Medical Insurance Cost Prediction Using Machine Learning

The increasing cost of healthcare services has made medical insurance a crucial financial tool. Predicting insurance costs accurately helps insurance providers assess risk and allows customers to plan better. This project focuses on building a machine learning model to predict individual medical insurance charges using key features such as age, sex, BMI, number of children, smoking status, and region. The model uses linear regression as a base method to map the relationship between these variables and insurance cost. The data is pre-processed and visualized using exploratory data analysis (EDA), followed by model training and evaluation using metrics like R² score. This project demonstrates the application of data science in real-world financial estimation, providing an efficient and scalable solution for insurance cost prediction. Index Terms: Medical Insurance, Machine Learning, Linear Regression, Cost Prediction, EDA, Streamlit, Health Analytics, Insurance Premium Estimation.