cs.LGNov 10, 2026

Market-Conditioned JEPA: Learning from Unpredictable Market Shocks

Authors: Yuqi Wang, Fengyuan Liu, Mukai Li, Haochen Luo, Lei Li, Qi Liu

Organizations: The University of Hong Kong · Grace Investment Machine

Abstract

Much of the variation in financial time series is driven by market-wide shocks that cannot be predicted from an asset's own history. Per-asset self-supervised learning treats this variation as irreducible noise. Under a latent factor model, we show that conditioning prediction on the realized market factor makes the asset's market exposure necessary for optimal prediction, while reducing the noise against which the asset-specific component is learned. Building on this insight, we introduce Market-Conditioned JEPA (MC-JEPA), a joint-embedding predictive architecture for financial time series. During training, we construct a leave-one-out market condition for each asset from the future target embeddings of other assets and incorporate it through factor loadings derived from the asset's own representation. On 11 years of minute-level Chinese A-share data, MC-JEPA improves over per-asset JEPA across nine targets spanning returns, market exposure, risk, and liquidity, with the strongest and most statistically significant gains in exposure, risk, and liquidity. It achieves the best RankIC on all liquidity targets and on return horizons from two hours to five days, outperforming time-series foundation models and self-supervised baselines, and delivers the best portfolio performance in a historical backtest. Ablations show that the return and exposure gains require the condition to be aligned with the realized market movement. After restoring the volatility scale removed by normalization, the predictor's factor loadings rank stocks by market beta nearly as well as a supervised probe, without labels. A synthetic factor-model study with known parameters shows that conditioning improves the recovery of both market exposure and the asset-specific component.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. STOCK-JEPA: Prior-Anchored Latent Revision Representation Learning in Equity Markets

    Oct 4, 2026Yizhi Luo, Jiahe Yi, Jianhui Zhang +1Quantitative FinanceJoint-Embedding Predictive Architecture

  2. Towards Financial World Modeling

    Oct 6, 2026Humzah Merchant, Alec Guthrie, Simon Mahns +2Representation LearningTime Series Representation Learning

  3. DIVINE: Simple Cross-Market Stock Pretraining via Diverse Indicator Reconstruction

    Oct 2, 2026Kuan-Yu Chen, Shu-Cheng Zheng, Yu-Chen Den +2Financial Time SeriesSelf-Supervised Pre-Training