A Streamlit-based web application that helps Indian students estimate their chances of getting admitted into top Ivy League graduate programs. Powered by a regression model trained on historical admission data, the app provides real-time predictions based on academic credentials and research experience.
This application is designed for students planning to pursue graduate studies abroad. Built to support Jamboree’s vision of helping students make data-informed decisions, the app takes in user inputs such as GRE score, GPA, TOEFL, research experience, and more—then returns the predicted probability of admission to top-tier universities.
✅ Predict graduate admission chances using:
- GRE Score (out of 340)
- TOEFL Score (out of 120)
- University Rating (1 to 5)
- Statement of Purpose (SOP) strength (1 to 5)
- Letter of Recommendation (LOR) strength (1 to 5)
- Undergraduate GPA (out of 10)
- Research Experience (Yes/No)
✅ Simple and clean UI built with Streamlit
✅ Instant prediction results
✅ Designed for Indian applicants targeting Ivy League universities
(Insert screenshot of your app UI here for visual impact)
- 🐍 Python
- 📊 Pandas, NumPy
- 📈 Scikit-learn, Statsmodels
- 🌐 Streamlit
- 📦 Joblib (for model serialization)
- Clone the repository
git clone https://github.com/yugmint/Admission_prediction_app.git- Run the Streamlit app
streamlit run admission_predict_app.pyThis app uses a Linear Regression model trained on a Kaggle dataset of graduate applications. The model has been evaluated using:
- R² Score
- Adjusted R²
- MAE and RMSE
It captures up to 82% variance in admission outcomes based on academic and research indicators.
- Deploy using Docker or Hugging Face Spaces
- Add more features like work experience, extracurriculars
- Enable batch predictions for counselors
- Visual explanation of predictions (e.g., SHAP values)
Yugendra Salunke Data Engineer | NLP & ML Enthusiast 📧 [email protected] 🌐 GitHub | LinkedIn
This project is licensed under the MIT License.
Thanks to Kaggle for the admission dataset and Streamlit for making deployment so seamless.