English

FairFinGAN: Fairness-aware Synthetic Financial Data Generation

Machine Learning 2026-03-06 v1

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.

Keywords

Cite

@article{arxiv.2603.05327,
  title  = {FairFinGAN: Fairness-aware Synthetic Financial Data Generation},
  author = {Tai Le Quy and Dung Nguyen Tuan and Trung Nguyen Thanh and Duy Tran Cong and Huyen Giang Thi Thu and Frank Hopfgartner},
  journal= {arXiv preprint arXiv:2603.05327},
  year   = {2026}
}

Comments

Accepted to Special Session: Data Science: Foundations and Applications (DSFA), PAKDD 2026

R2 v1 2026-07-01T11:05:09.241Z