Paper Contents
Abstract
This research advances student performance prediction in Educational Data Mining by developing a multi-channel classifier that integrates multiple classification algorithms, including decision trees and Nave Bayes. Utilizing historical academic data from Saurashtra University, the system classifies students based on academic records, attendance, and skill-based assessments while analyzing subject dependencies. A classification smoothing technique is applied to reduce noise and enhance prediction reliability. The proposed model outperforms individual classifiers, achieving an accuracy of 96.39%, as validated through experimental results. By identifying at-risk students and uncovering performance patterns, the system supports personalized academic interventions and informed decision-making. This approach offers a robust framework for educational institutions to optimize learning outcomes and improve student success.
Copyright
Copyright © 2025 Dr. Jitendra Agrawal. This is an open access article distributed under the Creative Commons Attribution License.
