发表机构
The Hong Kong University of Science and Technology; Shanghai Jiaotong University; Beijing Zhongguancun Academy（香港科技大学; 上海交通大学; 北京中关村学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出Stock-JEPA，一种联合嵌入预测框架，通过先验锚定和上下文条件修正学习股票市场中的可预测增量表示，在理论和实验上均优于现有基线。
AI 中文摘要
学习有效的表示有助于从低信噪比的金融数据中刻画股票市场的结构和动态。黑盒深度模型能够捕捉复杂模式，但可能过拟合样本噪声，且缺乏明确的经济结构。与此同时，经典的线性金融模型提供了可解释的参考，但其过度简化的假设无法捕捉非线性信号。为了结合这两个方向的优势，我们提出了Stock-JEPA，一种联合嵌入预测框架，该框架学习相对于时间点金融先验的可预测增量修正。首先，我们利用一个低复杂度的金融模型生成总结多周期收益和风险的固定统计量。然后，一个先验投影器将这些统计量映射到目标编码器的潜在空间中作为锚点。其次，我们设计了一个上下文条件修正预测器，以估计未来表示相对于锚点的可预测位移。两个分支通过分离的损失函数进行更新：锚点从先验统计量中学习，而修正则从历史上下文中捕捉额外的可预测信息。第三，我们冻结所有表示模块，训练一个下游读取器，并通过横截面排序和投资组合表现评估其预测。理论上，我们证明了最优修正将先验锚点对同一未来表示的期望平方误差减少了恰好 $\mathbb{E}[\\|\boldsymbol{\Delta}\\|_2^2]$。这一非负增益是历史上下文中可预测的额外信号的期望平方幅度。实验上，Stock-JEPA在大型中国和美国股票池中，在5个关键评估指标上优于13个强基线。消融研究和表示分析进一步证明了学习到的修正对股票市场表示学习的价值。
英文摘要
Learning effective representations helps characterize the structure and dynamics of equity markets from financial data with a low signal-to-noise ratio. Black-box deep models can capture complex patterns but may overfit sample noise and lack explicit economic structure. Meanwhile, classic linear financial models provide interpretable references, but their oversimplified assumptions leave non-linear signals uncaptured. To combine the strengths of these two directions, we propose Stock-JEPA, a joint-embedding predictive framework that learns predictable incremental revisions relative to a point-in-time financial prior. First, we leverage a low-complexity financial model to produce fixed statistics summarizing multi-horizon return and risk. A prior projector then maps these statistics into the target encoder's latent space as an anchor. Second, we design a context-conditioned revision predictor to estimate the future representation's predictable displacement from the anchor. Separate losses update the two branches: the anchor learns from prior statistics, while the revision captures additional predictable information from historical context. Third, we freeze all representation modules and train a downstream readout, evaluating its forecasts through cross-sectional ranking and portfolio performance. Theoretically, we prove that optimal revision reduces the prior anchor's expected squared error for the same future representation by exactly $\mathbb{E}[\|\boldsymbolΔ\|_2^2]$. This non-negative gain is the expected squared magnitude of the additional signal predictable from historical context. Experimentally, Stock-JEPA outperforms 13 strong baselines across large-scale China and U.S. equity universes on 5 key evaluation metrics. Ablation studies and representation analysis further demonstrate the value of the learned revisions for representation learning in equity markets.
