用生成对抗网络模拟金融资产收益，解决数据少时的建模难题。
MarketGANs: Multivariate financial time-series data augmentation using generative adversarial networks
- 基于资产定价因子结构设计生成模型，保留跨资产依赖与尾部联动。
- 生成数据更贴近真实市场特征，如厚尾分布、波动聚集和杠杆效应。
- 适合金融风控、投资组合优化等需高维收益模拟的场景。
本文提出MarketGAN，一种基于因子的生成框架，用于在严重数据稀缺条件下生成高维资产收益。通过嵌入显式的资产定价因子结构作为经济先验知识，以单一联合向量生成收益，从而保留截面依赖性、尾部共动性及时间动态。MarketGAN采用带有时间卷积网络（TCN）主干的生成对抗学习，建模随时间变化的因子载荷与波动率，并捕捉长程时间依赖。基于美国大型股票的日度收益数据，实验表明，MarketGAN生成的数据更接近真实市场的典型特征，包括厚尾边际分布、波动聚集、杠杆效应，尤其在高维截面相关结构与资产间的尾部共动性方面表现优异，优于传统基于因子模型的重采样方法。在投资组合应用中，由MarketGAN生成样本推导的协方差估计，在因子信息至少弱相关时，优于其他方法，体现出明显的经济价值。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。