When and Where: Predicting Human Movements Based on Social Spatial-Temporal Events

Predicting both the time and the location of human move-ments is valuable but challenging for a variety of applica-tions. To address this problem, we propose an approach considering both the periodicity and the sociality of hu-man movements. We first define a new concept, Social Spatial-Temporal Event (SSTE), to represent social interac-tions among people. For the time prediction, we characterise the temporal dynamics of SSTEs with an ARMA (AutoRe-gressive Moving Average) model. To dynamically capture the SSTE kinetics, we propose a Kalman Filter based learn-ing algorithm to learn and incrementally update the ARMA model as a new observation becomes available. For the loca-tion prediction, we propose a ranking model where the peri-odicity and the sociality of human movements are simultane-ously taken into consideration for improving the prediction accuracy. Extensive experiments conducted on real data sets validate our proposed approach.