Detecting SIM box fraud using neural network

One of the most severe threats to revenue and quality of service in telecom providers is fraud. The advent of new technologies has provided fraudsters new techniques to commit fraud. SIM box fraud is one of such fraud that has emerged with the use of VOIP technologies. In this work, a total of nine...

Full description

Saved in:
Bibliographic Details
Main Authors: Hussein Elmi, Abdikarim, Ibrahim, Subariah, Sallehuddin, Roselina
Format: Conference or Workshop Item
Published: 2012
Online Access:http://eprints.utm.my/id/eprint/34051/
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Teknologi Malaysia
id my.utm.34051
record_format eprints
spelling my.utm.340512017-09-07T04:10:28Z http://eprints.utm.my/id/eprint/34051/ Detecting SIM box fraud using neural network Hussein Elmi, Abdikarim Ibrahim, Subariah Sallehuddin, Roselina One of the most severe threats to revenue and quality of service in telecom providers is fraud. The advent of new technologies has provided fraudsters new techniques to commit fraud. SIM box fraud is one of such fraud that has emerged with the use of VOIP technologies. In this work, a total of nine features found to be useful in identifying SIM box fraud subscriber are derived from the attributes of the Customer Database Record (CDR). Artificial Neural Networks (ANN) has shown promising solutions in classification problems due to their generalization capabilities. Therefore, supervised learning method was applied using Multi layer perceptron (MLP) as a classifier. Dataset obtained from real mobile communication company was used for the experiments. ANN had shown classification accuracy of 98.71 %. 2012 Conference or Workshop Item PeerReviewed Hussein Elmi, Abdikarim and Ibrahim, Subariah and Sallehuddin, Roselina (2012) Detecting SIM box fraud using neural network. In: The International Conference on IT Convergence and Security (ICITCS 2012).
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
description One of the most severe threats to revenue and quality of service in telecom providers is fraud. The advent of new technologies has provided fraudsters new techniques to commit fraud. SIM box fraud is one of such fraud that has emerged with the use of VOIP technologies. In this work, a total of nine features found to be useful in identifying SIM box fraud subscriber are derived from the attributes of the Customer Database Record (CDR). Artificial Neural Networks (ANN) has shown promising solutions in classification problems due to their generalization capabilities. Therefore, supervised learning method was applied using Multi layer perceptron (MLP) as a classifier. Dataset obtained from real mobile communication company was used for the experiments. ANN had shown classification accuracy of 98.71 %.
format Conference or Workshop Item
author Hussein Elmi, Abdikarim
Ibrahim, Subariah
Sallehuddin, Roselina
spellingShingle Hussein Elmi, Abdikarim
Ibrahim, Subariah
Sallehuddin, Roselina
Detecting SIM box fraud using neural network
author_facet Hussein Elmi, Abdikarim
Ibrahim, Subariah
Sallehuddin, Roselina
author_sort Hussein Elmi, Abdikarim
title Detecting SIM box fraud using neural network
title_short Detecting SIM box fraud using neural network
title_full Detecting SIM box fraud using neural network
title_fullStr Detecting SIM box fraud using neural network
title_full_unstemmed Detecting SIM box fraud using neural network
title_sort detecting sim box fraud using neural network
publishDate 2012
url http://eprints.utm.my/id/eprint/34051/
_version_ 1643649501422944256