Optimizing health insurance premium predictions using machine learning

Abstract

This research conducts a comprehensive investigation into the application of the XGBoost regressor algorithm for predicting insurance premiums. Insurance pricing serves as a cornerstone of the industry, as it directly influences profitability and operational stability through effective risk mitigation. To maintain market competitiveness and foster long-term viability, insurers require robust predictive frameworks capable of delivering accurate premium estimates. XGBoost, a powerful machine learning algorithm renowned for its proficiency in processing intricate datasets and generating reliable forecasts, has garnered significant attention in recent studies. The study examines the historical context and critical role of insurance pricing methodologies, introduces the XGBoost regression framework, and evaluates existing studies on its implementation in premium prediction. By elucidating the opportunities and limitations of XGBoost in this domain, the findings lay the groundwork for future research and innovation in optimizing actuarial models. KEY WORDS: Health Insurance, Premium Prediction, Machine Learning Algorithms, Regression.