Can We Predict the Financial Markets Based on Google's Search Queries?

24 Pages Posted: 17 Nov 2014 Last revised: 14 Sep 2016

See all articles by Marcelo Perlin

Marcelo Perlin

Escola de Administração - UFRGS

João Caldeira

Universidade Federal do Rio Grande do Sul (UFRGS)

André Santos

Universidade Federal de Santa Catarina (UFSC) - Department of Economics

Martin Pontuschka

Universidade Federal do Rio Grande do Sul (UFRGS)

Date Written: November 16, 2014

Abstract

In this paper we look into the interaction of Google's search queries and several aspects of international equity markets. Using a novel methodology for selecting words and a VAR modeling approach, we study whether the search queries of finance related words can have an impact on market uncertainty, log returns and traded volume of four different english speaking countries. Our overall main results are positive, we find several words that have a robust impact over the explained variables. Particularly, the most robust result we find is that an increase of the search queries including the word "stock" predicts an increase of volatility and decrease of index prices in the next week. With the support of this finding, we investigate the performance of a market timing strategy based on the search frequency of this word and compare it against random words from the Word-Net database and a naive buy and hold strategy. The results of this empirical application are positive, indicating the potential of this new set of data in predicting financial markets.

Keywords: market microstructure, investor attention, google trends, internet search volume

JEL Classification: G10, G11, G15

Suggested Citation

Perlin, Marcelo and Caldeira, João and Santos, André and Pontuschka, Martin, Can We Predict the Financial Markets Based on Google's Search Queries? (November 16, 2014). Available at SSRN: https://ssrn.com/abstract=2525909 or http://dx.doi.org/10.2139/ssrn.2525909

Marcelo Perlin (Contact Author)

Escola de Administração - UFRGS ( email )

Porto-Alegre RS
Brazil

HOME PAGE: http://sites.google.com/site/marceloperlin/

João Caldeira

Universidade Federal do Rio Grande do Sul (UFRGS) ( email )

Av. Carlos Gomes 1111
Porto Alegre, Rio Grande do Sul 90480-004
Brazil

André Santos

Universidade Federal de Santa Catarina (UFSC) - Department of Economics ( email )

PO Box 476
Florianopolis, SC 88010-970
Brazil

Martin Pontuschka

Universidade Federal do Rio Grande do Sul (UFRGS) ( email )

Av. Carlos Gomes 1111
Porto Alegre, Rio Grande do Sul 90480-004
Brazil

Register to save articles to
your library

Register

Paper statistics

Downloads
412
rank
67,045
Abstract Views
1,571
PlumX Metrics