可解释机器学习与股指收益率预测的经济价值——来自中国市场的证据

摘要：

本文针对上证综指和深证成指，搭建了一个同时具备预测能力和可解释性的多模态混合框架.输入端汇集了宏观经济、市场交易、企业盈利和投资者情绪4类信息.建模时,先用CEEMDAN把收益率序列按尺度分解，由LighiGBM挑出各频段的关键特征，再分别用 Attention-LSTM,Attention-GRU和 LSTM 拟合高、中、低频分量,最后由SVR做非线性集成.在样本外检验中,混合模型在两个市场都取得了正的调整后样本外R²--上证0.48%.深证1.23%，均优于线性基准和单一深度学习模型.SHAP分析显示，真正驱动预测的主要是宏观货币与价格类变量.择时方面，在long-cash策略、0.1%交易成本的设定下，混合模型相对买入持有改善了风险调整后绩效.这些结果为多模态机器学习用于股指收益率预测、并兼顾可解释性与经济价值，提供了来自中国市场的经验证据.

This paper builds a multimodal hybrid framework for the Shanghai Composite index and the Shenzhen Component index that aims to be both predictive and interpretable. On the input side it draws on four kinds of information-macro-eonomic conditions, market trading. corporate earnings, and investor sentiment. The modeling proceeds in stages: CEEM-DAN first decomposes the return series by scale,LightGBM selects the key features within each frequency band, Attention-LSTM, Attention-GRU. and LSTM then fit the high-, medium-, and low-frequency components respectively, and SVR carries out the nonlinear ensemble. The hybrid model attains a positive adjusted external examination R² in both markets-0.48 % for Shanghai and 1.23 % for Shenzhen-outperformning linear benchmarks and a single deep-learning model. SHAP analysis shows that the predictions are driven mainly by monetary and price-related macroeconomic variables. On the timing side, under a long-cash strategy with a 0.1% transaction cost, the hybrid model improves risk-adjusted performance relative to buy-and-hold.Taken together, these results offer evidence from the Chinese market on the interpretability and economic value of multimodal machine learning for stock index return forecasting.

作者：

李艳

Li Yan

机构地区：

河南大学商学院

引用本文：

李艳.可解释机器学习与股指收益率预测的经济价值一来自中国市场的证据[J].河南师范大学学报(自然科学报).2026.54(5):11-20.(Li Yan.Interpretable machine learning and the economic value of stock index return forecasts:Evidence from Chinese stock market[J].Journal of Henan Normal University (Natural Science Edition),2026,54(5):11-20.DOI:10.16366/j.cnki.1000-2367.2026.05.31.0001.)

基金：

国家社会科学基金

关键词：

股指收益率预测;多模态数据;可解释机器学习;SHAP;市场择时

stock index return forecasting; multimodal data; interpretable machine learning; SHAP; market timing

分类号：

F830.91;TP181

可解释机器学习与股指收益率预测的经济价值—来自中国市场的证据.pdf