Data Mining Application In Supporting Fraud Detection On Ethio-mobile Services

The problem of Mobile frauds has been getting more and more serious for many years,rnand is even getting more and more worse not only in western countries but also in somerndeveloping countries. Fraud is the most significant threat to the communicationsrnbusiness, eroding margins, consuming network capacity and jeopardizing customerrnrelationships. Detection, Analysis and prevention mechanisms are emerging both fromrntelecommunications operators and academia. In this paper, the possible application ofrndata mining in supporting fraud detection on Ethio-Mobile Services has been tested byrnthe use of neural network technique.rnThe methodology used for this research had three basic steps. These were: datarncollection, data preparation, and model building and testing. The required data wasrncollected from Ethiopian Telecommunication Corporation which is called Call DetailrnRecord. This record shows the behavior of each mobile phone users. Next, datarnpreparation tasks (such as data cleaning, feature selection, data transformation etc) werernundel1aken. Several Neural network models were built and tested for their classificationrnaccuracy; and the model with encouraging results was taken.

Get Full Work

Report copyright infringement or plagiarism