Predictive Modeling for International Roaming Fraud Detection in Ethio Telecom

dc.contributor.advisorTeferi, Dereje (PhD)
dc.contributor.authorWorku, Tarikua
dc.date.accessioned2019-09-26T10:09:10Z
dc.date.accessioned2023-11-18T12:44:33Z
dc.date.available2019-09-26T10:09:10Z
dc.date.available2023-11-18T12:44:33Z
dc.date.issued2018-03-04
dc.description.abstractTelecommunication fraud is remaining a challenging task since the beginning of commercial telecom service. There are various reasons that makes telecom fraud detection and prevention challenging. Integration of new technologies with ex-isting technologies without evaluating the security hole is main reason. Interna-tional roaming service is one of the immerged service in mobile technology. Roaming service allow subscribers to continue to use their home operator phone number, and other services while they are in another country. This geographical difference between service providers and subscribers make the roaming service open for different types of fraud attacks. So prevention and detection of interna-tional roaming fraud is crucial for service providers. In this study an effort has been made to build a predictive modeling for fraud detection using classification method. From decision tree and rule based classi-fication algorithms: random forest, J48, and ZeroR are used. Random Forest meet the highest accuracy 99.8154% with around 0.0109% false positive rate. So Ran-dom Forest algorithm is proposed as the best algorithm to detect international roaming fraud than the other two algorithms (J48 and ZeroR).en_US
dc.identifier.urihttp://etd.aau.edu.et/handle/12345678/19195
dc.language.isoenen_US
dc.publisherAddis Ababa Universityen_US
dc.subjectTelecom Frauden_US
dc.subjectInternational Roamingen_US
dc.subjectData Miningen_US
dc.subjectRan-Dom Foresten_US
dc.titlePredictive Modeling for International Roaming Fraud Detection in Ethio Telecomen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Tarikua Worku 2018.pdf
Size:
1.07 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Plain Text
Description: