Can police departments gain the ability to predict crimes by analyzing mobile data? According to work done in Italy, Spain, and at the Massachusetts Institute of Technology (MIT), mobile data significantly improved the accuracy of crime predictions. Of course, it wouldn’t be the only tool used.
Current systems use crime statistics and local demographics for crime predictions. Unfortunately, these systems aren’t regularly updated and are expensive, making them difficult for practical use. By comparison, mobile phones collect data on gender, age, and real-rime location of the phone itself.
The study’s researchers were able to create an algorithm that can predict crimes by obtaining data from European mobile phone company Telefonica, which owns O2 in the U.K. They also obtained information from the London Borough Profiles Dataset, which shows an area’s political affiliation, transportation, homelessness, housing market, life expectancy, and more. The researchers were able to make maps of predicted crimes in London.
This approach for predicting crimes has implications for letting police departments and city governments know how and where to invest their efforts, as well as how to better react to crimes, according to the paper.
“From a proactive perspective, the ability to predict the safety of a geographical area may provide information on explanatory variables that can be used to identify underlying causes of these crime occurrence areas and hence enable officers to intervene in very narrowly defined geographic areas,” the report reads.