When and where next: individual mobility prediction

The ability to predict when an individual mobile user will leave his current location and where we will move next enables a myriad of qualitatively different Location-Based Services (LBSes) and applications. To this extent, the present paper proposes a statistical method that explicitly performs these related temporal and spatial prediction tasks in three continuous, sequential phases. In the first phase, the method continuously extracts grid-based staytime statistics from the GPS coordinate stream of the location-aware mobile device of the user. In the second phase, from the grid-based staytime statistics, the method periodically extracts and manages regions that the user frequently visits. Finally, in the third phase, from the stream of region-visits, the method continuously estimates parameters for an inhomogeneous continuous-time Markov model and in a continuous fashion predicts when the user will leave his current region and where he will move next. Empirical evaluations, using a number of long, real world trajectories from the Geo-Life data set, show that the proposed method outperforms a state-of-the-art, rule-based trajectory predictor both in terms of temporal and spatial prediction accuracy.