Cell Phone Usage Can Predict Unemployment Rates, MIT Researchers Find

When people lose jobs, data shows that their cell phone use declines, which can be correlated with other unemployment indicators, say the researchers.

job search

Unemployment rates are typically tracked through weekly jobless benefits claims and other indicators, but researchers at the Massachusetts Institute of Technology say they have found that cell phone usage can also be used as a method to refine and confirm the latest unemployment figures.

A study co-authored by several researchers at the school found that the cell phone data "can provide rapid insight into employment levels, precisely because people's communications patterns change when they are not working," according to a June 15 announcement from MIT.

Without a commute or a place to work, the researchers hypothesized, most people will make a higher portion of their calls from home, while also potentially making fewer mobile calls, which would show up in their mobile phone usage patterns.

The phone data in the study was analyzed following the 2006 closure of an automotive plant in Europe that left about 1,100 workers unemployed in a town of roughly 15,000 people. To conduct the study, the researchers built an algorithm that analyzed anonymous phone-use patterns and then assigned a probability that someone has become unemployed, according to MIT. They then compared that data to eight quarters of unemployment data in 52 provinces of a European country to determine if their theory held up.

By scouring the mobile phone usage data of the former auto plant workers after the facility shut down, the researchers found that the laid-off workers made 51 percent fewer mobile calls compared with working residents, according to the study. In addition, mobile calls made by a newly unemployed worker to someone in the town where they had worked dropped by 5 percentage points, while the number of individual cell phone towers needed to transmit the calls of unemployed workers dropped by around 20 percent, the study concluded.

"Individuals who we believe to have been laid off display fewer phone calls incoming, contact fewer people each month, and the people they are contacting are different," Jameson Toole, a Ph.D. candidate in MIT's engineering systems division and a co-author of the research paper, said in a statement. "People's social behavior diminishes, and that might be one of the ways layoffs have these negative consequences. It hurts the networks that might help people find the next job."

The data and conclusions were recently published in the Journal of the Royal Society Interface, according to MIT. None of the researchers who participated in the study was available immediately to talk in more depth with eWEEK about their work.

While the cell phone data analysis method won't replace the existing methods that are used to calculate unemployment rates, it could be used as a way to further refine and correlate those methods, perhaps allowing the figures to be calculated two to eight weeks faster than it is done today, according to the researchers.

"Using mobile phone data to project economic change would allow almost real-time tracking of the economy, and at very fine spatial granularities … both of which are impossible given current methods of collecting economic statistics," David Lazer, a professor at Northeastern University and a co-author of the paper, said in a statement.

Other co-authors of the paper and research are Marta Gonzalez, an associate professor of civil and environmental engineering at MIT; Yu-Ru Lin of the University of Pittsburgh; Erich Muehlegger of the University of California at Davis; and Daniel Shoag of the Harvard Kennedy School.