Hierarchical approach for identifying social groups from mobile phone call detail records

Abstract

With the increasing use of mobile devices, now it is possible to collect different data about the day-to-day activities of personal life of the user. Call Detail Record (CDR) is the available mobile phone usage dataset at large-scale, as they are already constantly collected by the mobile operator mostly for billing purpose. By examining this data it is possible to analyze the activities of the people in urban areas and discover the human behavioral patterns of their daily life. These datasets can be used for many applications that vary from urban and transportation planning to predictive analytics of human behavior. In our research work, we have proposed a hierarchical analytical model for finding facts from CDR dataset for progressive exploration of facts on the day-to-day social activities of urban users in multiple layers. In our model, only the raw CDR data are used as the input in the initial layer and the outputs from each consecutive layer is used as new input combined with the original CDR data in the next layers to learn more detailed and deeper facts on social interaction, work and travel activity, friends, family and working relationship and predicting social groups based on these facts. Our proposed model starts with an aggregated overview of the activities of the users in their social life and allows us to gradually focus on smaller groups, using multiple layers of abstraction by applying clustering techniques and prediction classifiers. The uniqueness of our model is that the output in each layer is dependent on the results of the previous layers, thus, allow us to explore fact on social relationships and groups which can not be predicted in a single layered approach. This model utilized the CDR dataset of one month collected from the Dhaka city, which is one of the most densely populated cities of the world. So, our main focus of this research work is to explore the applications of CDR data containing spatio-temporal traces of the mobile phone users for progressive predicting of facts and features of social groups and relationships in a busy city.