Using location data to recommend social events whilst protecting user privacy

Daniele Quercia - chercheur à l?University of Cambridge
Digital Security

Date: -
Location: Eurecom

Nowadays companies increasingly use location data from mobile phones to offer location-based services such as estimating current road traffic conditions and finding the best nightlife locations in a city. This talk is about a study of the relationship between preferences for social events and geography, the first of its kind in a large metropolitan area. We sampled location estimations of one million mobile phone users in Greater Boston, combined the sample with social events in the same area, and inferred the social events attended by 2,519 residents. Upon this data, we tested a variety of algorithms for recommending social events. We found that the most effective algorithm recommends events that are popular among residents of an area. The least effective, instead, recommends events that are geographically close to the area. This last result has interesting implications for location-based services that emphasize recommending nearby events. We will also touch on the problem of privacy by a new scheme in which mobile phones report, in addition to their actual locations, a very large number of "carefully chosen" fake locations. Upon real mobility data, we find that, in the presence of this scheme, a service provider is still able to accurately estimate the number of people in any geographic location in Zurich and London.