Predicting Students’ Performance Using Support Vector Machine Variants

DOI

10.2991/978-94-6239-634-0_14How to use a DOI?

Keywords

Support Vector Machine (SVM); ν $$\nu $$-Support Vector Machine ( ν $$\nu $$-SVM); Granular Ball Twin Support Vector Machine (GBTSVM); Student Performance; Classification Models; SMOTE (Synthetic Minority Oversampling Technique)

Abstract

Machine learning has been applied across multiple disciplines, for instance, education. Many schools have been using machine learning to improve the educational experience from different perspectives, notably Predicting Student Performance has gained a lot of attention by researchers as it directly influences academic advancement through forecasting future actions, enabling readiness to potential problems, and even minimizing the rate of drop outs by estimating at-risk students. Support Vector Machine (SVM), a widely used learning algorithm known for its high potential, has been employed in different domains including education. Support Vector Machine continues to be a focal point of investigation, and different variants of it have been introduced. Despite the extensive application of SVM in education, its variants remain unexplored in educational contexts. In this paper, some of SVM variants are used to build a classifier that can predict the performance of the students using a publicly available UCI dataset. Given the imbalanced nature of the dataset, we applied SMOTE (Synthetic Minority Over-sampling Technique) and evaluated its influence on the models’ results. This work could be valuable for professionals in education and machine learning who are exploring ways to improve learning efficiency.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Najoua Aafar
AU  - Bouchaib Ferrahi
PY  - 2026
DA  - 2026/04/02
TI  - Predicting Students’ Performance Using Support Vector Machine Variants
BT  - Proceedings of the E-Learning and Smart Engineering Systems (ELSES 2025)
PB  - Atlantis Press
SP  - 173
EP  - 185
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6239-634-0_14
DO  - 10.2991/978-94-6239-634-0_14
ID  - Aafar2026
ER  -