用离散潜在因子+金融先验，提升股票排序预测准确率
Vector-Quantized Discrete Latent Factors Meet Financial Priors: Dynamic Cross-Sectional Stock Ranking Prediction for Portfolio Construction
- 引入向量量化机制捕捉市场结构，抑制噪声
- 在沪深300和标普500上超越多个强基线模型
- 兼顾可解释性，适合量化投资研究者使用
跨股市值收益预测因信噪比低和市场状态动态变化而困难。传统因子模型具有可解释性但灵活性不足，深度学习模型表现强却常忽视金融先验。本文提出PRISM-VQ（融合金融先验的股票预测模型），结合专家先验因子、从横截面结构中学习的向量量化离散潜在因子，以及结构条件下的专家混合模型，生成时变因子载荷。向量量化作为信息瓶颈，抑制噪声同时保留稳健市场结构，离散码既作潜在因子，也作为时间专家特化的路由信号。在CSI 300和S&P 500上的实验表明，该模型在跨股市值收益预测和投资组合表现上持续优于强基线，且保持可解释性。
原文摘要 · Abstract (English)
Predicting cross-sectional stock returns is challenging due to low signal-to-noise ratios and evolving market regimes. Classical factor models offer interpretability but limited flexibility, while deep learning models achieve strong performance yet often underutilize financial priors. We address this gap with PRISM-VQ (PRior-Informed Stock Model with Vector Quantization), a dynamic factor framework that integrates expert prior factors, vector-quantized discrete latent factors learned from cross-sectional structure, and a structure-conditioned Mixture-of-Experts to generate time-varying factor loadings. Vector quantization acts as an information bottleneck that suppresses noise while capturing robust market structure, with discrete codes serving both as latent factors and as routing signals for temporal expert specialization. Experiments on CSI 300 and S&P 500 show consistent improvements in cross-sectional return prediction and portfolio performance over strong baselines while preserving interpretability. Our code is available at https://github.com/finxlab/PRISM-VQ.
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。