This project is intended to predict whether a customer would switch to other insurance party or gets retained.
Insurance companies around the world operate in a very competitive environment. With various aspects of data collected from millions of customers, it is painstakingly hard to analyse and understand the reason for a customer’s decision to switch to a different insurance provider. For an industry where customer acquisition and retention are equally important, and the former being a more expensive process, insurance companies rely on data to understand customer behavior to prevent retention. Thus knowing whether a customer is possibly going to switch beforehand gives Insurance companies an opportunity to come up with strategies to prevent it from actually happening.
Multiple machine learning models are created with the car insurance data to predict the churn.
Some of the algorithms used for training are
XGBoost
Random Forest
Logistic Regression
Support Vector Machines
K-Nearest Neighbors
Naive Bayes