Selecting Complementary Factors for a China Equity Model

Summary

This report outlines a first step in building a multifactor model: choosing which factors to combine. It proposes screening combinations using three criteria: how strongly a factor differs from benchmark exposure, how correlated the factors are with each other, and how well each factor selects stocks. Including benchmark factor exposure in the screening process is intended to narrow the search.

The reported comparison covers market capitalization, share capital, turnover, ROE, PE, EPS, net profit growth, and trading volume across three stock indices. Market capitalization and share capital show the largest exposure deviations, while net profit growth shows the smallest. The report identifies several pairs with low correlation and says most factors have similar stock-selection ability, with turnover stronger and net profit growth weaker. It ultimately favors share capital paired with turnover. The supplied text is a summary of a report whose underlying analysis is not included, so it gives no detailed methodology, sample period, or performance evidence with which to assess the selection.

Key ideas

• The factor-combination screen evaluates benchmark exposure, inter-factor correlation, and stock-selection ability.
• Including benchmark factor exposure is presented as a way to reduce the factor search space.
• Market capitalization and share capital have the greatest reported deviations from benchmark exposure.
• The report recommends combining share capital with turnover, based on its stated selection criteria.

Tags

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