User profiling and classification for fraud detection in mobile communications networks

No Thumbnail Available

URL

Journal Title

Journal ISSN

Volume Title

Doctoral thesis (article-based)
Checking the digitized thesis and permission for publishing
Instructions for the author

Date

2000-12-19

Major/Subject

Mcode

Degree programme

Language

en

Pages

55, [53]

Series

Acta polytechnica Scandinavica. Ma, Mathematics and computing series, 109

Abstract

The topic of this thesis is fraud detection in mobile communications networks by means of user profiling and classification techniques. The goal is to first identify relevant user groups based on call data and then to assign a user to a relevant group. Fraud may be defined as a dishonest or illegal use of services, with the intention to avoid service charges. Fraud detection is an important application, since network operators lose a relevant portion of their revenue to fraud. Whereas the intentions of the mobile phone users cannot be observed, it is assumed that the intentions are reflected in the call data. The call data is subsequently used in describing behavioral patterns of users. Neural networks and probabilistic models are employed in learning these usage patterns from call data. These models are used either to detect abrupt changes in established usage patterns or to recognize typical usage patterns of fraud. The methods are shown to be effective in detecting fraudulent behavior by empirically testing the methods with data from real mobile communications networks.

Description

Keywords

fraud detection, telecommunication, neural networks, probabilistic models, data analysis, data mining

Other note

Parts

  • Alhoniemi, E., J. Hollmén, O. Simula, and J. Vesanto (1999). Process monitoring and modeling using the self-organizing map. Integrated Computer Aided Engineering 6(1), 3-14. [article1.pdf] © 1999 IOS Press. By permission.
  • Taniguchi, M., M. Haft, J. Hollmén, and V. Tresp (1998). Fraud detection in communication networks using neural and probabilistic methods. In Proceedings of the 1998 IEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP'98), Volume II, pp. 1241-1244. [article2.pdf] © 1998 IEEE. By permission.
  • Hollmén, J. and V. Tresp (1999). Call-based fraud detection in mobile communication networks using a hierarchical regime-switching model. In M. Kearns, S. Solla, and D. Cohn (Eds.), Advances in Neural Information Processing Systems 11: Proceedings of the 1998 Conference (NIPS'11), pp. 889-895. MIT Press. [article3.pdf] © 1998 MIT Press. By permission.
  • Hollmén, J., V. Tresp, and O. Simula (1999). A self-organizing map for clustering probabilistic models. In Proceedings of the Ninth International Conference on Artificial Neural Networks (ICANN'99), Volume 2, pp. 946-951. IEE.
  • Hollmén, J., M. Skubacz, and M. Taniguchi (2000). Input dependent misclassification costs for cost-sensitive classification. In N. Ebecken and C. Brebbia (Eds.), DATA MINING II - Proceedings of the Second International Conference on Data Mining 2000, pp. 495-503. WIT Press. [article5.pdf] © 2000 WIT Press. By permission.
  • Hollmén, J. and V. Tresp (2000). A hidden Markov model for metric and event-based data. In Proceedings of EUSIPCO 2000 - X European Signal Processing Conference, Volume II, pp. 737-740. [article6.pdf] © 2000 EUSIPCO - 2000. By permission.
  • Hollmén, J., V. Tresp, and O. Simula (2000). A learning vector quantization algorithm for probabilistic models. In Proceedings of EUSIPCO 2000 - X European Signal Processing Conference, Volume II, pp. 721-724. [article7.pdf] © 2000 EUSIPCO - 2000. By permission.

Citation

Permanent link to this item

https://urn.fi/urn:nbn:fi:tkk-002567