EduLytics AI: Student Performance Analyzer

📌 Project Overview

EduLytics AI is an intelligent student performance analysis platform designed to help educators and administrators unlock actionable insights from student data. By leveraging Machine Learning (K-Means Clustering and Random Forest Classifiers), the system identifies at-risk students, categorizes performance levels, and predicts potential outcomes.

❓ Key Questions Answered

• Who are the top-performing students and who needs support?
• How are students grouped based on their academic patterns? (High Achievers vs. Developing vs. Needs Support)
• What is the overall pass rate and subject-wise performance?
• Can we predict student success based on attendance and historical data?

💡 Key Insights

• Performance Clustering: Students fall into three distinct clusters, allowing for targeted interventions.
• Subject Correlation: Strong performance in core subjects often correlates with higher overall attendance.
• Predictive Accuracy: The Random Forest model achieves ~92% accuracy in predicting pass/fail outcomes based on early indicators.

---

🛠️ Tech Stack

• Backend: Django 5.0 (Python)
• Data Science: Pandas, Scikit-learn, NumPy
• Frontend: Bootstrap 5, Chart.js, HTML5/CSS3
• Database: SQLite (Dev) / PostgreSQL (Prod ready)
• PDF Generation: xhtml2pdf

---

📂 Repository Structure

student-performance-analysis/
│
├── data/
│   └── student_marks.csv       # Dataset used for analysis
│
├── notebooks/
│   └── student_performance_analysis.ipynb  # Jupyter Notebook with ML logic
│
├── analyzer/                   # Django App Source Code
│   ├── ml_engine.py            # Core ML Logic Class
│   └── views.py                # View Controllers
│
├── templates/                  # HTML Templates
│   └── analyzer/               # Dashboard, Analysis, Reports
│
├── manage.py                   # Django Entry Point
└── README.md                   # Project Documentation

---

📸 System Components

1. Home Page / Landing

Introduction to the platform and value proposition.

2. Login & Authentication

Secure user access.

3. Registration

User onboarding flow.

4. Analytics Dashboard

Central hub for recent uploads, key metrics, and AI insights.

5. Analysis Results

Detailed breakdown of student performance including clustering and charts.

---

🚀 How to Run the Project

Prerequisites

• Python 3.10+
• Pip

Setup Steps

1. Clone the repository

   git clone https://github.com/AgreementMudau05/EduLytics-AI.git
   cd EduLytics-AI

2. Install Dependencies

   pip install django pandas scikit-learn numpy xhtml2pdf

3. Run Migrations

   python manage.py migrate

4. Start the Server

   python manage.py runserver

   Visit http://127.0.0.1:8000 in your browser.

Running the Notebook

To explore the data analysis logic interactively:

cd notebooks
jupyter notebook

---

📝 License

This project is open-source and available under the MIT License.