🎓 Student Academic Risk Predictor

A Machine Learning-powered web application that predicts a student's academic risk level based on academic performance, study habits, and lifestyle-related factors.

🚀 Live Demo

Live Application:
https://student-academic-risk-predictor-0vrx.onrender.com

💻 GitHub Repository

https://github.com/tejjas12/Student-Academic-Risk-Predictor

📌 Project Overview

Student academic performance can be influenced by several factors such as attendance, GPA, study hours, assignment completion, backlogs, sleep, class participation, internet access, and part-time work.

This project uses Machine Learning to analyze these factors and predict the student's academic risk level.

🎯 Prediction Levels

• 🟢 Low Risk
• 🟡 Medium Risk
• 🔴 High Risk

The application also provides a simple recommendation based on the predicted risk level.

✨ Key Features

• 📊 Student academic risk prediction
• 🤖 Machine Learning-based prediction
• 🧹 Data preprocessing using a trained preprocessor
• 🟢 Low / 🟡 Medium / 🔴 High risk classification
• 💡 Personalized academic recommendations
• 🌐 Interactive Flask web application
• 📱 User-friendly interface
• ☁️ Live deployment using Render

🧠 Machine Learning

The project uses a trained Machine Learning model with Logistic Regression.

Input Features

• Gender
• Attendance Percentage
• Study Hours per Week
• Previous GPA
• Assignment Submission Rate
• Class Participation Score
• Sleep Hours
• Extracurricular Hours
• Backlog Count
• Internet Access
• Part-time Job

The input data is processed using the saved preprocessor before being passed to the trained model.

🛠️ Technologies Used

• Python
• Pandas
• NumPy
• Scikit-learn
• Joblib
• Flask
• HTML
• CSS
• Git & GitHub
• Render

📂 Project Structure

Student-Academic-Risk-Predictor/
│
├── Dataset/
├── Model/
│   ├── student_risk_model.pkl
│   └── student_risk_preprocessor.pkl
│
├── Notebooks/
├── Static/
│   └── style.css
│
├── templates/
│   └── index.html
│
├── app.py
├── requirements.txt
└── README.md

⚙️ How It Works

Student Input
      ↓
Data Preprocessing
      ↓
Trained ML Model
      ↓
Risk Prediction
      ↓
Low / Medium / High
      ↓
Academic Recommendation

▶️ Run the Project Locally

1. Clone the repository

git clone https://github.com/tejjas12/Student-Academic-Risk-Predictor.git
cd Student-Academic-Risk-Predictor

2. Create and activate a virtual environment

python -m venv student-risk
source student-risk/bin/activate

3. Install dependencies

pip install -r requirements.txt

4. Run the Flask application

python app.py

Then open the local address shown by Flask in your browser.

☁️ Deployment

The application is deployed as a Python Flask web service using Render.

The GitHub repository is connected to Render, so when changes are pushed to the main branch, Render can automatically build and deploy the latest version.

👨‍💻 Author

Tejas Patil

Data Science & Machine Learning Project

📄 License

This project is created for educational and academic purposes.

©️ 2026 Tejas Patil. All Rights Reserved.

⭐ Acknowledgement

This project was developed as part of my learning journey in Data Science, Machine Learning, Python, Flask, and web application deployment.