Discovering user’s background information from mobile phone data

Abstract

Data collected from mobile phone have potential knowledge to provide background information of a mobile phone user, such as work location, home location, job occupation, income, consumption and even lifestyle etc., which are quite valuable to many location-aware applications. In the existing research, there is relatively few commercial software or application systems to fully meet the requirements of effectively mining these personal behavioral characteristics. In the paper, we propose approaches to analyzing personal activity characteristics and mining behavioral regularity from mobile phone location information, automatically generating some semantic labels by integrating mobile phone log data with map data and web data, and location prediction for personalized advertising services. We use actual mobile phone data to perform the functions for discovering background information and demonstrate effectiveness of our approaches.