Predicting complex user behavior from CDR based social networks

Abstract

Call Detail Record (CDR) datasets provide enough information about personal interactions of cell phone service customers to enable building detailed social networks. We take one such dataset and create a realistic social network to predict which customer will default on payments for the phone services, a complex behavior combining social, economic, and legal considerations. After extracting a large feature set from this network, we find that each feature poorly correlates with the default status. Hence, we develop a sophisticated model to enable reliable predictions. Our main contribution is a methodology for building complex behavior models from very large sets of diverse features and using different methods to choose those features that perform best for the final model. This approach enables us to identify the most efficient features for our problem which, unexpectedly, are based on the number of unique users with whom the given user communicates around the Christmas and New Year's Eve holidays. In general, features based on the number of close ties maintained by a user perform better than others. Our resulting models significantly outperform the methods * Corresponding author currently published in the literature. The paper contributes also a systematic analysis of properties of the network derived from CDR.

The geography of connectivity: a review of mobile positioning data for economic geography

“…This is for example prevalent in tourism studies (see Shoval and Ahas 2016). Other studies analyse activity patterns of humans with the aim to deduce home-work patterns (Ahas et al 2010), fit algorithms that predict movement patterns (Dashdorj et al 2018;Doyle et al 2019;Hoteit et al 2014), or aim to increase the accuracy of the sensing data (Chen et al 2018;Rodriguez-Carrion et al 2018;Zhou and Huang 2016). Secondly, individual data is used to infer social networks from the sensing data (Peng et al 2017a, b).…”

“…Secondly, individual data is used to infer social networks from the sensing data (Peng et al 2017a, b). Here phones are treated as nodes in a network and whilst some have a spatial perspective on the social networks (e.g., Doyle et al 2019;Onnela et al 2011;Phithakkitnukoon and Smoreda 2016;Puura et al 2018), it is not uncommon that these studies leave out spatial patterns in their analysis (e.g., Peng et al 2017a, b;Werayawarangura et al 2016). Thirdly, some studies combine sensing data with other datasets such as physical proximity to others or phone surveys with individuals in the dataset (Eagle et al 2008).…”

Untitled

“…Отдельную группу составляют исследования, в которых с помощью цифровых следов осуществляется прогноз непосредственно поведения (например, оплата кредитов и сотовой связи, совершение преступлений и др.) (Doyle et al, 2019;Drouin et al, 2018;San Pedro et al, 2015). В рамках данной статьи мы не станем подробно рассматривать эту проблематику, сосредоточившись на работах, в которых прогнозируются более обобщенные психологические образования (личностные черты, ценности и т.п.).…”

“…Как показывают исследования, такой ориентированный на поведение подход демонстрирует неплохие результаты на практике, что создает основу для его активного развития в ближайшем будущем. Так, с опорой на характеристики, связанные с использованием сотовой связи, удается весьма успешно прогнозировать финансовую дисциплину при оплате за телефон и пользование кредитом (Doyle et al, 2019;San Pedro et al, 2015). В ряде случаев ориентированный на поведение подход дает даже более точный прогноз поведения, чем личностно-ориентированный (Wilson, 2019).…”

A Hive-Based Retrieval Optimization Scheme for Long-Term Storage of Massive Call Detail Records

“…The authors of [23] studied evaluating the potential of call detail record data in the context of route choice behavior modeling that infers the user's chosen routes or subsets of their likely routes from partial CDR trajectories and data fusion with external sources. Reference [24] studied how to predict complex user behavior combining social, economic, and legal considerations from CDRs by developing a sophisticated model. Researchers in [25] studied degree characteristics and structural properties in large-scale social networks by analyzing tera-scale CDRs that are useful for managing and planning communication networks.…”