Google Trends Could Predict Stock Market Moves, Study Shows
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.
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.
Keep Reading
Most Popular
Large language models can do jaw-dropping things. But nobody knows exactly why.
And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.
How scientists traced a mysterious covid case back to six toilets
When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.
The problem with plug-in hybrids? Their drivers.
Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.
Google DeepMind’s new generative model makes Super Mario–like games from scratch
Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.
Stay connected
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.