Analyzing and Predicting Telecommunication Churn

In this chapter, we will develop a machine learning (ML) project to analyze and predict whether a customer is likely to cancel the subscription to his telecommunication contract or not. In addition, we'll do some preliminary analysis of the data and take a closer look at what types of customer features are typically responsible for such a churn.

Widely used classification algorithms, such as decision trees, random forest, logistic regression, and Support Vector Machines (SVMs) will be used for analyzing and making the prediction. By the end, readers will be able to choose the best model to use for a production-ready environment.

In a nutshell, we will learn the following topics throughout this end-to-end project:

• Why, and how, do we do churn prediction?
• Logistic regression-based churn prediction
• SVM-based churn prediction
• Decision tree-based churn prediction
• Random forest-based churn prediction
• Selecting the best model for deployment