Fed-DPSDG-WGAN: Differentially Private Synthetic Data Generation for Loan Default Prediction via Federated Wasserstein GAN

Lenders typically conduct thorough credit checks to mitigate credit default risk before lending money. Proactively predicting loan defaulters has become increasingly important. However, creating robust deep-learning algorithms that classify loan defaulters requires abundant data, potentially comprom...

وصف كامل

التفاصيل البيبلوغرافية

الحاوية / القاعدة:	IEEE Access
المؤلفون الرئيسيون:	Padmaja Ramachandra, Santhi Vaithiyanathan
التنسيق:	مقال
اللغة:	الإنجليزية
منشور في:	IEEE 2025-01-01
الموضوعات:	Federated learning WGAN CTGAN differentially private data oversampling trivial auto-encoder
الوصول للمادة أونلاين:	https://ieeexplore.ieee.org/document/10930895/