LGCEJun 11

Interpretable Factor Decomposition for Decision Intelligence in Large-Scale Financial Markets: Evidence from China's A-Share Market

arXiv:2606.12843v11.8
Predicted impact top 100% in LG · last 90 daysOriginality Synthesis-oriented
AI Analysis

For quantitative finance practitioners, the paper provides an interpretable factor decomposition method for Chinese equities, though the performance is modest (AUC 0.547) and the approach is incremental.

The paper presents an interpretable machine learning pipeline using XGBoost and TreeSHAP to decompose equity return predictability in China's A-share market, achieving a mean AUC of 0.547 and a long-short spread of +2.38%/month (Sharpe 2.23) with persistent alpha after Carhart adjustment. Behavioral signals dominate predictive attribution (58.2%) over valuation ratios (10.7%).

We present an interpretable machine learning pipeline to decompose Cross-Sectional Equity Return Predictability into auditable factor contribution. We apply an XGBoost model with TreeSHAP attribution and conduct stress testing on 3632 Chinese A-share stocks from 2009 until 2019. Using 60-month, rolling windows over 55 months of out-of-sample data, XGBoost obtains a mean AUC of 0.547 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). 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 55 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes