Generative AI for Banks: Benchmarks and Algorithms for Synthetic Financial Transaction Data
Abstract
The banking sector faces challenges in using deep learning due to data sensitivity and regulatory constraints, but generative AI may offer a solution. Thus, this study identifies effective algorithms for generating synthetic financial transaction data and evaluates five leading models - Conditional Tabular Generative Adversarial Networks (CTGAN), DoppelGANger (DGAN), Wasserstein GAN, Financial Diffusion (FinDiff), and Tabular Variational AutoEncoders (TVAE) - across five criteria: fidelity, synthesis quality, efficiency, privacy, and graph structure. While none of the algorithms is able to replicate the real data's graph structure, each excels in specific areas: DGAN is ideal for privacy-sensitive tasks, FinDiff and TVAE excel in data replication and augmentation, and CTGAN achieves a balance across all five criteria, making it suitable for general applications with moderate privacy concerns. As a result, our findings offer valuable insights for choosing the most suitable algorithm.
Cite
@article{arxiv.2412.14730,
title = {Generative AI for Banks: Benchmarks and Algorithms for Synthetic Financial Transaction Data},
author = {Fabian Sven Karst and Sook-Yee Chong and Abigail A. Antenor and Enyu Lin and Mahei Manhai Li and Jan Marco Leimeister},
journal= {arXiv preprint arXiv:2412.14730},
year = {2024}
}
Comments
Presented at the 34th Workshop on Information Technologies and Systems (WITS 2024)