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

• URL: http://arxiv.org/abs/2601.17773v1
• Date: Sun, 25 Jan 2026 10:19:04 GMT
• Title: MarketGANs: Multivariate financial time-series data augmentation using generative adversarial networks
• Authors: Jeonggyu Huh, Seungwon Jeong, Hyun-Gyoon Kim, Hyeng Keun Koo, Byung Hwa Lim,
• Abstract summary: MarketGAN is a factor-based generative framework for high-dimensional asset return generation under severe data scarcity.<n>We embed an explicit asset-pricing factor structure as an economic inductive bias and generate returns as a single joint vector.<n>Using daily returns of large U.S. equities, we find that MarketGAN more closely matches empirical stylized facts of asset returns.
• Score: 4.104902299123294
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• MaGNet: A Mamba Dual-Hypergraph Network for Stock Prediction via Temporal-Causal and Global Relational Learning [3.2859360081297715]
  This work introduces MaGNet, a novel Mamba dual-hyperGraph Network for stock prediction.<n>MaGNet integrates a MAGE block, Feature-wise and Stock-wise 2D Spatiotemporal Attention modules, and a dual hypergraph framework.<n>Experiments on six major stock indices demonstrate MaGNet outperforms state-of-the-art methods in both superior predictive performance and exceptional investment returns.
  arXiv  Detail & Related papers  (2025-10-29T20:47:16Z)
• FactorGCL: A Hypergraph-Based Factor Model with Temporal Residual Contrastive Learning for Stock Returns Prediction [16.70420232738428]
  We propose a hypergraph-based factor model with temporal residual contrastive learning (FactorGCL)<n>To mine hidden factors that supplement human-designed prior factors for predicting stock returns, we design a cascading residual hypergraph architecture.<n>Our experiments on real stock market data demonstrate that FactorGCL outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-02-05T12:37:15Z)
• STORM: A Spatio-Temporal Factor Model Based on Dual Vector Quantized Variational Autoencoders for Financial Trading [55.02735046724146]
  In financial trading, factor models are widely used to price assets and capture excess returns from mispricing.<n>We propose a Spatio-Temporal factOR Model based on dual vector quantized variational autoencoders, named STORM.<n>Storm extracts features of stocks from temporal and spatial perspectives, then fuses and aligns these features at the fine-grained and semantic level, and represents the factors as multi-dimensional embeddings.
  arXiv  Detail & Related papers  (2024-12-12T17:15:49Z)
• Copula Variational LSTM for High-dimensional Cross-market Multivariate Dependence Modeling [46.75628526959982]
  We make the first attempt to integrate variational sequential neural learning with copula-based dependence modeling. Our variational neural network WPVC-VLSTM models variational sequential dependence degrees and structures across time series. It outperforms benchmarks including linear models, volatility models, deep neural networks, and variational recurrent networks in cross-market portfolio forecasting.
  arXiv  Detail & Related papers  (2023-05-09T08:19:08Z)
• Factor Investing with a Deep Multi-Factor Model [123.52358449455231]
  We develop a novel deep multi-factor model that adopts industry neutralization and market neutralization modules with clear financial insights. Tests on real-world stock market data demonstrate the effectiveness of our deep multi-factor model.
  arXiv  Detail & Related papers  (2022-10-22T14:47:11Z)
• Forecasting Financial Market Structure from Network Features using Machine Learning [0.6999740786886535]
  We propose a model that forecasts market correlation structure from link- and node-based financial network features using machine learning. We provide empirical evidence using three different network filtering methods to estimate market structure, namely Dynamic Asset Graph (DAG), Dynamic Minimal Spanning Tree (DMST) and Dynamic Threshold Networks (DTN) Experimental results show that the proposed model can forecast market structure with high predictive performance with up to $40%$ improvement over a time-invariant correlation-based benchmark.
  arXiv  Detail & Related papers  (2021-10-22T12:51:32Z)
• Temporal-Relational Hypergraph Tri-Attention Networks for Stock Trend Prediction [45.74513775015998]
  We present a collaborative temporal-relational modeling framework for end-to-end stock trend prediction. A novel hypergraph tri-attention network (HGTAN) is proposed to augment the hypergraph convolutional networks. In this manner, HGTAN adaptively determines the importance of nodes, hyperedges, and hypergraphs during the information propagation among stocks.
  arXiv  Detail & Related papers  (2021-07-22T02:16:09Z)
• A Sentiment Analysis Approach to the Prediction of Market Volatility [62.997667081978825]
  We have explored the relationship between sentiment extracted from financial news and tweets and FTSE100 movements. The sentiment captured from news headlines could be used as a signal to predict market returns; the same does not apply for volatility. We developed an accurate classifier for the prediction of market volatility in response to the arrival of new information.
  arXiv  Detail & Related papers  (2020-12-10T01:15:48Z)
• Transformer Hawkes Process [79.16290557505211]
  We propose a Transformer Hawkes Process (THP) model, which leverages the self-attention mechanism to capture long-term dependencies. THP outperforms existing models in terms of both likelihood and event prediction accuracy by a notable margin. We provide a concrete example, where THP achieves improved prediction performance for learning multiple point processes when incorporating their relational information.
  arXiv  Detail & Related papers  (2020-02-21T13:48:13Z)
• Detecting Changes in Asset Co-Movement Using the Autoencoder Reconstruction Ratio [5.5616364225463055]
  We propose a real-time indicator to detect temporary increases in asset co-movements. The Autoencoder Reconstruction Ratio measures how well a basket of asset returns can be modelled using a lower-dimensional set of latent variables.
  arXiv  Detail & Related papers  (2020-01-23T22:33:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.