发表机构
Peking University; The Chinese University of Hong Kong, Shenzhen; International Digital Economy Academy (IDEA); Cornell University; The Hong Kong University of Science and Technology, Guangzhou（北京大学; 香港中文大学（深圳）; 国际数字经济发展研究院; 康奈尔大学; 香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对股票预测中股票间与时间依赖混淆及单变量目标局限，提出LiMT分层多任务学习框架，集成流动性感知信号，通过MRE、LDL和APO模块提升预测与组合优化，在CSI300/500上表现最优，回测中显著提升收益与夏普比率。
AI 中文摘要
股票价格预测是计算金融领域长期存在的挑战，其难点在于市场的内在随机性和复杂的时间模式。尽管近期的深度学习模型通过联合建模股票间和时间的价格动态提高了预测准确性，但它们将股票间关系与股票内时间依赖性混为一谈，并且仅关注价格走势的单变量目标。为解决这些局限性，我们提出了LiMT，一个集成了流动性感知信号的分层多任务学习框架，用于股票价格预测。LiMT采用市场状态编码器（MRE）模块，首先提取同期跨股票依赖性，然后对每只股票的时间动态进行建模，产生统一的潜在状态。在此潜在状态的基础上，我们引入了流动性驱动学习（LDL）模块，这是一个专家混合架构，具有跨任务门控机制，以联合预测价格走势、波动率和交易量。我们进一步设计了一种自适应投资组合优化（APO）机制，将多任务预测转化为在交易成本和流动性约束下可执行的组合权重。在CSI300和CSI500基准上的大量实验表明，LiMT在报告指标上优于强神经和基于树的基线。在现实的CSI300回测中，与等权重相比，APO将年化收益从3.99%提高到10.01%，夏普比率从1.22提高到1.86，表明多任务预测可转化为可部署的投资组合收益。
英文摘要
Stock price forecasting is a long-standing challenge in computational finance, driven by the inherent randomness of markets and complex temporal patterns. While recent deep-learning models have raised forecasting accuracy by jointly modeling inter-stock and temporal price dynamics, they conflate inter-stock relationships with intra-stock temporal dependencies and focus solely on the univariate objective of price movement. To address these limitations, we propose LiMT, a Hierarchical Multi-Task Learning framework that integrates liquidity-aware signals for stock price forecasting. LiMT employs a Market Regime Encoder (MRE) module that first extracts contemporaneous cross-stock dependencies, then models each stock's temporal dynamics, yielding a unified latent state. Building on this latent state, we introduce a Liquidity-Driven Learning (LDL) module, a mixture-of-experts architecture that features cross-task gating mechanisms to jointly predict price movement, volatility, and trading volume. We further design an Adaptive Portfolio Optimization (APO) mechanism that converts multi-task forecasts into executable portfolio weights under transaction-cost and liquidity constraints. Extensive experiments on the CSI300 and CSI500 benchmarks show that LiMT performs best among strong neural and tree-based baselines across the reported metrics. In realistic CSI300 backtests, APO improves annualized return from 3.99% to 10.01% and Sharpe ratio from 1.22 to 1.86 over equal weighting, showing that the multi-task forecasts translate into deployable portfolio gains.
