Forecasting Member Churn in Medical Insurance through Machine Learning Analysis

Abstract

The insurance industry faces an escalating challenge with increasing customer churn, spurred by global advancements in technology. The ease with which customers can compare policies, explore new offers, and switch providers online has intensified industry competition. This phenomenon has led to substantial revenue loss for many companies, as acquiring new customers often incurs higher costs than retaining existing ones. Recognizing the paramount importance of client retention, this research addresses the issue by proposing a Churn Prediction System tailored for the medical insurance sector. The system leverages machine learning models to forecast whether an existing customer is likely to churn, crucial for proactive retention strategies. To determine the most effective algorithm for this task, four models—Logistic Regression, Random Forest Decision Tree, Support Vector Machine, and Artificial Neural Network—are tested. The Random Forest Classifier emerges as the optimal performer which achieve accuracy of 90%.