Predicting Financial Markets with Google Trends and Not so Random Keywords

9 Pages Posted: 15 Aug 2013

See all articles by Damien Challet

Damien Challet

CentraleSupélec

Ahmed Bel Hadj Ayed

BNP Paribas; Ecole Centrale Paris - Laboratory of Mathematics Applied to Systems

Date Written: August 14, 2013

Abstract

We check the claims that data from Google Trends contain enough data to predict future financial index returns. We first discuss the many subtle (and less subtle) biases that may affect the back-test of a trading strategy, particularly when based on such data. Expectedly, the choice of keywords is crucial: by using an industry-grade back-testing system, we verify that random finance-related keywords do not to contain more exploitable predictive information than random keywords related to illnesses, classic cars and arcade games. We however show that other keywords applied on suitable assets yield robustly profitable strategies, thereby confirming the intuition of Preis et al. (2013)

Suggested Citation

Challet, Damien and Bel Hadj Ayed, Ahmed and Bel Hadj Ayed, Ahmed, Predicting Financial Markets with Google Trends and Not so Random Keywords (August 14, 2013). Available at SSRN: https://ssrn.com/abstract=2310621 or http://dx.doi.org/10.2139/ssrn.2310621

Damien Challet (Contact Author)

CentraleSupélec ( email )

Labo MICS
3, rue Joliot-Curie
Gif-sur-Yvette, 91192
France

Ahmed Bel Hadj Ayed

BNP Paribas ( email )

Paris
France

Ecole Centrale Paris - Laboratory of Mathematics Applied to Systems ( email )

Grande Voie des Vignes
Châtenay-Malabry, 92290
France

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
1,115
Abstract Views
6,670
Rank
35,942
PlumX Metrics