Health insurance is one of the primary factors propelling the general insurance industry’s growth in India. According to CMS, Medicare and Medicaid, the two largest US government health insurance government programs, had a spending of $944.3 billion and $805.7 billion in 2022 respectively. Developed nations spend the most on health care, both in terms of total expenditure and as a share of GDP. The government pays a significant portion of the medical expenses for the elderly population through its Medicare program. The growing cost of healthcare combined with the baby boomer generation’s approaching retirement and ensuing Medicare eligibility places a heavy burden on the exchequer. Consequently, it is critical to employ every resource at hand in order to reduce health-related expenses. In order to predict health insurance prices, this study uses machine learning methods like Gradient Boosting, Support Vector Machine, Linear Regression, Random Forest Regression and XG Boost. The principal aim is to enable companies to make knowledgeable decisions regarding health coverage of the consumers by taking into account their specific health qualities. The study highlights the need for early cost estimation to assist people in choosing appropriate coverage by assessing algorithm performance on a health insurance dataset. The results of this study address the urgent need for efficient management of healthcare costs, and they are helpful for both individual decision-making and policymakers who are trying to find a balance between providing high-quality healthcare and being financially responsible.