Hybrid Data can Enhance the Utility of Synthetic Data for Training Anti-Money Laundering Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911171301343232 |
|---|---|
| author | Chung, Rachel Sharma, Pratyush Nidhi Siponen, Mikko Vadodaria, Rohit Smith, Luke |
| author_facet | Chung, Rachel Sharma, Pratyush Nidhi Siponen, Mikko Vadodaria, Rohit Smith, Luke |
| contents | Money laundering is a critical global issue for financial institutions. Automated Anti-money laundering (AML) models, like Graph Neural Networks (GNN), can be trained to identify illicit transactions in real time. A major issue for developing such models is the lack of access to training data due to privacy and confidentiality concerns. Synthetically generated data that mimics the statistical properties of real data but preserves privacy and confidentiality has been proposed as a solution. However, training AML models on purely synthetic datasets presents its own set of challenges. This article proposes the use of hybrid datasets to augment the utility of synthetic datasets by incorporating publicly available, easily accessible, and real-world features. These additions demonstrate that hybrid datasets not only preserve privacy but also improve model utility, offering a practical pathway for financial institutions to enhance AML systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18499 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hybrid Data can Enhance the Utility of Synthetic Data for Training Anti-Money Laundering Models Chung, Rachel Sharma, Pratyush Nidhi Siponen, Mikko Vadodaria, Rohit Smith, Luke Machine Learning Money laundering is a critical global issue for financial institutions. Automated Anti-money laundering (AML) models, like Graph Neural Networks (GNN), can be trained to identify illicit transactions in real time. A major issue for developing such models is the lack of access to training data due to privacy and confidentiality concerns. Synthetically generated data that mimics the statistical properties of real data but preserves privacy and confidentiality has been proposed as a solution. However, training AML models on purely synthetic datasets presents its own set of challenges. This article proposes the use of hybrid datasets to augment the utility of synthetic datasets by incorporating publicly available, easily accessible, and real-world features. These additions demonstrate that hybrid datasets not only preserve privacy but also improve model utility, offering a practical pathway for financial institutions to enhance AML systems. |
| title | Hybrid Data can Enhance the Utility of Synthetic Data for Training Anti-Money Laundering Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.18499 |