User Travelling Pattern Prediction via Indistinct Cellular Data Mining

Abstract

Smart devices, i.e., smartphone, have come into our daily lives, which become obviously inseparable. Although a variety of functions (e.g., gaming, networking, etc.) are provided, making calls remain the major task. This phenomenon implies the possibility of understanding human behaviors, especially the action contexts (e.g., moving preference, regularity, sociability, etc.), can be expected. In addition, precise services become applicable to be provided through mining, analysis, and prediction of such information. In this study, we investigate the travelling pattern, focusing especially on routine (say excluding the events in holidays), of mobile users via real calling histories. A general model, Travelling Pattern Model, was developed, primarily dealing with the contexts of calling and correlated geographical information. This model not only enables high prevision prediction of users but also benefits business models through the detail understanding of user behaviors.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 3 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.