Exploring the predictive power of Google searches over the US stock market

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Finance from the NOVA – School of Business and Economics

This paper takes search intensity for stock tickers in Google (SVI) as a direct measure of retail investor attention and assesses whether it holds predictive power over short-term market outcomes. In a sample of the most representative US stocks, during the period 2005 – 2008, I provide evidence that (1) surges of investor attention forecast higher stock liquidity and volatility; (2) depending severely on what is considered an abnormal level of SVI, retail investor attention can also be priced; and (3) SVI does not relate to firm-specific features, such as size and value. Furthermore, I extend the investigation to the aggregate market level, finding that investor attention to the market index predicts greater market liquidity, volatility and return.