Building a Stock Sentiment Factor from Active and Passive Buying

Summary

This summary of a Changjiang Securities study explains a stock-selection factor based on the balance between active and passive buying. Active buying occurs when an investor’s order trades against displayed sell orders; passive buying places a limit order and waits for a later sell order to fill it. The study uses the ratio of these behaviors to construct a buying sentiment factor, described as BM. It also argues that higher-frequency data can provide finer information about price and volume changes and make trading behavior easier to distinguish.

The supplied summary reports an average RankIC of 0.0724 and annualized excess returns over the CSI 500 for three BM variants during January 2010 through February 2017: the raw factor, a reversal-neutralized version, and one neutralized for reversal and market value. These are reported backtest results, not proof of future performance. The underlying paper is referenced but not reproduced, so details on data construction, transaction costs, statistical significance, and robustness are unavailable here.

Key ideas

• The factor distinguishes aggressive purchases that trade with sell orders from limit orders that wait for sellers.
• BM is constructed from the relationship between active and passive buying.
• The summary argues that higher-frequency data can improve price and volume detail and reveal trading behavior.
• It reports RankIC and CSI 500 excess-return results for raw and neutralized BM variants over a stated backtest period.
• The summary omits the study’s methodology details, costs, significance tests, and robustness checks.

Tags

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