FairFinGAN: Fairness-aware Synthetic Financial Data Generation

TL;DR

FairFinGAN is a novel GAN-based framework that generates synthetic financial data with reduced bias, ensuring fairness while maintaining data utility for predictive tasks.

Contribution

It introduces fairness constraints into the GAN training process for bias mitigation in synthetic financial data generation.

Findings

Achieves superior fairness metrics compared to existing methods

Maintains data utility for downstream tasks

Effective across multiple real-world datasets

Abstract

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.