This project demonstrates the development of a machine learning system to predict individual
medical insurance costs. The primary goal is to provide a reliable, data-driven tool for
estimating healthcare expenses, offering significant value to both insurance providers for
premium calculation and individuals for financial planning.ascular health profile.
A Linear Regression model was developed and trained on a dataset containing key
demographic and health attributes, including age, Body Mass Index (BMI), and smoking status.
These factors were identified as the most significant drivers of medical costs.
The model performs strongly, achieving an Adjusted R-squared of 80%. This indicates that
the model successfully explains 80% of the variance in insurance charges, proving it to be a
robust and effective predictive tool. The high Adjusted $R^2$ value confirms that the selected
features have a strong, relevant relationship to the costs, without being unnecessarily
complex.ed decisions promptly.
This tool is designed to automate and refine premium estimations, though it is intended for
informational purposes. Actual charges will vary, and this predictor is not a substitute for
professional medical or financial advice.