Researchers Use Google to Try and Predict Market Crashes

Researchers from Warwick Business School and Boston University have developed a method to automatically identify topics that people search for on Google before subsequent stock market falls.

The method shows that increases in searches for business and politics preceded falls in the stock market. Search engines such as Google record everything we search for.

"Records of these search queries allow us to learn about how people gather information online before making decisions in the real world," said Chester Curme, a research fellow at Warwick Business School.

In order to enable algorithms to automatically identify patterns in search activity that might be related to subsequent real world behaviour, the team quantified the meaning of every word on Wikipedia.

This allowed the researchers to categorise words into topics, so that a "business" topic may contain words such as "business", "management" and "bank".

The team used Google Trends to see how often each week these words were searched for by Internet users in the US between 2004 and 2012.

"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," said Suzy Moat, an assistant professor of Behavioural Science at Warwick Business School.

According to Moat, the results are in-line with the hypothesis that increase in searches relating to both politics and business could be a sign of concern about the state of the economy.

"This may lead to decreased confidence in the value of stocks, resulting in transactions at lower prices," he noted.

The study was published in the Proceedings of the National Academy of Sciences.