EduSense AI - Intelligent Student Performance Prediction & Academic Analytics System

EduSense AI is an intelligent student performance prediction and academic analytics system designed to help educational stakeholders understand and monitor student academic performance using machine learning and data-driven analytics.

The system uses a trained Linear Regression machine learning model to estimate a student's Performance Index based on academic and lifestyle-related factors including hours studied, previous scores, extracurricular activities, sleep hours, and sample question papers practiced.

EduSense AI provides separate role-based experiences for Administrators, Faculty, Students, and Parents. Administrators can manage users and view system-wide analytics, faculty can manage students and create predictions, students can view their own academic performance and generate predictions, and parents can monitor the performance of their linked children through a read-only portal.

The application stores academic records and prediction results as historical data, allowing users to review prediction history and performance trends over time. It also provides analytics dashboards, academic insights, personalized recommendations, and downloadable PDF performance reports.

The machine learning prediction is performed on the backend using the saved trained model, while the React frontend provides the interactive user interface.

The project is designed as a final-year academic demonstration system and uses a synthetic/illustrative student performance dataset. Model performance is therefore dataset-specific and predictions should be treated as estimates rather than guaranteed future outcomes.

1. Administrator logs into the system and manages users, students, faculty, parents, predictions, and system analytics.
2. Faculty logs in to view students, review academic information, create performance predictions, analyze student trends, and generate reports.
3. Students log in to view their dashboard, academic performance, prediction history, recommendations, and profile.
4. Students can enter academic factors and generate a machine learning based performance prediction.
5. Parents can log in to monitor the academic performance of their linked children.
6. Users can view prediction history and performance trends through interactive analytics.
7. The system generates academic insights and recommendations based on available student performance data.
8. Authorized users can generate and download PDF performance reports.
9. Administrators can use Django Admin to manage system data and review historical prediction records.
10. Developers can use the REST API and Swagger documentation to test and integrate system functionality.

Windows 10/11 or compatible operating system
Python 3.13 or compatible Python version
Node.js 22.x or compatible Node.js version
npm
Visual Studio Code or any suitable code editor
Existing Python virtual environment
Python dependencies from backend/requirements.txt
Node dependencies from frontend/package.json
SQLite
Modern web browser
Minimum 4 GB RAM recommended
Internet connection required initially if dependencies need to be downloaded