Searching for return: How Google search engine query data can beat the market

Throughout the last years technologic improvements have enabled internet users to analyze and retrieve data regarding Internet searches. In several fields of study this data has been used. Some authors have been using search engine query data to forecast economic variables, to detect influenza areas or to demonstrate that it is possible to capture some patterns in stock markets indexes. In this paper one investment strategy is presented using Google Trends’ weekly query data from major global stock market indexes’ constituents. The results suggest that it is indeed possible to achieve higher Info Sharpe ratios, especially for the major European stock market indexes in comparison to those provided by a buy-and-hold strategy for the period considered.

Predictability of stock market returns: Evidence from Eurozone's banking sectors

This paper analyzes the in-, and out-of sample, predictability of the stock market returns from Eurozone’s banking sectors, arising from bank-specific ratios and macroeconomic variables, using panel estimation techniques. In order to do that, I set an unbalanced panel of 116 banks returns, from April, 1991, to March, 2013, to constitute equal-weighted country-sorted portfolios representative of the Austrian, Belgian, Finish, French, German, Greek, Irish, Italian, Portuguese and Spanish banking sectors. I find that both earnings per share (EPS) and the ratio of total loans to total assets have in-sample predictive power over the portfolios’ monthly returns whereas, regarding the cross-section of annual returns, only EPS retain significant explanatory power. Nevertheless, the sign associated with the impact of EPS is contrarian to the results of past literature. When looking at inter-yearly horizon returns, I document in-sample predictive power arising from the ratios of provisions to net interest income, and non-interest income to net income. Regarding the out-of-sample performance of the proposed models, I find that these would only beat the portfolios’ historical mean on the month following the disclosure of year-end financial statements. Still, the evidence found is not statistically significant. Finally, in a last attempt to find significant evidence of predictability of monthly and annual returns, I use Fama and French 3-Factor and Carhart models to describe the cross-section of returns. Although in-sample the factors can significantly track Eurozone’s banking sectors’ stock market returns, they do not beat the portfolios’ historical mean when forecasting returns.