Amina Maqsood@aminaawan742

This project aims to predict yearly medical insurance premium costs using machine learning algorithms based on individual health and demographic data. Leveraging a dataset of nearly 1,000 entries, it incorporates various health factors such as age, BMI, existing medical conditions, and lifestyle habits to build an accurate prediction model. Through data preprocessing, visualization, and model training using libraries like pandas, seaborn, and scikit-learn, this project demonstrates the real-world application of AI in the healthcare and insurance domain. The model helps users understand how different health parameters affect insurance premiums, encouraging informed financial planning and healthier lifestyle choices. This solution has the potential to enhance transparency in insurance pricing and empower better decision-making. Results & Visualizations: Feature Impact Bar Chart Shows how average premium varies across features like Gender, Smoking Status, and Exercise. Future Scope Deploy it as a web application using Streamlit or Flask so users can input values and get predictions. Add more granular health data like cholesterol, blood pressure, and stress levels. Implement explainable AI (XAI) tools like SHAP or LIME to explain individual predictions. Train on larger, real-world datasets from hospitals or insurance providers. Conclusion: This project showcases the impact of machine learning in healthcare decision-making. By predicting insurance premiums based on user health profiles, it helps users understand cost drivers and promotes healthier living. While the model provides a valuable estimate, it should complement, not replace, professional advice.