Informed Trading and Return Predictability in China: Research Based on Ensemble Neural Network

Peiran Li and Lu Yang

Emerging Markets Finance and Trade, 2025, vol. 61, issue 1, 216-240

Abstract: We construct a new informed trading index based on the high-frequency trading data of the Chinese A-share market using the ensemble neural network algorithm. We find that the informed trading index is a strong negative predictor of future aggregate stock market returns, with monthly in-sample and out-of-sample ${R^2}$R2 of 5.45% and 3.53%, respectively, which is far greater than the predictive power of other previously studied informed trading indicators and macroeconomic variables. The asset allocation strategy based on our index can generate large economic gains for the mean-variance investors, with annualized CER (certain equivalent return) gains ranging from 10.91% to 7.80% as the investor’s risk appetite varies. The driving force of the predictive power appears to stem from the liquidity provider role that informed traders play, which decreases the market’s illiquidity risk and lowers the risk premium of equity. Our analysis complements the returns predictability study by adding a new predictor on the one hand and informs market timing strategies on the other.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/1540496X.2024.2379471 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:mes:emfitr:v:61:y:2025:i:1:p:216-240

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/MREE20

DOI: 10.1080/1540496X.2024.2379471

Access Statistics for this article

More articles in Emerging Markets Finance and Trade from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().