From the course: Statistics and Python for Telecommunication: Using Data Analytics for Decision-Making in Modern Telecommunications
Join today to access over 24,900 courses taught by industry experts.
Predicting customer churn in telecom - Python Tutorial
From the course: Statistics and Python for Telecommunication: Using Data Analytics for Decision-Making in Modern Telecommunications
Predicting customer churn in telecom
(calm music) - [Instructor] So I will go to the numbers first. So let's take an example. We have a total customers of 100. So out of these 100 customers, we know that 20 have churned. Now 20 have churned, 80 in the green, they have not churned. These 20 people who have left the network or left operator. What is the reason of their churn? Is it the call drops? Yes, 16 out of 20, they left because of the call drops because the call quality is not good. It has dropped. Okay. So we need to first of all figure out what is the overall probability of churn out of 100. Out of 100, 20 churn, irrespective of any reason. So fair enough, probability of churn is 20. Probability of non-churn, those who has not churned, it is pretty much straightforward. 80%. The users who have churned, but the reason is call drop. In that case, what it is, the probability of drops, the people who have already churned, and there is a reason is a drop. In that case, what is the probability of that? It's 16 out of 20,…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.