🎓 Academic Performance Predictor

A web-based Student Performance Prediction System developed using Django, Deep Learning, and Machine Learning to accurately predict whether a student enrolled in a Virtual Learning Environment (VLE) is likely to Pass or Fail. The system analyzes students' academic records, engagement metrics, and learning behaviors to identify at-risk learners early, enabling timely interventions and improving educational outcomes.

📌 Project Overview

This project provides an intelligent prediction system that helps educational institutions identify students who are at academic risk. The system preprocesses educational data, selects important features using Butterfly Optimization, trains multiple Deep Learning models, and predicts student performance.

---

🚀 Features

• 🔐 Student Registration & Login
• 👨‍💼 Admin Dashboard
• 📂 Dataset Upload
• ⚙️ Data Preprocessing
• 🦋 Butterfly Optimization Algorithm for Feature Selection
• 🧠 Multiple Deep Learning Models
• 📊 Performance Comparison
• 📈 Prediction of Student Performance
• 📥 CSV Upload for Prediction
• 📄 Prediction Results (Pass / Fail)

---

🏗️ System Workflow

Dataset Upload
       │
       ▼
Data Preprocessing
       │
       ▼
Feature Selection (Butterfly Optimization)
       │
       ▼
Model Training
       │
       ├── ResNet1D
       ├── Enhanced CNN
       ├── CNN + GRU
       └── CNN + XGBoost
       │
       ▼
Performance Evaluation
       │
       ▼
Prediction

---

🤖 Models Used

• ResNet1D
• Enhanced CNN (ECNN)
• CNN + GRU
• CNN + XGBoost

---

🛠️ Technologies Used

Backend

• Python
• Django

Machine Learning & Deep Learning

• TensorFlow
• Keras
• Scikit-learn
• XGBoost
• NumPy
• Pandas

Frontend

• HTML
• CSS
• Bootstrap
• JavaScript

---

📂 Project Structure

academic-performance-predictor/
│
├── application/
├── static/
├── template/
├── student_performance/
│
├── cnn_feature_extractor.h5
├── cnn_gru_model.h5
├── ecnn_model.h5
├── resnet1d_model.h5
├── xgb_classifier.pkl
│
├── student_encoded.csv
├── sample_test.csv
├── db.sqlite3
├── manage.py
├── requirements.txt
└── README.md

---

⚙️ Installation

Clone the repository

git clone https://github.com/Vinodkumar80744/academic-performance-predictor.git

Navigate to the project

cd academic-performance-predictor

Create a virtual environment

python -m venv venv

Activate the environment

Windows

venv\Scripts\activate

Linux / macOS

source venv/bin/activate

Install dependencies

pip install -r requirements.txt

Run the server

python manage.py runserver

Open your browser and visit:

http://127.0.0.1:8000/

---

📊 Prediction Output

After uploading a test CSV file, the system predicts whether each student is likely to:

• ✅ Pass
• ❌ Fail

---

📷 Screenshots

You can add screenshots of:

• Home Page
• Login Page
• Registration Page
• Admin Dashboard
• Dataset Upload
• Preprocessing
• Model Training
• Performance Comparison
• Prediction Page
• Prediction Result

Store them inside a folder named:

screenshots/

---

🎯 Future Enhancements

• Real-time Student Monitoring
• Explainable AI (XAI)
• Early Risk Detection Dashboard
• Cloud Deployment
• Email Alerts for At-Risk Students
• Additional Deep Learning Models

---

👨‍💻 Author

Vinod Kumar

GitHub: https://github.com/Vinodkumar80744

---

📄 License

This project is developed for educational and research purposes.