Google searches could predict whether the stock market is headed towards a bear or bull season, according to a new academic study published by Scientific Reports.
Based on the study entitled, “Quantifying Trading Behavior in Financial Markets Using Google Trends,” which was written by Tobias Preis, Helen Susannah Moat and H. Eugene Stanley, an increase in volume of search clicks for financial terms in the Google Inc (NASDAQ:GOOG) search engine will follow a drop in the stock market. On the other hand, when queries for financial terms decline, the stock market climbs.
The researchers added that Google Inc (NASDAQ:GOOG) trends data was also able to forecast certain future trends aside from the rise and fall of the stock market. They cited a similar study from Choi and Varian that Google Trends can be associated with current values of different economic indicators such as automobile sales, unemployment claims, or consumer confidence.
According to the researchers, “We suggest that within the time period we investigate, Google Trends data did not only reflect the current state of the stock markets but may have also been able to anticipate certain future trends. Our findings are consistent with the intriguing proposal that notable drops in the financial market are preceded by periods of investor concern.”
The researchers emphasized that during periods wherein a notable market decline happened, investors may have searched for more information about the stock market before deciding to buy or sell their stock holdings.
“Our results suggest that, following this logic, during the period 2004 to 2011 Google Trends search query volumes for certain terms could have been used in the construction of profitable trading strategies,” according to the researchers.
In their study, the researchers used a hypothetical investment strategy using search volume data and analyzed the performance of 98 search terms related to the concept of stock markets and terms suggested by Google Inc (NASDAQ:GOOG) Sets Service, a tool that identifies semantically related keywords.
According to them, the empirical results are so far consistent with a two-part hypothesis. First, “Key increases in the price of the [Dow Jones industrial average] were preceded by a decrease in search volume for certain financially related terms.” Second, “Key decreases in the price of the DJIA were preceded by an increase in search volume for certain financially related terms.”
They also cited that their trading strategy can be decomposed into two strategy components:
1.) a decrease in search volume prompts us to buy (or take a long position)
2.) an increase in search volume prompts us to sell (or take a short position)
The researchers also revealed that strategies based on search volume data for users in the United States are more successful for the U.S. market than strategies using global search data because there is a higher volume of internet users/traders in the U.S. markets than the worldwide population of internet users.