Research map / Label-efficient and robust learning / Recognition and long-tail
Realistic Synthetic Financial Transactions for Anti-Money Laundering Models
Erik Altman, Jovan Blanuša, Luc Von Niederhäusern, Beni Egressy, Andreea Anghel, Kubilay Atasu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use PNA aggregation instead of plain GIN | GNN on AMLworld · HI-Small | minority-class F1 (%): 28.70 -> 56.77 | Improved |
| add edge updates to GIN | GIN · HI-Small | minority-class F1 (%): 28.70 -> 47.73 | Improved |
| train on lower-illicit-ratio (LI) data instead of HI data | GFP + XGBoost · Small | minority-class F1 (%): 63.23 -> 27.30 | Hurt |
| share graph and model across banks versus private graph and model (ablation) | GFP + LightGBM · HI-Medium and HI-Large per-bank | F1 | Improved |
| pretrain on HI data then reuse/fine-tune on LI data | LightGBM and PNA · LI-Medium/Large, LI-Small | F1 | Improved |
Closest papers by meaning
- MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model (ICLR 2025 · similarity 0.81)
- Combating Data Laundering in LLM Training (NeurIPS 2026 · similarity 0.81)
- Debiasing Synthetic Data Generated by Deep Generative Models (NeurIPS 2024 · similarity 0.80)
- Unlocking Post-hoc Dataset Inference with Synthetic Data (ICML 2025 · similarity 0.80)
- The Canary’s Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text (ICML 2025 · similarity 0.80)
- BlockScan: Detecting Anomalies in Blockchain Transactions (NeurIPS 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
