Generative AI for Banks: Benchmarks and Algorithms for Synthetic Financial Transaction Data

TL;DR

This paper evaluates and benchmarks five generative AI models for creating synthetic financial transaction data, addressing privacy and data utility challenges in banking.

Contribution

It systematically compares leading generative models across multiple criteria, providing guidance for selecting appropriate algorithms in financial contexts.

Findings

DoppelGANger excels in privacy-sensitive applications

Financial Diffusion and TVAE are best for data replication and augmentation

CTGAN offers a balanced performance across all criteria

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.