Customer Churn Analysis Based On Telecom Data Warehouse

With the telecommunication system reform development and our entrance of WTO, the competition of mobile telecommunication operation is becoming fiercer. Compared with other industry, the mobile telecommunication operation has more data of customers. Who can mine and analyze the knowledge contained in the data correctly will offer product and service to customer better and find more opportunities, thus win the competition. Our domestic research on this field is still at infancy, abroad's has already been superior to mine greatly. So, there is important practical value in the research on data mining of our mobile telecommunication.The intense market competition of the telecommunication profession is the external power for the DW's establishment, the telecommunication enterprise own development intrinsic request is the DW application primary factor, at the same time the telecommunication profession accumulating the massive services operation data provides the external condition for the DW. These three have established the demand and the physical foundation for the application of DW technology in the telecommunication domain. Who can mine and analyze the knowledge contained in the data correctly will offer product and service to customer better and find more opportunities, thus win the competition. Our domestic research on this field is still at infancy, aroid's has already been superior to mine greatly. So, there is important practical value in the research on data mining of our mobile telecommunication.This paper mainly carries on following several works:1. The paper carries on the analysis on the DW's application in the main telecommunication domain with Liaoning Unicom business analysis system and the DW characteristic of telecommunication profession;2. Ascertain the objects methods of researching and the effects it should get.3. Explain the way that how to make the model and analyze junior customer values based on the data of one telecom company.4. Get the model according to the theories of decision tree and regress, and make contrast.The research fruit of this paper has applied in KPI module of the Telecom Management and Analysis System of some telecom operators in China, and the application effect is good, and this application experience will bring a useful way to build other decision-making applications in the whole data warehouse.