Mining Private Information from Public Data: The Transantiago Case

Transantiago, the smartcard-based public transportation system in Santiago, Chile, includes both a subway system and buses. An online information system lets card holders find detailed trip information, including start time and location, as well as frequency and type of transportation used, by simply providing its card ID. This article studies the privacy implications of the availability of the Transantiago online information system. The authors explore how much of a card holder´s information and behavior could be extracted from something as simple as their card ID. They concluded that, given that the corresponding card IDs are known, they can use simple statistical techniques to correctly predict the nearest public transport station to the homes of more than half of the users. This article is part of a special issue on pervasive analytics and citizen science.