FairFinGAN: Fairness-aware Synthetic Financial Data Generation
This work addresses the problem of biased financial datasets for financial institutions and researchers, aiming to prevent unfair decision-making in automated systems.
This paper proposes FairFinGAN, a WGAN-based framework that generates synthetic financial data while mitigating bias towards protected attributes. It achieves superior fairness metrics compared to existing GAN-based methods without significant loss in data utility across five real-world financial datasets.
Financial datasets often suffer from bias that can lead to unfair decision-making in automated systems. In this work, we propose FairFinGAN, a WGAN-based framework designed to generate synthetic financial data while mitigating bias with respect to the protected attribute. Our approach incorporates fairness constraints directly into the training process through a classifier, ensuring that the synthetic data is both fair and preserves utility for downstream predictive tasks. We evaluate our proposed model on five real-world financial datasets and compare it with existing GAN-based data generation methods. Experimental results show that our approach achieves superior fairness metrics without significant loss in data utility, demonstrating its potential as a tool for bias-aware data generation in financial applications.