Application of Data Mining Technology to Support Customer Insolvency Prediction at Ethiopian Telecommunication Corporation
No Thumbnail Available
Date
2004-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
Many service-providing companies often suffer from insolvent customers who
use the provided services without paying their dues. Ethiopian
Telecommunication Corporation is one of these companies which is loosing
considerable amount of money. This paper reports on the findings of a research that had the objective to build a
decision support system to handle customer insolvency, customers' failure to
meet their payment obligation, for Ethiopian Telecommunication Corporation.
The study focused on post paid mobile phone users for reason of data
availability. In the paper, the process of building a model through knowledge discovery and
data • mining techniques in heterogeneous as well as noisy data is described.
Different statistical tools are also used for the purpose of data analysis.
The neural network back propagation algorithm is used in the study. The
particular tool used for the model building was the neural network toolbox which
is incorporated in MA TLAB 6.5. Different variations of the basic back propagation
algorithm were tested and the one with the best performance was selected for
the model building process.
In general, a model that can classify customers, well in advance, as potentially
solvent or insolvent, was built and tested. The reported findings are promising,
making the proposed model a useful tool in the decision making process. And the
whole research process can be a good input for further in-depth research.
Description
Keywords
Information Science