School of Business publications portal
This portal is no longer updated. Aalto University School of Business Master's Theses are now in the Aaltodoc publication archive (Aalto University institutional repository)
School of Business | Department of Finance | Finance | 2012
Thesis number: 13098
Can you google the future? A study on the predictive power of Google Trends on company shares in the UK.
Author: Wuoristo, Leo
Title: Can you google the future? A study on the predictive power of Google Trends on company shares in the UK.
Year: 2012  Language: eng
Department: Department of Finance
Academic subject: Finance
Index terms: rahoitus; financing; osakemarkkinat; stock markets; ennusteet; forecasts; tulevaisuus; future; tiedonhaku; information retrieval; internet; internet; palvelut; service; trendit; economic trends; Iso-Britannia; United Kingdom; sijoittajat; investors
Pages: 62
Full text:
» hse_ethesis_13098.pdf pdf  size:533 KB (545293)
Key terms: internet search; investor attention; google; FTSE; ticker; abnormal returns; retail investor
Abstract:
Abstract Google Trends was released in 2006. The service enables one to see the aggregated search volume for any defined term. After its release it has gradually been incorporated into academic research from various fields, most often as a proxy for global attention. The purpose of this study is to analyze how investor attention for a particular stock ticker, as measured by Internet search frequency, affects its future trade volume and share price in the UK market. The effect is analyzed separately for different time periods, market capitalization sizes and industries. In addition the paper looks at how searches originating globally and from the UK differ in their relation to company shares. The data used in this study come from two different sources. Financial data is gathered via Datastream, including weekly share prices and trade volume. Search volume data is gathered manually from Google Trends for the company’s London Stock Exchange ticker symbol. The final sample consists of 93 firms in the FTSE AllShare index from 2004 to 2011. The results indicate that search volume does have predictive power over company shares. Firstly the study shows that searches for a company ticker have a direct and significant relation to current and future trade volume. Secondly, using a Fama-Macbeth cross-sectional regression it is proven that search volume predicts future abnormal returns at the 1%-significance level. A one-standard-deviation increase in abnormal search volume this week raises abnormal returns next week by 12.5 basis points, while resulting in price reversal in subsequent weeks. Furthermore the study finds that search volume data originating from the UK is not as good at predicting share price movement as global search volume. Keywords Internet search, Investor attention, Google, FTSE, Ticker, Abnormal returns, Retail investor
Electronic publications are subject to copyright. The publications can be read freely and printed for personal use. Use for commercial purposes is forbidden.