ARCHIVES
VOL. 13, ISSUE 1 (2026)
Machine learning in education: A comparative study on predicting students academic performance
Authors
Aparna Shivaji Gaikwad
Abstract
This study looks into how machine learning methods
can be used to guess how well students will do in school by looking at things
like test scores, attendance, and how engaged they are in school. We used and
compared four well-known algorithms: Decision Tree, Random Forest, Support Vector
Machine (SVM), and K-Nearest Neighbour (KNN) to see which ones worked best. The
study shows that Random Forest gave the most reliable outcomes, pointing out
that attendance and past scores are important factors that affect success. The
results show that predictive analytics can help teachers find students who are
likely to do poorly in school and come up with specific ways to help them. This
study shows that data-driven methods are becoming more and more useful in
education to help students learn better and help schools make better decisions.
Download
Pages:235-238
How to cite this article:
Aparna Shivaji Gaikwad "Machine learning in education: A comparative study on predicting students academic performance". International Journal of Multidisciplinary Research and Development, Vol 13, Issue 1, 2026, Pages 235-238
Download Author Certificate
Please enter the email address corresponding to this article submission to download your certificate.