Applying Fama–French Factors to A-Share Stock Selection

Summary

This document outlines a China A-share stock selection strategy using market, size, and book-to-market factors. It starts with constituents of a benchmark index, filters out stocks that are suspended or marked as special treatment, and uses a historical window to estimate returns and accounting ratios. Stocks are sorted by market capitalization and book-to-market value to construct size and value factor return series, alongside a benchmark market return adjusted for a stated risk-free rate.

For each stock, the strategy fits a linear regression of its returns on the three factor series, then ranks stocks by the estimated coefficients and selects a fixed number for a portfolio. It rebalances periodically, selling names that leave the selection and allocating available cash among new additions. The supplied code is an implementation sketch, not reported evidence: it gives no backtest results, transaction cost analysis, or robustness checks. Its reliance on historical index membership and fundamentals also makes data timing and survivorship bias important concerns; the ranking uses regression coefficients rather than an explicitly estimated intercept.

Key ideas

• The strategy builds market, size, and book-to-market return factors from A-share data.
• It filters the benchmark constituent universe for tradability and special-treatment status.
• A linear regression relates each stock's returns to the three factor series.
• Stocks are ranked by estimated regression coefficients and periodically rebalanced.
• The document gives code but no performance evidence or analysis of trading costs and data biases.

Tags

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