A Comprehensive Study on the Premium estimation of the Health Insurance Sector

Health insurance plays a crucial role in providing financial security against medical expenses, ensuring accessibility to healthcare services. However, premium estimation remains a complex process influenced by multiple factors such as age, medical history, and lifestyle choices. This study explores key determinants of health insurance premiums and employs machine learning models to enhance prediction accuracy. The study employs secondary data and uses a range of predictive models, such as Linear Regression, Decision Tree, Random Forest, Gradient Boosting, and K-Nearest Neighbors, to efficiently estimate insurance premiums. Exploratory Data Analysis (EDA) and statistical methods are used to detect meaningful correlations and enhance the transparency of premium calculation. The results show that age, chronic conditions, previous surgeries, and hereditary diseases are significant drivers of premium charges. Among the models tested, Random Forest Regression demonstrated the highest accuracy in premium prediction. By integrating machine learning into premium estimation, this study aims to improve transparency, optimize pricing structures, and empower consumers with better financial planning tools. Future research can further refine predictive models by incorporating real-time claim data and additional health-related variables.