Human Mobility Prediction

Predicting Human Mobility Using Mobile Phone Data


Overview

Is Human Mobility Predictable?

The study of the interdependence of human movement and social ties of individuals is one of the most interesting research areas in computational social science. Previous studies have shown that human movement is predictable to a certain extent at different geographic scales.

One of the open problems is how to improve the prediction exploiting additional available information. In particular, one of the key questions is how to characterise and exploit the correlation between movements of friends and acquaintances to increase the accuracy of the forecasting algorithms.

Nokia Mobile Data Challenge

Our dataset that has been provided for the Nokia Mobility Data Challenge is composed of information related to 39 users, including the following: GPS traces, telephone numbers, call and SMS history, Bluetooth and WLAN history.

We use GPS traces to analyse the movement of the users.

People Involved

From University of Birmingham:

From INSA Lyon:

  • Paul Mougel (Visiting Student)

Publications

Our paper was the winning entry of the Open Challenge of the Nokia Mobile Data Challenge 2012:

  • M. De Domenico, A. Lima, M. Musolesi. Interdependence and Predictability of Human Mobility and Social Interactions. Proceedings of the Nokia Mobile Data Challenge Workshop. Colocated with Pervasive 2012. Newcastle, United Kingdom. June 2012.
    [PDF]
  • M. De Domenico, A. Lima and M. Musolesi. Interdependence and Predictability of Human Mobility and Social Interactions. Journal version submitted for publication. arXiv:1210.2376.

Gallery

Press Coverage

Funding

This work was supported through the EPSRC Grant The Uncertainty of Identity: Linking Spatiotemporal Information Between Virtual and Real Worlds” (EP/J005266/1).

Contact

Please contact Mirco Musolesi sending an email to m.musolesi [AT] cs.bham.ac.uk