用可解释模型拆解A股收益预测因子，发现行为信号主导预测能力。
Interpretable Factor Decomposition for Decision Intelligence in Large-Scale Financial Markets: Evidence from China's A-Share Market
- 基于XGBoost与TreeSHAP的可解释机器学习流程，分解个股收益预测贡献。
- 模型月均超额收益2.38%，年化夏普比2.23，对冲四因子后仍显著。
- 行为类因子（换手率、动量）贡献58.2%，远超估值因子的10.7%。
我们提出一个可解释的机器学习流程，将横截面股票收益可预测性分解为可审计的因子贡献。在2009至2019年间中国A股市场3,632只股票上应用XGBoost模型结合TreeSHAP归因分析，并进行压力测试。在预测方面，使用60个月滚动窗口覆盖55个月的样本外数据，XGBoost模型平均AUC为0.547（排序IC=0.119），多空组合月均超额收益为+2.38%（Newey-West t=5.94；年化夏普比2.23）。该收益在调整Carhart四因子模型后仍保持显著（+2.31%/月；t=7.48）。在解释层面，SHAP分解显示，行为信号（换手率与动量）平均占预测贡献的58.2%，远高于估值比率的10.7%，跨50个行业组别。消融分析验证了这一排序，并揭示了SHAP与消融方法差异所体现的特征可替代性结构，该结构单独使用任一方法难以察觉。
原文摘要 · Abstract (English)
We present an interpretable machine learning pipeline to decompose cross-sectional equity return predictability into auditable factor contributions. We apply an XGBoost model with TreeSHAP attribution and conduct stress testing on 3,632 Chinese A-share stocks from 2009 until 2019. On prediction, using 60-month rolling windows over 55 months of out-of-sample data, XGBoost obtains a mean AUC of 0.547 (rank IC = 0.119) and +2.38%/month (Newey-West t = 5.94; annualized Sharpe 2.23) long-short spread for the top vs bottom quintiles. This alpha is persistent after adjusting for the Carhart four-factor model (+2.31%/month; t = 7.48). On interpretation, SHAP decomposition indicates that behavioral signals (turnover and momentum) account for 58.2% of predictive attribution compared to 10.7% for valuation ratios, on average, across 50 industry groups. Ablation analysis serves to cross-validate this ranking and provides evidence that SHAP and ablation diverge in a manner that highlights feature substitutability structure that is largely invisible to either method used in isolation.
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。