Health Insurance Cost Predictor Using Machine Learning

Health Insurance Cost Predictor

A simple project based on Health Insurance Premium Prediction System which is developed using machine learning to help users estimate their insurance premiums accurately. This project focuses on applying predictive modeling techniques to calculate health insurance costs based on user data, making it easier for individuals and companies to understand premium calculations.

The system uses two machine learning models combined with smart prediction methods to provide highly accurate results, achieving an impressive R² score of up to 99.7%. By analyzing various factors such as age, gender, BMI, smoking habits, and other health indicators, the models predict premiums effectively and reliably.

This project is not just a technical exercise but also a practical learning tool for students, developers, and anyone interested in machine learning applications in real-world domains like insurance, finance, and healthcare. It demonstrates how data-driven methods can improve decision-making and reduce errors in premium estimation.

The system is designed to be user-friendly and interactive, allowing users to input their personal and health-related data easily. Once the information is entered, the machine learning models process the data and generate instant premium predictions.

By using this Health Insurance Premium Prediction System, students can learn:

• How to apply machine learning algorithms to real-life financial or healthcare problems

• How to integrate predictive models into a web application

• How to evaluate model performance using metrics like R² score

• How real-world applications benefit from data-driven insights and predictions

This project serves as both an educational resource and a practical application, helping users understand how insurance premiums are calculated while giving students hands-on experience with machine learning, data analysis, and predictive modeling.

Project Details

Download New Real Time Projects :-Click here

About the Project

This project started as a standard regression task but evolved into a dual-model powerhouse after deep error analysis revealed age as a major factor in prediction variance.

Core Strategy

•  Young Model (Age ≤ 25) → Linear Regression
•  Older Model (Age > 25) → XGBoost Regressor
• Genetical Risk Factor: Game-changing feature that boosted overall prediction reliability.

Key Results

Young Users (Age ≤ 25)

• Model: Linear Regression + Genetical Risk
• Accuracy (R²): ~0.99 Train/Test

Older Users (Age > 25)

• Model: XGBoost + Genetical Risk
• Accuracy (R²): ~0.997 Train/Test/CV

Tech Stack

• Frontend: Streamlit
• ML Models: Linear Regression, XGBoost
• Tuning: GridSearchCV, RandomizedSearchCV
• Libraries: NumPy, pandas, scikit-learn, XGBoost
• Visualization: Seaborn, Matplotlib

Available Features

This Health Insurance Premium Prediction System comes with a comprehensive set of features to provide accurate and reliable premium predictions:

• ML Model Training & Prediction Scripts – The system includes scripts that allow users to train machine learning models from scratch and make premium predictions for new data. This helps students understand the full workflow of predictive modeling.

• Advanced Feature Engineering (Genetical Risk) – The project incorporates advanced feature engineering techniques, including factors like genetic risk, which improves the accuracy and relevance of premium predictions.

• Pre-Trained Model Notebooks for Both Age Groups – Jupyter Notebooks with pre-trained models are included for different age groups, allowing users to test predictions without retraining and understand how model performance varies with different datasets.

• Ready-to-Use Streamlit Web App – A fully functional Streamlit-based web application is provided for real-time premium prediction. Users can enter their details and get instant results in a simple and interactive interface.

• Residual & Accuracy Visualizations – Visualizations such as residual plots, accuracy charts, and performance graphs are included to help users analyze model accuracy and understand where predictions might vary.

• Test Datasets Included (.xlsx) – Sample test datasets in Excel format are provided to evaluate and validate predictions, giving users hands-on experience with real-world data.

• SourceOfWork.pdf – A complete methodology and implementation breakdown is included, explaining the project workflow, model selection, feature engineering, and prediction logic in detail.