The Effect of Weather on User-Generated Big Geo Data in Mobile Phone Networks

User-generated data in mobile networks are normally used as proxies for human activity and mobility, and it can be used in an extensive variety of research problems including mobility, city planning, tourism, event detection, urban well-being and many others. In not so many studies, the relationship between environmental variables and mobile usage data has been explored. This work tests this possible relationship in the city of Milan, as one first approach towards a predictive model for weather conditions/environmental stress from mobile usage data. Used data corresponded to two months (November and December 2013) of Call Detail Records (CDRs) of sent and received SMS, incoming and outgoing calls, and internet traffic; as well as the precipitation data from the meteorological network. According to the KruskalWallis test results, we can conclude that for a confidence interval (95%) the null hypothesis of equality of medians can be rejected: there is a significant relationship between telecommunications data and precipitation intensity levels.