Tobias Preis asks: can Google predict the stock market?
25 April 2013
An analysis of changes in Google query volume for search terms related to finance reveals patterns that could be interpreted as early-warning signs of stock market moves.
Tobias Preis, of Warwick Business School, Helen Susannah Moat, of University College London, and H. Eugene Stanley, of Boston University analysed changes in the frequency of 98 terms, such as ‘revenue’, ‘unemployment’, ‘credit’ and ‘nasdaq’, in Google searches from 2004 to 2011.
Preis, Moat and Stanley found that using these changes in search volume as the basis of a trading strategy investing in the Dow Jones Industrial Average Index could have led to substantial profit.
In their paper entitled Quantifying Trading Behavior in Financial Markets published in Nature Publishing Group’s Scientific Reports, the team of academics demonstrate that trading on the basis of the number of queries on Google using the keyword ‘debt’ could have brought in returns of up to 326 per cent.
Dr Preis, Associate Professor of Behavioural Science at Warwick Business School, said: “We found that changes in the volume of certain Google search terms could be used as early warning signs of subsequent stock market movement.”
The research supports the idea that drops in the financial market may be preceded by periods of investor concern. Investors may search for more information about the market before they are prepared to sell at lower prices. Conversely, the researchers found that drops in interest in financial topics could be used as a signal for subsequent stock market rises.
“Analysis of Google Trends data may offer a new perspective on the decision making processes of market participants during periods of large market movements”, said Dr Moat, based at University College London.
“It’s exciting to see that online search data may give us new insight into how humans gather information before making decisions - a process which was previously very difficult to measure.”
Dr Preis added: “We are generating gigantic amounts of data through our everyday interactions with technology. This is opening up fascinating new possibilities for a new interdisciplinary ‘computational social science’.”
The study was developed as part of the IARPA Open Source Indicators program which aims to develop methods for continuous, automated analysis of publicly available data in order to anticipate significant societal events.
“This work illustrates the insight that publicly available data can provide to identify early warning signals of emerging events in the world,” said Jason Matheny, programme manager of the Open Source Indicators programme at IARPA.
Find out more
To read the paper Quantifying Trading Behavior in Financial Markets click here.
Read more about Tobias Preis' work in an article that is part of Warwick Business School's new magazine Core.
Study with us
Tobias is involved with a new Big Data Analytics module which will be available for 2013 entry to our: