A paper titled "Predicting complex user behavior from CDR based social networks," by Casey Doyle, Zela Herga Stephen Dipple, Boleslaw K. Szymanski, Gyorgy Korniss, Dunja Mladenić was posted on arXiv

A paper titled "Predicting complex user behavior from CDR based social networks," by Casey Doyle, Zela Herga Stephen Dipple, Boleslaw K. Szymanski, Gyorgy Korniss, Dunja Mladenić was posted on arXiv. The paper uses Call Detail Record (CDR) datasets with information about personal interactions to support building and analyzing detailed empirical social networks. The authors describe the various ways of using CDR to create a true social network in spite of the highly noisy data source. The resulting network to predict each individual’s likelihood to default on payments for the network services, a complex behavior that involves a combination of social, economic, and legal considerations. Initially, a large number of features extracted from the network to build a model for predicting which users will default. By analyzing the relative contributions of features, the authors choose their best performing subsets ranging in size from small to medium. Features based on the number of close ties maintained by a user performed better than those derived from user’s geographical location. The paper contributions include systematic analysis of impact that the number of calls cutoff has on the properties of the network derived from CDR, and a methodology for building complex behavior models by creating very large sets of diverse features and systematically choosing those which perform best for the final model.