mlsanityData to 14 Oct 2026

Realistic Synthetic Financial Transactions for Anti-Money Laundering Models

arXiv 2306.16424 ↗First posted 22 Jun 2023cs.AI cs.LG q-fin.CPcited by 50

Not on the map. Why?

Abstract (arXiv)

With the widespread digitization of finance and the increasing popularity of cryptocurrencies, the sophistication of fraud schemes devised by cybercriminals is growing. Money laundering -- the movement of illicit funds to conceal their origins -- can cross bank and national boundaries, producing complex transaction patterns. The UN estimates 2-5% of global GDP or 0.8 - 2.0 trillion dollars are laundered globally each year. Unfortunately, real data to train machine learning models to detect laundering is generally not available, and previous synthetic data generators have had significant shortcomings. A realistic, standardized, publicly-available benchmark is needed for comparing models and for the advancement of the area. To this end, this paper contributes a synthetic financial transaction dataset generator and a set of synthetically generated AML (Anti-Money Laundering) datasets. We have calibrated this agent-based generator to match real transactions as closely as possible and made the datasets public. We describe the generator in detail and demonstrate how the datasets generated can help compare different machine learning models in terms of their AML abilities. In a key way, using synthetic data in these comparisons can be even better than using real data: the ground truth labels are complete, whilst many laundering transactions in real data are never detected.

Key facts. Cited by 50 papers in the map (data through 14 Oct 2026). Builds on 28 of its 60 references that are in the map. First posted on arXiv 22 Jun 2023.

Builds on

28 of 60 references.

References · 28

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  7. 2018Datasheets for Datasetscited by 1,386
  8. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  9. 2018Deep Graph Infomaxcited by 1,106
  10. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  11. 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
  12. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
16 more
  1. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 313
  2. 2020Can Graph Neural Networks Count Substructures?cited by 236
  3. 2019Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensicscited by 164
  4. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
  5. 2021A Review on Graph Neural Network Methods in Financial Applicationscited by 78
  6. 2018Scalable Graph Learning for Anti-Money Laundering: A First Lookcited by 33
  7. 2020xFraud: Explainable Fraud Transaction Detectioncited by 28
  8. 2023Provably Powerful Graph Neural Networks for Directed Multigraphscited by 27
  9. 2022LaundroGraph: Self-Supervised Graph Representation Learning for Anti-Money Launderingcited by 20
  10. 2021Efficient Scaling of Dynamic Graph Neural Networkscited by 11
  11. 2019Synthesizing Credit Card Transactionscited by 10
  12. 2022Ethereum Fraud Detection with Heterogeneous Graph Neural Networkscited by 9
  13. 2020Knowledge Discovery in Cryptocurrency Transactions: A Surveycited by 8
  14. 2022Scalable Fine-Grained Parallel Cycle Enumeration Algorithmscited by 3
  15. 2023Fast Parallel Algorithms for Enumeration of Simple, Temporal, and Hop-Constrained Cyclescited by 3
  16. 2017The ParallelEye Dataset: Constructing Large-Scale Artificial Scenes for Traffic Vision Researchcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 13; 2025: 10; 2026: 27.

50 papers.

Sort:

By area:

