A health insurance company’s financial success relies on generating more revenue than it incurs cost on the healthcare of its policyholders. However, forecasting medical expenses is challenging due to the unpredictability of costs associated with rare conditions. This project aims to precisely predict insurance costs by analyzing individuals’ data, such as age, Body Mass Index, smoking habits, and other factors. Furthermore, we will identify the key variable that has the most significant impact on insurance costs. These predictions can be utilized to develop actuarial tables, enabling the adjustment of yearly premiums based on anticipated treatment expenses. This essentially constitutes a regression problem.