Your phone data can reveal that you’re unemployed
- Gitanjali Gems, Nirav Modi stores down shutters across India, employees wait for dues
- News in Numbers: Nasscom to get first woman head in 30 years
- India ranks 81st in global corruption perception index by Transparency International
- Maharashtra power firm, Korean JV partner at loggerheads over breach of contract
- Google Reply will let users reply without typing a word
People’s communication patterns change when they are unemployed, according to a new study.
A study, co-authored by the Massachusetts Institute of Technology (MIT) researchers, which took data from two European countries, suggests that mobile phone data can indeed provide rapid insight into employment levels.
“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,” said Jameson Toole, a PhD candidate in MIT’s engineering systems division, and co-author of the study, in a 15 June press statement.
The paper, published in the Journal of the Royal Society Interface, builds a model of cellphone usage that lets the researchers correlate cellphone usage patterns with aggregate changes in employment.
The researchers demonstrate the reliability of these techniques by studying data from two European countries. In the first, they showed that it is possible to observe mass layoffs and identify the users affected by them in mobile phone records.
They then tracked the mobility and social interactions of the affected workers and observed that job loss has a systematic dampening effect on their social and mobility behaviour.
In the second country, where macro-level data was available, the researchers showed that changes in mobility and social behaviour can predict unemployment rates ahead of official reports and more accurately than traditional forecasts.
These results demonstrate the promise of using new data to bridge the gap between micro and macroeconomic behaviours and track important economic indicators.
The researchers used a plant closing in Europe as the basis for their study. There are three mobile phone towers close to the town and the plant that was shut down in 2006.
The first tower is in the town itself. The second roughly 3km from the first and is geographically closest to the manufacturing plant, while the third is roughly 6.5km from the first two on a nearby hilltop.
There are no other towns in the region covered by these towers. Because the exact tower through which a call is routed may depend on factors beyond simple geographical proximity (for example, obstructions due to buildings), the researchers considered any call made from these three towers as having originated from the town or the plant. The analysis was done at three levels: individual, community and provincial.
At the community (town) level, researchers examined the behavioural traces of a large-scale layoff event. At the community and individual levels, they analysed record data from a service provider with approximately 15% market share in an undisclosed European country.
The community-level data set spanned a 15-month period between 2006 and 2007.
At the province level, the researchers examined call detail records from a service provider from another European country, with approximately 20% market share and data running for 36 months from 2006 to 2009.
The records in each data set included an anonymous ID for caller and the recipient of the call, the location of the tower through which the call was made and the time the call occurred.
Analysis of the data showed that in the months following the layoffs, the total number of calls made by the laid-off individuals dropped by 51% compared with working residents, and by 41% compared with all phone users.
Even the number of individual cellphone towers needed to transmit the calls of unemployed workers dropped by around 20%.
“Using mobile phone data to project economic change would allow almost realtime tracking of the economy, and at very fine spatial granularities...both of which are impossible given current methods of collecting economic statistics,” said David Lazer, a professor at Northeastern University and co-author of the paper.
The researchers, however, emphasize that they are not proposing the new method as a replacement for time-tested ways of measuring unemployment. Instead, they see it as an additional tool for analysts.
According to Toole, the new study is conceptually similar to the MIT-based “Billion Prices Project”—an academic initiative that uses prices collected from hundreds of online retailers around the world on a daily basis to conduct economic research.
In the same way, said Toole, this research might make a methodological impact on unemployment estimates. The researchers have presented algorithms capable of identifying employment shocks at the individual, community and societal scales from mobile phone data.