MarketGANs: Multivariate financial time-series data augmentation using generative adversarial networks

TL;DR

MarketGAN introduces a factor-based generative adversarial network framework for high-dimensional financial time-series data augmentation, effectively capturing complex dependencies and stylized facts in asset returns.

Contribution

It embeds an explicit asset-pricing factor structure within a GAN framework, improving the realism of generated financial data compared to traditional bootstrap methods.

Findings

MarketGAN closely matches empirical stylized facts of asset returns.

It captures cross-sectional dependence and tail co-movement effectively.

Covariance estimates from MarketGAN samples outperform other methods in portfolio applications.

Abstract

This paper introduces MarketGAN, a factor-based generative framework for high-dimensional asset return generation under severe data scarcity. We embed an explicit asset-pricing factor structure as an economic inductive bias and generate returns as a single joint vector, thereby preserving cross-sectional dependence and tail co-movement alongside inter-temporal dynamics. MarketGAN employs generative adversarial learning with a temporal convolutional network (TCN) backbone, which models stochastic, time-varying factor loadings and volatilities and captures long-range temporal dependence. Using daily returns of large U.S. equities, we find that MarketGAN more closely matches empirical stylized facts of asset returns, including heavy-tailed marginal distributions, volatility clustering, leverage effects, and, most notably, high-dimensional cross-sectional correlation structures and tail co-movement across assets, than conventional factor-model-based bootstrap approaches. In portfolio applications, covariance estimates derived from MarketGAN-generated samples outperform those derived from other methods when factor information is at least weakly informative, demonstrating tangible economic value.