Google Trends Data and Stock Price Volatility

Open Access
Stitzel, Brandon T
Area of Honors:
Bachelor of Science
Document Type:
Thesis Supervisors:
  • James R. Tybout, Honors Advisor
  • Dr. Russell Paul Chuderewicz, Thesis Supervisor
  • Google
  • Google Trend
  • Stock
  • Volatility
  • Price Volatility
  • Economics
  • Finance
Financial markets are consistently trying to find innovative ways to track investors’ sentiment and expectations. By doing so, they are able to make investments with more certainty of returns. This paper seeks to determine if potential investment returns can be improved with the use of historical Google Trends data and investor’s bounded rationality. To do this, this paper evaluates the link between Google Trends data and the price volatility of individual stocks over a given time period. To evaluate this link, time series regression modeling on the top ten most traded companies since 2008 in the United States is utilized. Google Trends data is then compared with each stock’s price volatility on a monthly basis from January 2008 to June 2018 in addition to the aggregate stock price volatility data of all ten companies. The paper finds that there is a consistent, significant correlation between stock price volatility and Google Web data on a monthly basis among a majority of the stocks when evaluated individually. In aggregate form, the paper finds that the correlation between stock price volatility and Google Web data is statistically significant at the 1% level. The results suggest investors begin searching stocks on Google when important news announcements are expected to be released. They also suggest that investors search stocks after large instances of price volatility. As a result, when any investor sees a spike in Google Web data for a particular stock, they could use this information to open a straddle or strangle position in an attempt to profit off of price volatility with greater accuracy.