Representation learning with a transformer by contrastive learning for money laundering detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908447214141440 |
|---|---|
| author | Guéneau, Harold Celisse, Alain Delange, Pascal |
| author_facet | Guéneau, Harold Celisse, Alain Delange, Pascal |
| contents | The present work tackles the money laundering detection problem. A new procedure is introduced which exploits structured time series of both qualitative and quantitative data by means of a transformer neural network. The first step of this procedure aims at learning representations of time series through contrastive learning (without any labels). The second step leverages these representations to generate a money laundering scoring of all observations. A two-thresholds approach is then introduced, which ensures a controlled false-positive rate by means of the Benjamini-Hochberg (BH) procedure. Experiments confirm that the transformer is able to produce general representations that succeed in exploiting money laundering patterns with minimal supervision from domain experts. It also illustrates the higher ability of the new procedure for detecting nonfraudsters as well as fraudsters, while keeping the false positive rate under control. This greatly contrasts with rule-based procedures or the ones based on LSTM architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08835 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Representation learning with a transformer by contrastive learning for money laundering detection Guéneau, Harold Celisse, Alain Delange, Pascal Machine Learning Artificial Intelligence Statistics Theory Risk Management Statistical Finance The present work tackles the money laundering detection problem. A new procedure is introduced which exploits structured time series of both qualitative and quantitative data by means of a transformer neural network. The first step of this procedure aims at learning representations of time series through contrastive learning (without any labels). The second step leverages these representations to generate a money laundering scoring of all observations. A two-thresholds approach is then introduced, which ensures a controlled false-positive rate by means of the Benjamini-Hochberg (BH) procedure. Experiments confirm that the transformer is able to produce general representations that succeed in exploiting money laundering patterns with minimal supervision from domain experts. It also illustrates the higher ability of the new procedure for detecting nonfraudsters as well as fraudsters, while keeping the false positive rate under control. This greatly contrasts with rule-based procedures or the ones based on LSTM architectures. |
| title | Representation learning with a transformer by contrastive learning for money laundering detection |
| topic | Machine Learning Artificial Intelligence Statistics Theory Risk Management Statistical Finance |
| url | https://arxiv.org/abs/2507.08835 |