Manlio De Domenico, Antonio Lima, Mirco Musolesi
Extended version accepted for Publication in Pervasive and Mobile Computing.
Original version in Proceedings of the Nokia Mobile Data Challenge Workshop. Colocated with Pervasive 2012. Newcastle, United Kingdom. June 2012.
Previous studies have shown that human movement is predictable to a certain extent at different geographic scales. Existing prediction techniques exploit only the past history of the person taken into consideration as input of the predictors. In this paper, we show that by means of multivariate nonlinear time series prediction techniques it is possible to increase the accuracy of movement forecasting by considering movements of friends or people with correlated mobility patterns (i.e., characterised by high mutual information) as input of the predictor. Finally, we evaluate the proposed techniques on the Nokia Mobile Data Challenge and Cabspotting datasets.