Encyclopedia of Social Network Analysis and Mining

2018 Edition
| Editors: Reda Alhajj, Jon Rokne

Telecommunications Fraud Detection, Using Social Networks for

  • Chris Volinsky
Reference work entry
DOI: https://doi.org/10.1007/978-1-4939-7131-2_280




These are statistical profiles of entities based on transactional data. These signatures, like our handwritten ones, evolve through time

Social Networks

These are the networks or graphs created by the communication patterns, friendships, or trust relationships between individuals

Telecommunications Fraud

This occurs when someone uses or sells telecommunications services with no intention to pay for that service


Telecommunications fraud can be challenging to detect and eradicate for service providers. This entry describes one effective way of finding new cases of fraud through mining the network of relationships which emerges from the transactional data collected in the network. For each entity in the network, the social network – or community of interest (COI) – is observed and analyzed to look for patterns which might indicate fraud. The COI are updated regularly via an exponentially...

This is a preview of subscription content, log in to check access.



I thank Deepak Agarwal, Rick Becker, Robert Bell, Corinna Cortes, Shawndra Hill, Daryl Preg-ibon, and Allan Wilks, who were all key contributors to the methodologies and applications described here.


  1. Becker RA, Volinsky C, Wilks AR (2010) Fraud detection at AT&T: a historical perspective. Technometrics 52(1):20–33MathSciNetCrossRefGoogle Scholar
  2. Cortes C, Pregibon D (2001) Signature-based methods for data streams. Data Min Knowl Discov 5(3):167–182zbMATHCrossRefGoogle Scholar
  3. Hill S, Agarwal D, Bell R, Volinsky C (2006) Building an effective representation for dynamic networks. J Comput Graph Stat 15(3):584–608MathSciNetCrossRefGoogle Scholar
  4. Isaacson W (2011) Steve Jobs: the exclusive biography. Little Brown Book, LondonGoogle Scholar
  5. Phua C, Lee V, Smith K, Gayler R (2005) A comprehensive survey of data mining-based fraud detection research. Artif Intell RevGoogle Scholar

Copyright information

© Springer Science+Business Media LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Statistics Research DepartmentAT&T Labs-ResearchFlorham ParkUSA

Section editors and affiliations

  • Rosa M. Benito
    • 1
  • Juan Carlos Losada
    • 2
  1. 1.Universidad Politécnica de MadridMadridSpain
  2. 2.Universidad Politécnica de MadridMadridSpain