2015/12/25 by Mehwish Nasim, Aimal Rextin, Nasim, Mehwish +5
Decision Sciences · Physics and Astronomy · Social Sciences · #Complex Network Analysis Techniques #FOS: Computer and information sciences #Human Mobility and Location-Based Analysis #Opinion Dynamics and Social Influence #Personal Information Management and User Behavior #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.1512.08061
openalex publication_date 2015/12/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper we predict outgoing mobile phone calls using a machine learning\napproach. We analyze to which extent the activity of mobile phone users is\npredictable. The premise is that mobile phone users exhibit temporal regularity\nin their interactions with majority of their contacts. In the sociological\ncontext, most social interactions have fairly reliable temporal regularity. If\nwe quantify the extension of this behavior to interactions on mobile phones we\nexpect that caller-callee interaction is not merely a result of randomness,\nrather it exhibits a temporal pattern. To this end, we tested our approach on\nan anonymized mobile phone usage dataset collected specifically for analyzing\ntemporal patterns in mobile phone communication. The data consists of 783 users\nand more than 12,000 caller-callee pairs. The results show that users' historic\ncalling patterns can predict future calls with reasonable accuracy.\n