Telecommunication Subscription Fraud Detection Using Neural Network

Telecommunications fraud costs carriers billions of revenue dollars annually. The telecom fraud criminal is often ingenious and is typically motivated by money, anonymity, or both. Through use of the Internet, the fraud community is becoming more collaborative, and as a result, more ingenious. Beca...

Full description

Saved in:

Bibliographic Details
Main Author:	Nuratikhah, Shahrin
Format:	Thesis
Language:	eng eng
Published:	2008
Subjects:	TK5101-6720 Telecommunication
Online Access:	https://etd.uum.edu.my/938/1/Nuratikhah_Shahrin.pdf https://etd.uum.edu.my/938/2/Nuratikhah_Shahrin.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uum-etd.938
record_format	uketd_dc
spelling	my-uum-etd.9382013-07-24T12:09:43Z Telecommunication Subscription Fraud Detection Using Neural Network 2008-06 Nuratikhah, Shahrin College of Arts and Sciences (CAS) Faculty of Information Technology TK5101-6720 Telecommunication Telecommunications fraud costs carriers billions of revenue dollars annually. The telecom fraud criminal is often ingenious and is typically motivated by money, anonymity, or both. Through use of the Internet, the fraud community is becoming more collaborative, and as a result, more ingenious. Because of this, fraud detection applications must become more sophisticated to keep pace with the criminals. A system to prevent subscription fraud in fixed telecommunications with high impact on long-distance carriers is proposed. The system consists of a neural network technique, using Multilayer Perceptron (MLP). A total of 158 data samples from Telecom Malaysia Bhd were collected trained and tested using model. The prediction module allows identifying potential fraudulent customers at the time of subscription. The analysis of the data shows a reasonably strong correlation between the input variable, which consist of severity, user certainty factor, indicator case and target. The result shows that 78% of prediction accuracy has been obtained. From the result that has been produce, neural network has a potential to be used for detecting fraud in telecommunication. 2008-06 Thesis https://etd.uum.edu.my/938/ https://etd.uum.edu.my/938/1/Nuratikhah_Shahrin.pdf application/pdf eng validuser https://etd.uum.edu.my/938/2/Nuratikhah_Shahrin.pdf application/pdf eng public masters masters Universiti Utara Malaysia
institution	Universiti Utara Malaysia
collection	UUM ETD
language	eng eng
topic	TK5101-6720 Telecommunication
spellingShingle	TK5101-6720 Telecommunication Nuratikhah, Shahrin Telecommunication Subscription Fraud Detection Using Neural Network
description	Telecommunications fraud costs carriers billions of revenue dollars annually. The telecom fraud criminal is often ingenious and is typically motivated by money, anonymity, or both. Through use of the Internet, the fraud community is becoming more collaborative, and as a result, more ingenious. Because of this, fraud detection applications must become more sophisticated to keep pace with the criminals. A system to prevent subscription fraud in fixed telecommunications with high impact on long-distance carriers is proposed. The system consists of a neural network technique, using Multilayer Perceptron (MLP). A total of 158 data samples from Telecom Malaysia Bhd were collected trained and tested using model. The prediction module allows identifying potential fraudulent customers at the time of subscription. The analysis of the data shows a reasonably strong correlation between the input variable, which consist of severity, user certainty factor, indicator case and target. The result shows that 78% of prediction accuracy has been obtained. From the result that has been produce, neural network has a potential to be used for detecting fraud in telecommunication.
format	Thesis
qualification_name	masters
qualification_level	Master's degree
author	Nuratikhah, Shahrin
author_facet	Nuratikhah, Shahrin
author_sort	Nuratikhah, Shahrin
title	Telecommunication Subscription Fraud Detection Using Neural Network
title_short	Telecommunication Subscription Fraud Detection Using Neural Network
title_full	Telecommunication Subscription Fraud Detection Using Neural Network
title_fullStr	Telecommunication Subscription Fraud Detection Using Neural Network
title_full_unstemmed	Telecommunication Subscription Fraud Detection Using Neural Network
title_sort	telecommunication subscription fraud detection using neural network
granting_institution	Universiti Utara Malaysia
granting_department	College of Arts and Sciences (CAS)
publishDate	2008
url	https://etd.uum.edu.my/938/1/Nuratikhah_Shahrin.pdf https://etd.uum.edu.my/938/2/Nuratikhah_Shahrin.pdf
_version_	1747827032135303168

Telecommunication Subscription Fraud Detection Using Neural Network

Similar Items