Summary

In this chapter, we analyzed a very common business case: customer churn. Understanding the causes of this, as well as being able to take preventive actions to avoid this, can create a lot of revenue for a company.

In the example that we have analyzed, we have seen how to clean the variables in a dataset to properly represent them and prepare them for machine learning. Visualizing the variables in a relationship against the target variable that we are analyzing allows us to understand the problem better. Finally, we trained several machine learning models that we later analyzed to understand how their performances were when predicting the target variable.

In the next chapter, we will focus more of our attention on understanding how variables affect segments and group users with homogenous characteristics to understand them better.