Predicting Customer Churn in Insurance Industry Using Big Data and Machine Learning

The market is filled with cutthroat competition for businesses in the Insurance industry. Customers are the lifeblood of the Insurance industry. They would rather keep the customers they already have rather than try to bring in new ones because bringing in new customers requires a significant investment up front. Because they are losing long-term customers, Insurance operators are seeing their market share in the Insurance industry decrease. Business analysts and customer relationship management (CRM) analysts need to understand and analyse the behavioral patterns of existing customer churn data in order to reduce the amount of customers who leave a company. The hybrid LGBM and XGBoost model, Logistic Regression model, and Random Forest model were the three models that were used in the study to construct a valid and accurate churn prediction model for the Insurance industry. In addition, the results of the empirical evaluation suggest that the Logistic Regression model, which was chosen by the AUC metric, is the most appropriate model to use. The hybrid LGBM and XGBoost model performs well in all aspects of churn prediction as compared with other solo models. These findings provide an understanding of the characteristics and preferences of customers, which enables one to predict customers who are likely to churn and the reasons for churning so that preventative measures can be taken in advance.