Google Trends, a tool that looks at patterns of searches on the Internet, is a potential money-spinner for investors as it provides hints of impending stock movements, a study said on Thursday.
Researchers led by Tobias Preis at Warwick Business School in central England analysed data from Google Trends from 2004 to 2011.
They looked at the volume of searches for 98 terms, such as "metals," "stock," "finance," "forex," "house," "unemployment" and "health" as well as non-specific or neutral words, such as "ring," "train," kitchen" and "fun."
They then constructed a virtual portfolio of investment in the Dow Jones Industrial Average (DJIA), with a strategy based on search volumes that occurred on Sundays.
If the search volume that day was high compared with a week earlier, the DJIA investment was systematically sold at the closing price the following day, and then repurchased at the end of the first day of trading in the week after.
Conversely, if the search volume on Sunday was low compared with the previous week, the researchers "bought" the following day.
Using the keyword "debt"—the term that saw the most fluctuation during the study period—the strategy netted a whopping cyber-profit of 326 percent over seven years.
By comparison, a strategy of buy-and-hold—purchasing in 2004 and selling in 2011—would have yielded only 16 percent profit, equal to the rise in the DJIA during this time.
A third strategy, of buying or selling on the basis of movements in the Dow itself, would have netted a gain of 33 percent.
The paper, published in the journal Scientific Reports, suggests that search requests are a potential indicator of intent about investment decisions.
When a mass of people seek information about a particular subject on a Sunday, this is a sign of worry and boosts the likelihood that they will ditch stock when the market opens on the Monday, it argues.
"Notable drops in the financial market are preceded by periods of investor concern," according to the research.
"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."
In a phone interview with AFP, Preis said that the online world was a goldmine of data for behavioural experts.
"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," he said.
"From a scientific point of view, our interest is to link this to behaviour in the real world... it's extremely exciting."
Explore further: Active learning model for computer predictions
More information: Paper: DOI: 10.1038/srep01684