  1. 2024Graph Neural Networks for Financial Fraud Detection: A Reviewcited by 25
  2. 2024Network Analytics for Anti-Money Laundering -- A Systematic Literature Review and Experimental Evaluationcited by 7
  3. 2024When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmarkcited by 6
  4. 2024Improve Fidelity and Utility of Synthetic Credit Card Transaction Time Series from Data-centric Perspectivecited by 5
  5. 2024Graph Feature Preprocessor: Real-time Subgraph-based Feature Extraction for Financial Crime Detectioncited by 4
  6. 2024Temporal Graph Networks for Graph Anomaly Detection in Financial Networkscited by 4
  7. 2025Exploring the In-Context Learning Capabilities of LLMs for Money Laundering Detection in Financial Graphscited by 3
  8. 2024Translating Expert Intuition into Quantifiable Features: Encode Investigator Domain Knowledge via LLM for Enhanced Predictive Analyticscited by 2
  9. 2025TeMP-TraG: Edge-based Temporal Message Passing in Transaction Graphscited by 2
  10. 2024Pretext Training Algorithms for Event Sequence Datacited by 1
  11. 2024Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Launderingcited by 1
  12. 2024MEGA: Message Passing Neural Networks for Multigraphs with EdGe Attributescited by 1
38 more
  1. 2025Deep Learning Approaches for Anti-Money Laundering on Mobile Transactions: Review, Framework, and Directionscited by 1
  2. 2025Advances in Continual Graph Learning for Anti-Money Laundering Systems: A Comprehensive Reviewcited by 1
  3. 2025A Graph Machine Learning Approach for Detecting Topological Patterns in Transactional Graphscited by 1
  4. 2026PersonaLedger: Generating Realistic Financial Transactions with Persona Conditioned LLMs and Rule Grounded Feedbackcited by 1
  5. 2026Detecting Complex Money Laundering Patterns with Incremental and Distributed Graph Modelingcited by 1
  6. 2024A Customer Level Fraudulent Activity Detection Benchmark for Enhancing Machine Learning Model Research and Evaluationcited by 0
  7. 2024Behavioral Sequence Modeling with Ensemble Learningcited by 0
  8. 2024Multi-Class and Multi-Task Strategies for Neural Directed Link Predictioncited by 0
  9. 2025Amatriciana: Exploiting Temporal GNNs for Robust and Efficient Money Laundering Detectioncited by 0
  10. 2025GARG-AML against Smurfing: A Scalable and Interpretable Graph-Based Framework for Anti-Money Launderingcited by 0
  11. 2025FD4QC: Application of Classical and Quantum-Hybrid Machine Learning for Financial Fraud Detection A Technical Reportcited by 0
  12. 2025AMLNet: A Knowledge-Based Multi-Agent Framework to Generate and Detect Realistic Money Laundering Transactionscited by 0
  13. 2025Hybrid Data can Enhance the Utility of Synthetic Data for Training Anti-Money Laundering Modelscited by 0
  14. 2026Synthetic Pattern Generation and Detection of Financial Activities using Graph Autoencoderscited by 0
  15. 2026HybridFL: A Federated Learning Approach for Financial Crime Detectioncited by 0
  16. 2026Tide: A Customisable Dataset Generator for Anti-Money Laundering Researchcited by 0
  17. 2026DPxFin: Adaptive Differential Privacy for Anti-Money Laundering Detection via Reputation-Weighted Federated Learningcited by 0
  18. 2026Extracting Money Laundering Transactions from Quasi-Temporal Graph Representationcited by 0
  19. 2026TransXion: A High-Fidelity Graph Benchmark for Realistic Anti-Money Launderingcited by 0
  20. 2026TRAVELFRAUDBENCH: A Configurable Evaluation Framework for GNN Fraud Ring Detection in Travel Networkscited by 0
  21. 2026Federated Layer-Wise Exchange for Cross-Client Money Laundering Pattern Detectioncited by 0
  22. 2026Mechanical Enforcement for LLM Governance:Evidence of Governance-Task Decoupling in Financial Decision Systemscited by 0
  23. 2026Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networkscited by 0
  24. 2026Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Modelscited by 0
  25. 2026TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systemscited by 0
  26. 2026Choosing a parallel heterogeneous ensemble method for tabular classificationcited by 0
  27. 2026Detecting Money Laundering in Rwandan Mobile Money: A Machine Learning Frameworkcited by 0
  28. 2026Temporal Graph Prototype-conditioned Conformal Prediction for Fraud Detectioncited by 0
  29. 2026KONTOGRAPH: Verified Point-in-Time Feature Consistency and Amortised Explanation for Real-Time Anti-Money Laundering under a 200 ms Decision Budgetcited by 0
  30. 2026Population-Calibrated Graph Screening at 835-Million-Address Scale, with Label-Free Transfer to New Chainscited by 0
  31. 2026FINESSE: An Agent-Based Simulator and Benchmark Dataset for Multimodal Financial Event Sequencescited by 0
  32. 2026PixSim: a calibrated open-source simulator of instant-payment fraud, recovery and interdiction under analyst capacity constraintscited by 0
  33. 2026DynGraphAgentBench: A Benchmark for Agentic Lifecycle Control in Dynamic Graph Anomaly Detectioncited by 0
  34. 2026Behavior-Grounded Semantic Enrichment for Financial Fraud Modeling and Reasoningcited by 0
  35. 2026Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflowscited by 0
  36. 2026AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosiscited by 0
  37. 2026Privacy-Preserving GNN Inference on Financial Transaction Graphs via Homomorphic Encryptioncited by 0
  38. 2026Random Probing for Structural Self-Interactions in Graph Neural Networkscited by 0