Edu Net: Integrated Platform for Student Progress and Educator Insights

Abstract

The rapid growth of digital education has increased the need for intelligent systems that can effectively manage academic activities while providing meaningful insights into student performance. This work presents an AI-enabled centralized collaborative learning portal designed to connect students, teachers, and administrators within a single platform. The system integrates machine learning techniques to analyse academic data and predict student performance based on historical marks. Two algorithms, Naïve Bayes and XGBoost, are implemented and evaluated to determine their effectiveness in classification tasks. The dataset is processed and used to train predictive models, which are then applied to new student records for performance estimation. Evaluation metrics such as accuracy, precision, recall, and F1-score are used to assess model performance. Experimental results indicate that XGBoost achieves superior accuracy, exceeding 93%, compared to other methods. The platform also provides role-based dashboards that support academic management activities such as attendance tracking, assignment handling, material sharing, and communication. Teachers can monitor student progress and provide feedback, while students can access learning resources and performance reports. The system enhances transparency and supports datadriven decision-making in educational institutions. Overall, the proposed solution offers an efficient and scalable approach to academic monitoring and performance prediction.