In this chapter, we have seen how to develop a predictive model for analyzing insurance severity claims using some of the most widely used regression algorithms. We started with simple LR. Then we saw how we can improve performance using a GBT regressor. Then we experienced improved performance using ensemble techniques, such as the Random Forest regressor. Finally, we looked at performance comparative analysis between these models and chose the best model to deploy for production-ready environment.
In the next chapter, we will look at a new end-to-end project called Analyzing and Predicting Telecommunication Churn. Churn prediction is essential for businesses as it helps you detect customers who are likely to cancel a subscription, product, or service. It also minimizes customer defection. It does so by predicting which customers are more likely to cancel a subscription to a service.
