The cost of generating a new customer exceeds the cost of retaining a present customer. This belief applies to most industries where customers' loyalty became an important strategic and financial goal. In the paid television industry, viewers have many options for television services nowadays. The number of subscriptions to these services is growing day by day, becoming a multimillion-dollar business. Individuals usually subscribe to a single television provider, but they are continuously exposed to tempting offers from the competitors. With so many alternatives, keeping the subscribers' loyalty is a challenge that can be addressed by applying statistical methods. This project analyzes 12 months of customers' data from a satellite television provider in a South American country. It calculates the monthly attrition (churn) risk for each subscriber using data associated to her/his profile and 12 months of historical call center's contacts records. The attrition risk-scores are calculated with (a) logistic regression and (b) Cox proportional hazard models. The results are compared and validated by counting the actual attrition occurring within 30 days after scoring. Preliminary processes of data analysis and discovery are discussed and implemented. The results are validated and applied within the actual operational methodology. For the top 5% of the base (with higher churn risk), these models' predictions identify over 25% of the monthly churners on average.
|Commitee:||Korosteleva, Olga, Suaray, Kagba N.|
|School:||California State University, Long Beach|
|Department:||Mathematics and Statistics|
|School Location:||United States -- California|
|Source:||MAI 53/06M(E), Masters Abstracts International|
|Subjects:||Marketing, Applied Mathematics, Statistics|
|Keywords:||Attrition, Customer churn, Television churn|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be