful testbed for developing context-aware and robust AML detection methods. The dataset and code are publicly available at https://github.com/chaos-max/TransXion.