Predictive Modeling for Fraud Detection in Telecommunications: The Case of Ethio Telecom
No Thumbnail Available
Date
2013-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
Telecom fraud is a major concern for telecom operators as well as for governments all over the world. This is mainly because of security threats and economic impacts. These facts can be substantiated by the rules and regulations put in place by different countries.
In this study an effort has been made to predict fraudulent calls made using SIM-boxes to terminate international calls. Such frauds greatly affect the revenue of telephone operators.
Classification methods of data mining are applied using J48, PART and multilayer perceptron algorithms on data collected from ethio telecom. WEKA data mining tool has been used to come up with a model for predicting fraudulent activities. For this study pre-paid sampled voice CDR data has been used along with SMS, GPRS and other data such as pre-paid wallet recharge log from OCS and CCB data warehouse in ethio-telecom.
The experimentation result showed that the model from the PART algorithm exhibited 100% accuracy level followed by J48 algorithm with 99.98%. The rules generated from PART and J48 algorithms enable telecom operators in general and ethio telecom in particular to locate the whereabouts of SIM-boxes as well as other critical information. Moreover, an effort has been made to show the impact of SIM-boxes on telecom operators‟ revenue.
Description
Keywords
SIM-boxes as well as other critical information