Chinese Equity Index Enhancement with Stratified Sampling and Factor Optimization

Summary

This report surveys quantitative enhancement of Chinese equity indices, aiming to outperform a benchmark while controlling tracking error. It places multi-factor models at the center of the approach: estimate returns and risks through factor exposures, then constrain portfolio exposure to manage benchmark-relative risk. It also outlines a top-down framework spanning market timing, industry rotation, and stock selection, and notes that IPO subscriptions, discounted index futures, and other derivatives can provide additional sources of return or capital efficiency.

The empirical section compares stratified sampling—selecting stocks within industry and market-cap groups—with linear optimization that balances expected returns against risk-factor exposures. Backtests from 2008 to 2017 report excess returns alongside tracking errors for CSI 300 and CSI 500 implementations. These historical results illustrate the trade-off between enhancement and benchmark-relative risk; they do not establish future performance. The report cautions that changing market behavior can cause enhanced portfolios to underperform their indices.

Key ideas

• Index enhancement seeks benchmark outperformance while keeping tracking error under control.
• Multi-factor models manage risk by controlling portfolio exposure to selected factors.
• Enhancement decisions can span market timing, industry rotation, and stock selection.
• Stratified sampling and factor-constrained optimization are two tested portfolio construction methods.
• Historical backtest results may not persist if market patterns change.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.