Vital care insurance prediction using machine learning

Pasi, Ashok Kumar and Palarapu, Lasya and Mailaram, Akshitha and Kanithi, Laxmi Prasanna and Bommana, Deekshith (2025) Vital care insurance prediction using machine learning. World Journal of Advanced Research and Reviews, 25 (2). pp. 456-464. ISSN 2581-9615

The Vital Care Insurance Prediction System leverages machine learning, particularly linear regression, to estimate insurance costs based on user-specific attributes. It evaluates key factors such as age, gender, BMI, dependents, geographic region, medical risk, lifestyle, and occupation to enhance prediction accuracy. Unlike conventional actuarial models, this system provides dynamic forecasts and includes confidence metrics, ensuring greater transparency in cost estimation. The integration of machine learning enables a more adaptive and precise approach to risk assessment, improving the efficiency of insurance planning. A user-friendly Streamlit interface ensures accessibility, offering real-time results to both individuals and insurance professionals. The interactive "pop-up" feature enhances user engagement by presenting insights in a structured manner. This system bridges the gap between healthcare and finance, optimizing insurance decision-making processes. By increasing prediction accuracy and simplifying access to information, the system empowers users with data-driven insights, aiding them in making well-informed choices. This innovation ultimately enhances affordability and efficiency in the insurance sector, benefiting both providers and policyholders.