This project focuses on building a machine learning regression model to predict health insurance costs based on several demographic and health-related features. The objective is to estimate the insurance charges using data such as age, gender, BMI, number of children, smoking status, and region.
The project begins with Exploratory Data Analysis (EDA) to understand the dataset, identify relationships between variables, and visualize important patterns using plots such as correlation heatmaps and distribution graphs. These visualizations help reveal how different features influence insurance charges.
During the preprocessing stage, categorical variables were transformed into numerical values using encoding techniques, and the dataset was prepared for modeling. The data was then divided into training and testing sets to evaluate the performance of the regression model.
A regression algorithm was trained to predict the continuous target variable (insurance charges). Regression models are commonly used for predicting numerical values such as medical costs, prices, or demand forecasting.
The model performance was evaluated using regression evaluation metrics such as R² Score, Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) to measure how accurately the model predicts insurance costs.
Overall, this project demonstrates a complete machine learning pipeline including data exploration, preprocessing, regression modeling, and performance evaluation, providing insights into how machine learning can be applied to predict healthcare insurance expenses.
