Google Trends Could Predict Stock Market Moves, Study Shows
A paper found that trading based on search query volumes for the term “debt” could yield large returns.
This week’s fleeting stock market crash prompted by a false report from the Associated Press’s hacked Twitter account has focused attention again on the growing Wall Street practice of mining news and social data to make trades.
A study in Nature Scientific Reports today illustrates just how lucrative the right combination of algorithms could potentially be.
Using Google Trends, researchers analyzed the Google search query volumes from 2004 to 2011 for a set of 98 mostly finance-related search terms, looked at how stock prices changed over that same time, and tried to see if they could retroactively tease out search patterns that showed “early warning signs” of market moves. They also tested trading strategies that would act on these signs.
This story is only available to subscribers.
Don’t settle for half the story.
Get paywall-free access to technology news for the here and now.
Subscribe now
Already a subscriber?
Sign in
You’ve read all your free stories.
MIT Technology Review provides an
intelligent and independent filter for the
flood of information about technology.
Subscribe now
Already a subscriber?
Sign in
The volume of the search term “debt” turned out to be the word that showed the most promise, and one trading plan based on changes in searches for this term would have yielded a return of 326 percent over the period analyzed, the authors found. For comparison, a “buy and hold” investment in the Dow Jones Industrial Average yielded 16 percent return.
Of course, it’s easier to look at historic data and make hypothetical returns than to predict how well Google Trends-based trading will work over the next decade. However, as this study shows, it’s clear that the stock trading strategies based on the mining of real-time, public data sets will continue to become more sophisticated than what has played out this week.
