High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework

2026-05-26

AI Summary

Existing general-purpose generative models struggle to accurately reproduce the key statistical properties—known as “stylized facts”—of financial time series, particularly exhibiting notable deficiencies in modeling cross-asset dependencies. This work proposes a novel hybrid approach that integrates conditional generative adversarial networks (GANs) with diffusion models. Specifically, it first employs CoMeTS-GAN to generate multivariate price and volume sequences that capture realistic correlation structures, then innovatively embeds the GAN discriminator into the diffusion process as a quality-guidance module to explicitly enhance the fidelity of correlations in the synthetic data. The method consistently outperforms state-of-the-art generative models across multiple benchmarks, achieving superior accuracy in capturing financial stylized facts while maintaining computational efficiency and significantly improving the modeling of joint multi-asset distributions.

Abstract

In recent years, financial institutions and firms have increasingly adopted synthetic data to address data scarcity and to generate counterfactual market scenarios. However, reproducing all the statistical properties of financial time series, commonly known as stylized facts, remains an open challenge for many existing general-purpose architectures. In this paper, we present a quality-aware generative framework that combines two classes of generative methods, demonstrating how their integration addresses existing limitations while enhancing the realism of synthetic data. Specifically, we first introduce CoMeTS-GAN (Correlated Multivariate Time Series GAN), a Conditional Generative Adversarial Network (C-GAN) designed to jointly generate mid-price and volume time-series for correlated stocks. We then show how our GAN architecture can be incorporated into state-of-the-art diffusion models to enhance the quality of generated correlation structures. Specifically, the GAN's Critic serves as a quality evaluation module that guides the diffusion process, enforcing learned correlation structures in the generated time-series. Our framework offers a lightweight and responsive solution for realistic stock market simulation, explicitly modeling inter-asset correlation structures. We experimentally validate our framework against leading generative architectures, showing that it more effectively captures the stylized facts of stock markets and models inter-asset correlations.

Problem

• synthetic financial time series
• stylized facts
• inter-asset correlation
• generative models
• data scarcity

Innovation

• GAN-Diffusion Framework
• CoMeTS-GAN
• Stylized Facts
• Inter-asset Correlation
• Synthetic Financial Time Series