Analysis and Detection Mechanisms of SIM Box Fraud in The Case of Ethio Telecom
| dc.contributor.advisor | Yalemzewd, Negash (PhD) | |
| dc.contributor.author | Frehiwot, Mola | |
| dc.date.accessioned | 2019-05-30T10:03:20Z | |
| dc.date.accessioned | 2023-11-04T15:14:41Z | |
| dc.date.available | 2019-05-30T10:03:20Z | |
| dc.date.available | 2023-11-04T15:14:41Z | |
| dc.date.issued | 2017-12-12 | |
| dc.description.abstract | Telecommunication fraud can be defined as theft of services (fixed telephone, mobile, data and etc.) or measured abuse of voice or data networks. Fraud is one of the most severe threats to revenue and quality of service in telecommunication networks. The advent of new technologies has provided fraudsters with new techniques to commit fraud. Subscriber identity module box (SIMbox) fraud is one of such fraud that is used in international calls and it has emerged with the use of VOIP technologies. In this thesis, the call detail records (CDR’s) from ethio telecom were organized in order to develop models of normal and fraudulent number behavior via data mining techniques. And four classification algorithms namely decision trees, rule based induction, neural network and hybrid algorithms are used. First we have done data analysis on the data set and for classification we use nine selected features of data extracted from Customer Database Record. The experimentation result will enable to understand the problem of SIM box fraud in the case of ethio telecom and clarifying the behavior of fraudulent and legitimate calls. Finally, we got a good result from PART rule based and hybrid (J48 and PART) algorithms and performed the best among the four algorithms. PART rule based induction classification algorithm had a better performance with an accuracy rate of 99.4906% with true positive and 0.5094 % false positive ratio and followed by hybrid of J48 and PART algorithm with accuracy rate 99.4795% with true positive and 0.5205% false positive ratios. | en_US |
| dc.identifier.uri | http://etd.aau.edu.et/handle/123456789/18345 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | Addis Ababa University | en_US |
| dc.subject | SIM Box Fraud | en_US |
| dc.subject | Telecom Fraud, Decision Tree | en_US |
| dc.subject | Multilayer perceptron | en_US |
| dc.title | Analysis and Detection Mechanisms of SIM Box Fraud in The Case of Ethio Telecom | en_US |
| dc.type | Thesis | en_US |