Link Prediction in Human Mobility Networks

Yang Yang, Nitesh V. Chawla, Prithwish Basu, Bhaskar Prabhala, Thomas La Porta
Publication Date: 
December, 2013

The understanding of how humans move is a long-standing challenge in the natural science. An important questionis, to what degree is human behavior predictable? The abilityto foresee the mobility of humans is crucial from predicting thespread of human to urban planning. Previous research has fo-cused on predicting individual mobility behavior, such as the nextlocation prediction problem. In this paper we study the humanmobility behaviors from the perspective of network science. In thehuman mobility network, there will be a link between two humansif they are physically proximal to each other. We perform bothmicroscopic and macroscopic explorations on the human mobilitypatterns. From the microscopic perspective, our objective is toanswer whether two humans will be in proximity of each other ornot. While from the macroscopic perspective, we are interested in whether we can infer the future topology of the human mobility network. In this paper we explore both problems by using link prediction technology, our methodology is demonstrated to have a greater degree of precision in predicting future mobility topology.