MarketGANs: Multivariate financial time-series data augmentation using generative adversarial networks
This work addresses data scarcity in finance for researchers and practitioners by providing a method to augment high-dimensional asset return data, though it is incremental as it builds on existing GAN and factor model approaches.
The paper tackles the problem of generating realistic multivariate financial time-series data under data scarcity by introducing MarketGAN, a generative adversarial network framework that incorporates economic factor structures. The result shows that MarketGAN better matches empirical stylized facts like heavy-tailed distributions and cross-sectional correlations, and improves covariance estimates for portfolio applications when factor information is informative.
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.