ai-powered-student-insights

🎓 IntelliDash - AI-Powered Student Insights

Track. Analyze. Improve.

An intelligent dashboard that transforms student data into actionable insights through AI-powered analytics and predictive modeling.

Features • Demo • Installation • Usage • API • Contributing

---

📋 Table of Contents

• Overview
• Features
• Tech Stack
• Project Structure
• Installation
• Usage
• API Documentation
• Machine Learning Models
• Screenshots
• Contributing
• License

---

🌟 Overview

IntelliDash is a comprehensive educational analytics platform that helps educators and institutions:

• 📊 Visualize student performance trends and patterns
• 🎯 Predict academic outcomes using machine learning
• 🔍 Identify at-risk students early
• 📈 Track learning metrics and engagement
• 💡 Make data-informed educational decisions

The platform combines interactive data visualizations with two AI models: a Random Forest Classifier for dropout prediction and a Linear Regression Model for performance forecasting.

---

✨ Features

📊 Interactive Dashboard

• Real-time Data Visualization - Dynamic charts using Chart.js
• Student Performance Table - Paginated, searchable data grid
• Individual Student Profiles - Detailed modal views with quiz breakdowns
• Responsive Design - Works seamlessly on desktop, tablet, and mobile

🤖 AI-Powered Predictions

1. Performance Prediction (Linear Regression)

Predicts academic performance based on:

• 📚 Hours Studied
• 📊 Previous Scores
• ⚽ Extracurricular Activities
• 😴 Sleep Hours
• 📝 Papers Practiced

2. Dropout Risk Analysis (Random Forest)

Identifies at-risk students using:

• Age & GPA
• Attendance Rate
• Assignment Submission Rate
• Quiz Completion Rate
• Learning Platform Engagement
• Login Frequency

📈 Visualizations

• Donut Charts - Average class scores across subjects
• Bar Charts - Grade distribution histograms
• Student-specific Charts - Individual quiz performance
• Color-coded Insights - Performance level indicators

🎨 Modern UI/UX

• Glassmorphism design with gradient accents
• Smooth animations and transitions
• Blue/purple theme with high contrast
• Accessible and intuitive interface

---

🛠 Tech Stack

Frontend

• HTML5 - Semantic markup
• CSS3 - Modern styling with gradients, glassmorphism
• JavaScript (ES6+) - Dynamic interactions
• Chart.js - Data visualizations

Backend

• Python 3.9+ - Core language
• Flask - Web framework
• Flask-CORS - Cross-origin resource sharing

Machine Learning

• NumPy - Numerical computations
• Scikit-learn - ML models (Random Forest, Linear Regression)
• Pickle - Model serialization

Data

• CSV - Student performance datasets
• Pandas - Data processing (training phase)

---

📁 Project Structure

ai-powered-student-insights/
├── backend/
│   ├── data/
│   │   ├── Student_Performance.csv           # Raw performance data (10,000+ records)
│   │   ├── cleaned_student_data.csv          # Processed student data
│   │   └── student_data_with_quiz_scores.csv # Quiz-enriched dataset
│   ├── main.py                                # Dropout prediction API (Port 5000)
│   ├── regression-main.py                     # Performance prediction API (Port 5001)
│   ├── regression-training-script.ipynb       # Model training notebook
│   ├── regression_model.pkl                   # Trained regression model
│   └── student_dropout_random_forest.pkl      # Trained classifier model
├── index.html                                 # Main dashboard page
├── styles.css                                 # Styling and themes
├── visualization.js                           # Frontend logic and API calls
├── PREDICTION_INTEGRATION.md                  # Integration documentation
└── README.md                                  # This file

---

🚀 Installation

Prerequisites

• Python 3.9 or higher
• pip package manager
• Modern web browser (Chrome, Firefox, Safari, Edge)

Step 1: Clone the Repository

git clone https://github.com/rehanxt5/ai-powered-student-insights.git
cd ai-powered-student-insights

Step 2: Create Virtual Environment

python3 -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

Step 3: Install Dependencies

pip install flask flask-cors numpy scikit-learn pandas

Step 4: Verify Model Files

Ensure the following model files exist:

ls backend/regression_model.pkl
ls backend/student_dropout_random_forest.pkl

---

💻 Usage

Starting the Backend Servers

1. Performance Prediction Server (Port 5001)

python backend/regression-main.py

Server will run on: http://localhost:5001

2. Dropout Prediction Server (Port 5000)

python backend/main.py

Server will run on: http://localhost:5000

Opening the Frontend

Option 1: Direct File Open

open index.html

Option 2: Local HTTP Server (Recommended)

python3 -m http.server 8000
# Navigate to http://localhost:8000

---

🔌 API Documentation

Performance Prediction API

Endpoint: POST http://localhost:5001/predict

Request Body:

{
  "features": [
    7,    // Hours Studied (0-24)
    85,   // Previous Scores (0-100)
    1,    // Extracurricular Activities (0=No, 1=Yes)
    8,    // Sleep Hours (0-24)
    5     // Papers Practiced (0-100+)
  ]
}

