Jeonggyu Huh, Seungwon Jeong, Hyun-Gyoon Kim, Hyeng Keun Koo, Byung Hwa Lim
arXiv 25 Jan 2026 · Finance — Statistical Finance
arXiv:2601.17773 · PDF · DOI · OpenAlex · Extracted main text
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.
appendix boundary found by appendix_command · 75% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Wiese, Magnus and Knobloch, Robert and Korn, Ralf and Kretschmer, Pe… (2020) Quant GANs: deep generation of financial time series | 1.000 | 5 | 3 | 100% |
| 2 | Gu, Shihao and Kelly, Bryan and Xiu, Dacheng (2020) Empirical asset pricing via machine learning | 0.843 | 3 | 3 | 100% |
| 3 | Bai, Shaojie and Kolter, J Zico and Koltun, Vladlen (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling | 0.811 | 4 | 2 | 100% |
| 4 | Gulrajani, Ishaan and Ahmed, Faruk and Arjovsky, Martin and Dumoulin… (2017) Improved training of wasserstein gans | 0.737 | 4 | 3 | 50% |
| 5 | Arjovsky, Martin and Chintala, Soumith and Bottou, Léon (2017) Wasserstein generative adversarial networks | 0.737 | 3 | 3 | 67% |
| 6 | Takahashi, Shuntaro and Chen, Yu and Tanaka-Ishii, Kumiko (2019) Modeling financial time-series with generative adversarial networks | 0.737 | 3 | 2 | 100% |
| 7 | Ang, Andrew and Chen, Joseph (2007) CAPM over the long run: 1926–2001 | 0.644 | 2 | 2 | 100% |
| 8 | Bonneel, Nicolas and Rabin, Julien and Peyré, Gabriel and Pfister, H… (2015) Sliced and radon wasserstein barycenters of measures | 0.644 | 2 | 2 | 100% |
| 9 | Chamberlain, Gary (1982) Multivariate regression models for panel data | 0.644 | 2 | 2 | 100% |
| 10 | Cont, Rama and Cucuringu, Mihai and Xu, Renyuan and Zhang, Chao (2022) Tail-gan: Learning to simulate tail risk scenarios | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 53 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.
| Citing paper | Intensity | Mentions | Sections | |
|---|---|---|---|---|
| 1 | Diffolio: A Diffusion Model for Multivariate Probabilistic Financial Time-Series Forecasting and Portfolio Construction | 0.405 | 1 | 1 |