EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Privacy Preserving Risk Modeling Across Financial Institutions via Federated Learning with Adaptive Optimization

James Whitmore, Priya Mehra, Jingwen Yang, Emily Linford

Frontiers in Artificial Intelligence Research · 2025

DOI: 10.71465/fair230 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Artificial Intelligence Research, 2025. Verfasst von James Whitmore und 3 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a privacy-aware risk control method based on federated learning, named FedRisk, which aims to mitigate the long-standing conflict between data isolation and information sharing among financial institutions. By integrating the FedAvg algorithm with differential privacy, the method allows banking, e-commerce, and insurance entities to update model parameters jointly without exposing raw user data. To address distributional discrepancies caused by non-independent and identically distributed (non-IID) data, a dynamic weighting scheme is applied. The approach is validated using real-world data from 820,000 users, covering contract performance, repayment behavior, and credit defaults. Compared with a conventional centralized XGBoost model, FedRisk shows a moderate drop in AUC from 0.874 to 0.861 (approximately 1.5%) but effectively safeguards user privacy. In out-of-bag (OOB) testing, the F1-score improves by 3.7%, suggesting better adaptability to unseen data. Overall, FedRisk provides a practical balance between model performance and privacy preservation in financial risk detection across institutions.

Zitieren

APA

Whitmore, J., Mehra, P., Yang, J., & Linford, E. (2025). Privacy Preserving Risk Modeling Across Financial Institutions via Federated Learning with Adaptive Optimization. Frontiers in Artificial Intelligence Research. https://doi.org/10.71465/fair230

Vancouver

Whitmore J, Mehra P, Yang J, Linford E. Privacy Preserving Risk Modeling Across Financial Institutions via Federated Learning with Adaptive Optimization. Frontiers in Artificial Intelligence Research. 2025. doi:10.71465/fair230

BibTeX
@article{Whitmore2025,
  author = {Whitmore, James and Mehra, Priya and Yang, Jingwen and Linford, Emily},
  title = {Privacy Preserving Risk Modeling Across Financial Institutions via Federated Learning with Adaptive Optimization},
  journal = {Frontiers in Artificial Intelligence Research},
  year = {2025},
  doi = {10.71465/fair230}
}
Kostenlos starten →