Forecasting stock market movements using Google Trend searches

Melody Y. Huang (), Randall R. Rojas () and Patrick D. Convery ()
Additional contact information
Melody Y. Huang: University of California, Los Angeles
Randall R. Rojas: University of California, Los Angeles
Patrick D. Convery: University of California, Los Angeles

Empirical Economics, 2020, vol. 59, issue 6, No 9, 2839 pages

Abstract: Abstract In the following paper, we seek to evaluate the predictive capabilities of internet search data. While past studies have proposed using Google Trends as an effective proxy for investor attention, we re-evaluate this idea in the context of a Granger causal framework. We apply the Kaplan–Meier estimator to quantify the level of persistence in lagged correlations between the search volume series and the directional movements in the S&P 500. We find that the directional movement of the S&P 500 from changes in the search volume series is dependent on the specific term being searched for, and by extension, the sentiment of the term itself. We hypothesize that while Google Trends is a valid measure of investor attention, the signals derived from changes in search volume is conditional upon the sentiment inherent to the search terms. Using the terms that are persistently found to be Granger causal with the index, we propose several generalized linear models for forecasting the probability of positive or negative directional movements, and propose a trade strategy from the generated forecasts, resulting in a 40% outperformance of a traditional buy-and-hold strategy in our testing period.

Keywords: Investor attention; Stock market; Forecasting; Google Trends (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (16)

Downloads: (external link)
http://link.springer.com/10.1007/s00181-019-01725-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:empeco:v:59:y:2020:i:6:d:10.1007_s00181-019-01725-1

Ordering information: This journal article can be ordered from
http://www.springer. ... rics/journal/181/PS2

DOI: 10.1007/s00181-019-01725-1

Access Statistics for this article

Empirical Economics is currently edited by Robert M. Kunst, Arthur H.O. van Soest, Bertrand Candelon, Subal C. Kumbhakar and Joakim Westerlund

More articles in Empirical Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().