Application Of Data Mining Technology To Support Customer Insolvency Prediction At Ethiopian Telecommunication Corporation

Many service-providing companies often suffer from insolvent customers whornuse the provided services without paying their dues. EthiopianrnTelecommunication Corporation is one of these companies which is loosingrnconsiderable amount of money. This paper reports on the findings of a research that had the objective to build arndecision support system to handle customer insolvency, customers' failure tornmeet their payment obligation, for Ethiopian Telecommunication Corporation.rnThe study focused on post paid mobile phone users for reason of datarnavailability. In the paper, the process of building a model through knowledge discovery andrndata • mining techniques in heterogeneous as well as noisy data is described.rnDifferent statistical tools are also used for the purpose of data analysis.rnThe neural network back propagation algorithm is used in the study. Thernparticular tool used for the model building was the neural network toolbox whichrnis incorporated in MA TLAB 6.5. Different variations of the basic back propagationrnalgorithm were tested and the one with the best performance was selected forrnthe model building process.rnIn general, a model that can classify customers, well in advance, as potentiallyrnsolvent or insolvent, was built and tested. The reported findings are promising,rnmaking the proposed model a useful tool in the decision making process. And thernwhole research process can be a good input for further in-depth research.

Get Full Work

Report copyright infringement or plagiarism