On information propagation in mobile call networks

We consider the dynamics of rapid propagation of information (RPI) in mobile phone networks. We propose a heuristic method for identification of sequences of calls that supposedly propagate the same information and apply it to large-scale real-world data. We show that some of the information propagation events identified by the proposed method can explain the physical co-location of subscribers. We further show that features of subscriber’s behavior in these events can be used for efficient churn prediction. To the best of our knowledge, our method for churn prediction is the first method that relies on dynamic, rather than static, social behavior. Finally, we introduce two generative models that address different aspects of RPI. One model describes the emergence of sequences of calls that lead to RPI. The other model describes the emergence of different topologies of paths in which the information propagates from one subscriber to another. We report high correspondence between certain features observed in the data and these models.

[1]  Steffen Staab,et al.  Social Networks Applied , 2005, IEEE Intell. Syst..

[2]  S. Doyle.  The role of social networks in marketing , 2007 .

[3]  Pedro M. Domingos.  Mining Social Networks for Viral Marketing , 2022 .

[4]  M. Saravanan,et al.  Analyzing and labeling telecom communities using structural properties , 2011, Social Network Analysis and Mining.

[5]  Shiwei Tang,et al.  A Mixed Process Neural Network and its Application to Churn Prediction in Mobile Communications , 2006, Sixth IEEE International Conference on Data Mining - Workshops (ICDMW'06).

[6]  P. Lachenbruch.  Mathematical Statistics, 2nd Edition , 1972 .

[7]  David Lazer,et al.  Inferring friendship network structure by using mobile phone data , 2009, Proceedings of the National Academy of Sciences.

[8]  Christos Faloutsos,et al.  The "DGX" distribution for mining massive, skewed data , 2001, KDD '01.

[9]  Alex Pentland,et al.  Composite Social Network for Predicting Mobile Apps Installation , 2011, AAAI.

[10]  T. E. Harris,et al.  The Theory of Branching Processes. , 1963 .

[11]  Christos Faloutsos,et al.  Surprising Patterns for the Call Duration Distribution of Mobile Phone Users , 2010, ECML/PKDD.

[12]  Elen de Oliveira Lima.  Domain knowledge integration in data mining for churn and customer lifetime value modelling: new approaches and applications , 2009 .

[13]  Adriana Iamnitchi,et al.  Identifying high betweenness centrality nodes in large social networks , 2012, Social Network Analysis and Mining.

[14]  Chao Fan,et al.  Inferring Social Networks Based on Movie Rating Data , 2011 .

[15]  Fernando Vega-Redondo,et al.  Complex Social Networks: Searching in Social Networks , 2007 .

[16]  Bin Li,et al.  Automated Cellular Modeling and Prediction on a Large Scale , 2000, Artificial Intelligence Review.

[17]  Yossi Richter,et al.  Predicting Customer Churn in Mobile Networks through Analysis of Social Groups , 2010, SDM.

[18]  Sougata Mukherjea,et al.  On the structural properties of massive telecom call graphs: findings and implications , 2006, CIKM '06.

[19]  David G. Stork,et al.  Pattern Classification , 1973 .

[20]  B. Libai,et al.  Social Effects on Customer Retention , 2011 .

[21]  J. Goldenberg,et al.  The Role of Hubs in the Adoption Process , 2009 .

[22]  Jure Leskovec,et al.  Inferring networks of diffusion and influence , 2010, KDD.

[23]  Jon Kleinberg,et al.  Maximizing the spread of influence through a social network , 2003, KDD '03.

[24]  Dirk Van den Poel,et al.  Handling class imbalance in customer churn prediction , 2009, Expert Syst. Appl..

[25]  Kristof Coussement,et al.  Churn prediction in subscription services: an application of support vector machines while comparing two parameter-selection techniques , 2008 .

[26]  Parag C. Pendharkar,et al.  Genetic algorithm based neural network approaches for predicting churn in cellular wireless network services , 2009, Expert Syst. Appl..

[27]  Luo Bin,et al.  Customer Churn Prediction Based on the Decision Tree in Personal Handyphone System Service , 2007, 2007 International Conference on Service Systems and Service Management.

[28]  Fang Wu,et al.  Novelty and collective attention , 2007, Proceedings of the National Academy of Sciences.

[29]  J. Goldenberg,et al.  The NPV of bad news , 2007 .

[30]  Matthew Richardson,et al.  Mining the network value of customers , 2001, KDD '01.

[31]  Kathy E. Gill.  How can we measure the influence of the blogosphere? , 2004 .

[32]  R. Fildes,et al.  Telecommunications demand forecasting—a review , 2002 .

[33]  Rupesh K. Gopal,et al.  Customer Churn Time Prediction in Mobile Telecommunication Industry Using Ordinal Regression , 2008, PAKDD.

[34]  D. Lazer,et al.  Inferring Social Network Structure using Mobile Phone Data , 2006 .

[35]  Sougata Mukherjea,et al.  Social ties and their relevance to churn in mobile telecom networks , 2008, EDBT '08.

[36]  Jiaqin Yang,et al.  Social reference group influence on mobile phone purchasing behaviour: a cross-nation comparative study , 2007, Int. J. Mob. Commun..

[37]  Jure Leskovec,et al.  The dynamics of viral marketing , 2005, EC '06.

[38]  Peter van der Putten,et al.  The Impact of Experimental Setup in Prepaid Churn Prediction for Mobile Telecommunications: What to Predict, for Whom and Does the Customer Experience Matter? , 2010, Trans. Mach. Learn. Data Min..

[39]  Chris Volinsky,et al.  Network-Based Marketing: Identifying Likely Adopters Via Consumer Networks , 2006, math/0606278.

[40]  Ronald L. Rivest,et al.  Introduction to Algorithms , 1990 .

[41]  Jure Leskovec,et al.  Correcting for missing data in information cascades , 2011, WSDM '11.

[42]  Shie Mannor,et al.  Generative models for rapid information propagation , 2010, SOMA '10.

[43]  Emilio Ferrara,et al.  Forensic analysis of phone call networks , 2012, Social Network Analysis and Mining.