Online Search Data Could Predict Future Market Crashes: Study


Sudden changes in the volume of Google searches for finance-related terms could be an “early warning sign” of imminent stock market movements, showed a research study published on Thursday, in the latest attempt to correlate online behavioural patterns to the behaviour of financial market participants and trends.

The study, entitled Quantifying Trading Behavior in Financial Markets Using Google Trends, found that spikes in Google searches for financial terms often preceded market drops, while a decline in searches pointed to stocks climbing.

The researchers, from Warwick Business School, University College London, and Boston University, also claimed that they then a 326 percent return based on hypothetical investments, derived from a short-term trading strategy constructed around searches for “debt”.

'Our results suggest that … search query volumes for certain terms could have been used in the construction of profitable trading strategies,'' the research paper wrote.

"These results further illustrate the exciting possibilities offered by new big data sets to advance our understanding of complex collective behaviour in our society," they added.

The team started with a set of 98 search terms and tracked how search volumes on those terms varied over a period between 2004 and 2011, correlating those results with the Dow Jones Industrial Average.

"We were intrigued by the idea that stock market data serves as a really large record of all the actions people take in the stock market, but don't necessarily tell us much about how people decided to take those actions," said co-author Suzy Moat of University College London in an interview with the BBC. "We wondered whether by looking at Google, we could get some insight into some early information-gathering stages of how people make decisions.”

“Our findings are consistent with the intriguing proposal that notable drops in the financial market are preceded by periods of investor concern…In such periods, investors may search for more information about the market, before eventually deciding to buy or sell.

“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,” the paper added.

Related: Bank-ing on Google For Economic Insight

Related: Online Privacy: The Relentless Pursuit For Your Personal Data

Related: Twitter Hoax Briefly Wipes $200 Billion Off US Stock Markets

According to the Financial Times, the paper was funded by a U.S. government programme set up to study the predictive power of many different types of data. Tobias Preis, a associate professor of behavioural science and finance at Warwick Business School, said that his group was already in discussions with several investment groups about practical uses for their research.

“All these new data resources from online activities, which are an essential part of our everyday life these days - we are tweeting on Twitter, we are using Wikipedia, we are using search engines like Google and upload photos to Flickr and share information on Facebook - all of this leaves indicators of behaviour," said Preis to AFP.

"From a scientific point of view, our interest is to link this to behaviour in the real world... it's extremely exciting."