Is a sentiment-based trading strategy profitable?

Karam Kim, Doojin Ryu*, Jinyoung Yu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

16 Citations (Scopus)

Abstract

We examine whether sentiment indices predict individual firms’ stock returns and evaluate the performances of sentiment-based trading strategies in the Korean equity market. We find that the sentiment indices (constructed using the principal component analysis (PCA) and overnight stock returns) positively predict stock price movements, whereas news sentiment does not significantly determine future stock returns. A comparison of portfolio performances among sentiment indices reveals that the long-short equity strategy based on PCA sentiment changes yields the highest return–a result that is not explained by well-known risk factors. Moreover, investors may earn even greater returns by employing multiple sentiment measures when constructing portfolios, suggesting that each measure reflects different aspects of investor sentiment.

Original languageEnglish
Pages (from-to)94-107
Number of pages14
JournalInvestment Analysts Journal
Volume51
Issue number2
DOIs
Publication statusPublished - 2022
Externally publishedYes

Keywords

  • cross-sectional stock returns
  • investor sentiment
  • portfolio management
  • return predictability
  • trading strategy

Fingerprint

Dive into the research topics of 'Is a sentiment-based trading strategy profitable?'. Together they form a unique fingerprint.

Cite this