Response:

{
  "predicted_performance": 77.88857895121386
}

Health Check:

GET http://localhost:5001/health

---

Dropout Prediction API

Endpoint: POST http://localhost:5000/predict

Request Body:

{
  "age": 18,
  "gpa": 3.5,
  "gender_encoded": 1,
  "attendance_rate": 85.5,
  "assignment_submission_rate": 90.0,
  "quiz_completion_rate": 88.0,
  "time_spent_on_learning_platform": 120.5,
  "login_frequency": 15
}

Response:

{
  "prediction": 0,  // 0 = No dropout risk, 1 = At risk
  "features": { /* echo of input */ }
}

Health Check:

GET http://localhost:5000/health

---

🤖 Machine Learning Models

1. Linear Regression - Performance Predictor

Purpose: Predict student performance index (0-100)

Features (5):

1. Hours Studied
2. Previous Exam Scores
3. Extracurricular Participation
4. Sleep Hours
5. Practice Papers Completed

Training Data: Student_Performance.csv (10,000+ records)

Normalization: Z-score standardization

Model File: regression_model.pkl

---

2. Random Forest Classifier - Dropout Prediction

Purpose: Identify students at risk of dropping out

Features (8):

1. Age
2. GPA
3. Gender (encoded)
4. Attendance Rate
5. Assignment Submission Rate
6. Quiz Completion Rate
7. Time on Learning Platform
8. Login Frequency

Training Data: cleaned_student_data.csv

Model File: student_dropout_random_forest.pkl

---

🎨 Screenshots

Dashboard Overview

• Clean, modern interface with gradient design
• Real-time data loading and visualization
• Interactive charts and tables

Performance Predictor

• User-friendly form with validation
• Instant AI predictions
• Color-coded results:
  • 🌟 90-100: Excellent (Green)
  • ✅ 75-89: Good (Blue)
  • ⚠️ 60-74: Moderate (Orange)
  • 🔴 <60: Needs Support (Red)

Student Details Modal

• Individual quiz scores breakdown
• Performance metrics
• Visual progress indicators

---

🧪 Testing the APIs

Test Performance Prediction

curl -X POST http://localhost:5001/predict \
  -H "Content-Type: application/json" \
  -d '{"features": [7, 85, 1, 8, 5]}'

Expected Output:

{"predicted_performance": 77.88857895121386}

Test Dropout Prediction

curl -X POST http://localhost:5000/predict \
  -H "Content-Type: application/json" \
  -d '{
    "age": 18,
    "gpa": 3.5,
    "gender_encoded": 1,
    "attendance_rate": 85.5,
    "assignment_submission_rate": 90.0,
    "quiz_completion_rate": 88.0,
    "time_spent_on_learning_platform": 120.5,
    "login_frequency": 15
  }'

---

🐛 Troubleshooting

Issue: Port Already in Use

# Kill process on port 5001
lsof -ti:5001 | xargs kill -9

# Kill process on port 5000
lsof -ti:5000 | xargs kill -9

Issue: CORS Errors

• Ensure flask-cors is installed
• Verify CORS(app) is called in Flask apps

Issue: Model Not Found

# Check model files exist
ls -la backend/*.pkl

Issue: Module Not Found

# Reinstall dependencies
pip install flask flask-cors numpy scikit-learn pandas

---

🎯 Use Cases

For Educators

• 📊 Monitor class performance trends
• 🔍 Identify struggling students early
• 📈 Track engagement metrics
• 💡 Make informed intervention decisions

For Administrators

• 📉 Reduce dropout rates
• 📊 Analyze program effectiveness
• 🎯 Allocate resources efficiently
• 📈 Improve student outcomes

For Researchers

• 🔬 Study learning patterns
• 📊 Validate educational interventions
• 🤖 Experiment with ML models
• 📈 Publish data-driven insights

---

🔮 Future Enhancements

• User authentication and role-based access
• Real-time data updates with WebSockets
• Export reports as PDF/Excel
• Email alerts for at-risk students
• Mobile app (React Native)
• Integration with LMS platforms
• Advanced ML models (Deep Learning, XGBoost)
• A/B testing framework
• Multi-language support
• Dark mode theme

---

🤝 Contributing

Contributions are welcome! Please follow these steps:

1. Fork the repository
2. Create a feature branch

   git checkout -b feature/AmazingFeature

3. Commit your changes

   git commit -m 'Add some AmazingFeature'

4. Push to the branch

   git push origin feature/AmazingFeature

5. Open a Pull Request

---

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

---

👨‍💻 Author

Rehan

• GitHub: @rehanxt5
• Repository: ai-powered-student-insights

---

🙏 Acknowledgments

• Chart.js - Beautiful, responsive charts
• Flask - Lightweight web framework
• Scikit-learn - Machine learning toolkit
• Educational Data Community - Inspiration and datasets

---

📞 Support

For questions or issues:

• 🐛 Open an Issue
• 💬 Start a Discussion

---

⭐ Star this repo if you find it helpful!

Made with ❤️ and ☕ by Rehan