Market-Conditioned JEPA（MC-JEPA）：从不测市场冲击中学习金融时序
Market-Conditioned JEPA: Learning from Unpredictable Market Shocks
AI 导读
MC-JEPA 是一种面向金融时序的联合嵌入预测架构，通过将预测条件设定在已实现市场因子上，使资产的市场暴露成为最优预测的必要条件。在 11 年分钟级中国 A 股数据上，它在收益、市场暴露、风险和流动性共九个目标上超越逐资产 JEPA，在所有流动性目标及 2 小时至 5 天收益区间上取得最佳 RankIC，并在历史回测中获得最佳组合表现。
正文 · 原文
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.
| Comments: | 23 pages, 4 figures, 14 tables |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE) |
| Cite as: | arXiv:2611.13572 [cs.LG] |
| (or arXiv:2611.13572v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13572 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuqi Wang [view email]
[v1]
Tue, 10 Nov 2026 04:40:04 UTC (300 KB)
来源：arXiv cs.AI · arxiv.org