Subscribe to DSC Newsletter

How to develop churn prediction model for telecom company?

Hi everyone,

I am working in a telecom company, which is interested in developing a churn prediction model. I want to know the which steps should I follow in order to develop such kind of model. Any help regarding the problem is highly appreciated. thanks in advance.

Views: 35132

Reply to This

Replies to This Discussion

Thank you to all for all your suggestions. I got lots of valuable feedback.

Read and try Survival Analysis Modeling for a churn prediction...

Hi good evening everyone.
I read this article little late. You do have many variables. You can use customer demographic data, purchase history, severe usage and billing date. Then you can use logistic regression model to do prediction. Since you do have nominal, ordinal and scale data.

Kindly check the following link for right answer: (An example is given for churn prediction in case study) 

http://www.academia.edu/11846437/Statistical_Analysis_Need_of_Today...

The most important step in churn is defining your target variable. And more importantly, whatever you define as churn must be in agreement with the business team. Once you have agreement, you can then begin to code for this and then build your analytical file with all the independent variables.  But if the business team asks you to define churn, one good way is to look at activity, be it usage or billing. But you need to define a period of time for where there is no usage or billing and which can be defined as being representative of churn..

  

RSS

On Data Science Central

Follow Us

© 2018   AnalyticBridge.com is a subsidiary and dedicated channel of Data Science Central LLC   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service