Loading...
An Ensemble-based Machine Learning Approach to Predicting Students' Performance
Citations
Altmetric:
Abstract
In this research, advanced machine learning models are investigated for their ability to predict student academic performance, focusing on key features termed "important features." The study thoroughly compares data mining techniques to categorise student performance and predict grades, utilising a diverse array of classifiers, including Bayes networks, logistic regression, random forests, support vector machines, and decision trees. Additionally, ensemble methods like voting were employed to enhance classifier performance. Exploring an ensemble-based machine learning method to predict students' performance is driven by the desire to improve learning. Notably, the results showed exceptional performance by the voting classifier, achieving impressive accuracy rates of 68% in the online dataset and 92% in the local dataset compared to other classifiers. This research significantly contributes to the evolution of predictive modelling within educational settings, offering insights into the comparative effectiveness of different classifiers and ensemble approaches. By identifying important features and exploring ensemble methods, the study provides valuable insights for personalised education, resource allocation, and informed decision-making in educational policies. Educators and institutions of learning can leverage these findings to develop targeted interventions and support systems tailored to individual student needs, ultimately promoting academic success.
PCF11 Plus: Beyond the Forum
Sub-Theme: Gender, technology and innovation in open education
Paper ID: 6226
Subject
Country
Region
DOI
Collections
Files
Loading...
PDF
Adobe PDF, 348.62 KB
Link
Date
2025-09
Author
ORCID
Corporate Author
Editor
Publisher
Commonwealth of Learning (COL)