The volume of Google searches for finance-related terms may predict moves in markets, according to a scientific research paper. The study, in Nature magazine’s Scientific Reports, was based on publicly available data from the Google Trends service. The data indicates that as the search volume on generic terms such as “debt”, “portfolio” and “stocks” fell, […]
The volume of Google searches for finance-related terms may predict moves in markets, according to a scientific research paper.
The study, in Nature magazine’s Scientific Reports, was based on publicly available data from the Google Trends service.
The data indicates that as the search volume on generic terms such as “debt”, “portfolio” and “stocks” fell, the Dow Jones average tended to go up – and vice versa.
An investment strategy based on these search volume data between 2004 and 2011 would have made a profit of 326%, the paper finds.
It joins an ever-increasing array of “big data” studies in which aggregated data are beginning to give striking insights into behaviour.
Web searches are increasingly integral to our decision-making, and because of its dominance among search engines, Google data have already proven their worth in big-data studies.
“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 Suzy Moat of University College London, co-author of the paper.
Large scale patterns
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, and correlated those with the Dow Jones Industrial Average.
Generally, searches for the most finance-focused terms such as “stocks” and “revenue” went down before rises in that market average, whereas when those terms were searched for more often, the average tended to fall in subsequent weeks.
The researchers have already been approached by executives within the financial industry to try to put their findings to use, and have recently received a grant from the Engineering and Physical Sciences Research Council to develop a “big data” software platform specifically aimed at the emerging business models that will depend on it.
Large data sets are increasingly being used to find patterns in people’s behaviour which we can then use as a predictions for large scale trends that repeat in the future.
Recently, Google’s own researchers found that searches can track the spread of influenza and more recently showed that they “predict the present”with regard to economic indicators.
In 2011, the Bank of England determined that searches for relevant terms could even predict house prices.
