Report from C.D. Howe Institute says electronic data provides real-time snapshot of regional conditions
TORONTO—A study out of a Canadian think-tank claims it may be possible to predict future economic downturns by mining search engine trends.
According to the report from the C.D. Howe Institute, predicting recessions in real-time could become a reality simply by mining troves of electronic data to monitor economic trends, including consumer spending habits.
“New sources of electronically recorded data are both timely and reflect the real-time intentions of millions (or billions) of agents,” Greg Tkacz, author of Predicting Recessions in Real-Time: Mining Google Trends and Electronic Payments Data for Clues, said in a statement.
“Most policymakers and economists failed to predict the last recession because of the lag in traditional economic data. I look at the search data in Google Trends, as well as electronic payments data, to see if the recession signals were there in real time.”
With a number of official economic indicators released with a time lag—think Statistics Canada reports—new data compiled through search engines are being compiled faster than analysts can review them, according to Tkacz.
And with the emergence of Google as the dominant search engine, he said its search-term usage can provide a snapshot of current interests like economics, politics and health.
In principle, if many people are entering the same economic search terms, it could provide a clue about changing conditions, such as the onset of a recession.
Tkacz even goes so far as to claim that the use of Google search terms “recession” and “jobs” could have predicted the last recession up to three months in advance of its onset.
However, he cautions that since Google query data are only available from 2004, the time span studied is very short in the context of business cycles.
Consequently, the study should be viewed as illustrative of the potential uses of electronic data.