A Machine Learning-powered platform for health insurance prediction, built with a mission to empower India's rural population with transparent, accessible, and affordable healthcare insights.
Humara Swasthya is a web-based application that utilises machine learning to predict health insurance premiums. This project eliminates the need for intermediaries by providing a user-friendly interface that allows users—especially those in rural areas—to receive accurate premium estimates based on personal and lifestyle data.
Built as part of the final-year BSc (Computer Science) project at S.I.E.S College of Arts, Science and Commerce (Autonomous), Mumbai, the application supports multilingual usage and is mobile-optimised to reach users in remote areas.
- Provide an intuitive health insurance prediction tool.
- Eliminate fraudulent intermediaries to enhance transparency.
- Offer a multilingual, mobile-friendly solution tailored to rural needs.
- Use machine learning for personalised premium estimation.
- Foster trust and awareness in digital health services.
SDG 3: Good Health and Well-being
By equipping rural and underserved communities with transparent, accessible health-insurance premium predictions, Humara Swasthya directly contributes to Universal Health Coverage and promotes preventative care.
- User Interface: Web pages for registration, prediction, feedback, charts.
- Admin Dashboard: Dataset upload, training control, prediction logs.
- ML Engine: Random Forest & Stacking Regressor models.
- Analytics: Visualisation of user feedback and prediction metrics.
- ✅ Accurate health insurance premium prediction using ML.
- 🌐 Multilingual and mobile-friendly UI.
- 🔐 Secure admin panel for dataset management.
- 📊 Visualised analytics on prediction trends.
- 📄 Export predictions to PDF.
- ⭐ Built-in feedback system for continuous improvement.
| Category | Tools & Frameworks |
|---|---|
| Frontend | HTML5, CSS3, Bootstrap, JavaScript |
| Backend | Python (Flask), Pandas, NumPy |
| ML Models | Random Forest Regressor, Stacking Regressor |
| Visualisation | Matplotlib, Chart.js |
| Deployment | Localhost / Custom server |
-
Clone the repository
git clone https://github.com/your-username/humara-swasthya.git cd humara-swasthya -
Create and activate a virtual environment
python -m venv venv source venv/bin/activate # or venv\Scripts\activate on Windows
-
Install dependencies
pip install -r requirements.txt
-
Run the application
python app.py
-
Open your browser and navigate to
http://127.0.0.1:5000/
Testing of the web application and ML workflows was conducted using Selenium IDE:
- Functional Tests: Automated test suites for all user flows (registration, prediction, feedback submission).
- Regression Tests: Ensured that updates did not break existing functionality.
- Cross-Browser Checks: Verified UI consistency in Chrome, Firefox and Edge.
- Test Reports: Generated HTML reports summarising pass/fail statuses for each test case.
- Integrate with real-time insurance providers for dynamic quotes.
- Add regional language voice-assist.
- Develop an Android app for offline access.
- Extend to include health diagnostics (e.g., sugar levels, BP trends).
- Implement OTP-based login for rural authentication.
Debarjun Chakraborty
Mumbai University
📧 Email: debarjun14@gmail.com
📁 Roll No: TCS2425012
- University of Mumbai Curriculum Guidelines (2024–2025)
- Government of India Health Insurance Schemes
- Ayushman Bharat Portal
- Kaggle Dataset: Health Insurance Costs
- Scikit-learn Documentation
GitHub Repository: https://github.com/DebarjunChakraborty/HumaraSwasthya.git