Google search terms can be used to predict market crashes

Search data could be used to identify the warning signs of an imminent stock market crash, according to researchers from Warwick Business School and Boston University.

 

In a study called “Quantifying the semantics of search behaviour before stock market moves”, they show that a rise in certain terms put into Google correlates with a subsequent stock market crash. 

 

"Search engines, such as Google, record almost everything we search for," says Chester Curme, research fellow at Warwick Business School and lead author of the study. "Records of these search queries allow us to learn about how people gather information online before making decisions in the real world. So there's potential to use these search data to anticipate what large groups of people may do.”

 

The team quantified the meaning of every single word on Wikipedia, so that algorithms could automatically identify patterns in search activity that might be related to real world behaviour. They grouped words into a wide range of topics, so that the category of “business”, for example, contained words such as "business", "management", and "bank". 

 

They then used Google Trends to find out how regularly each of these words was put into search by users in the US between 2004 and 2012. By applying this search data to a simple trading strategy for the S&P 500, they found that an increase in searches of certain words related to business and politics often preceded a fall in the stock market.

 

"By mining these datasets, we were able to identify a historic link between rises in searches for terms for both business and politics, and a subsequent fall in stock market prices," says Suzy Moat, assistant professor of Behavioural Science at Warwick Business School.

 

“The finding that political terms were of use in our trading strategies, as well as more obvious financial terms, provides evidence that valuable information may be contained in search engine data for keywords with less obvious semantic connections to events of interest. Our method provides a new approach for identifying such keywords."