Skip to content
All library documents

Using Search Behavior to Study Stock Market Moves

Article BigQuant
Read the original

Summary

This research summary describes a method for studying whether public information-seeking behavior can reveal topics associated with subsequent stock market moves. The cited 2014 study analyzes historical data from 2004 through 2012, drawing on Google and Wikipedia records and judgments gathered through Amazon Mechanical Turk. Its focus is the meaning of search topics, rather than search volume alone, as a possible source of information about changing public attention.

The summary reports an association between searches related to politics or business and later stock market movements. In particular, increases in searches about these topics often preceded market declines. This suggests that semantic analysis of search activity could serve as a large-scale information stream for studying public concern before real-world events or market changes. The document offers only a brief account of the study and gives no details on model construction, predictive accuracy, trading returns, or robustness. The reported relationship is associative, so it does not establish that search behavior causes declines or would reliably support a profitable trading strategy.

Key ideas

  • The study examines search topics as a measure of public attention before stock market moves.
  • It combines Google and Wikipedia records with human topic judgments.
  • Political and business search activity was associated with subsequent market direction.
  • Rising searches on these topics often preceded stock market declines in the analyzed period.
  • The summary does not report predictive accuracy or evidence of profitable trading returns.

Tags

EquitiesSentimentStatisticsMachine learning

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