Abstract :

Monitoring And Predicting Student Performance Is Increasingly Critical In Modern Data-driven Educational Environments. Conventional Academic Management Systems Often Function As Static Repositories For Attendance And Grades, Lacking Predictive Insights And Integrated Communication Channels Necessary For Timely Academic Intervention. This Study Proposes A Centralized E-learning And Management Portal Integrated With Machine Learning (ML) Analytics To Proactively Track And Predict Student Outcomes. The Framework Employs A Rolebased Architecture Comprising Admin, Faculty, And Student Dashboards To Facilitate Seamless Data Flow And Engagement. To Classify Student Performance Into Good, Fair, And Poor Categories, Two Predictive Models, Naïve Bayes And XGBoost, Were Implemented And Evaluated. Experimental Results Demonstrate That The XGBoost Model Significantly Outperforms The Baseline, Achieving An Accuracy Exceeding 93%. Beyond Performance Metrics, The System Introduces An Algorithmic Faculty Suggestion Module To Enhance Studentinstructor Alignment. By Synthesizing Predictive Modeling With A Unified Management Interface, This Research Provides A Scalable Solution For Early Academic Intervention, Improved Institutional Transparency, And Personalized Pedagogical Support. Keywords: Student Performance, Machine Learning, XGBoost, Educational Data Mining, Academic Management Systems, Predictive Analytics.

Published:

20-3-2026

Issue:

Vol. 26 No. 3 (2026)

Page Nos:

395-403

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite