Welcome to the InfoSci Platform
The Effect of Imbalanced Classes on Students' Academic Performance Prediction: An Evaluation Study

The Effect of Imbalanced Classes on Students' Academic Performance Prediction: An Evaluation Study

Osama Mohammed El-Deeb, Walid Elbadawy, Doaa Saad Elzanfaly
Copyright: © 2022 |Volume: 18 |Issue: 1 |Pages: 17
ISSN: 1548-3673|EISSN: 1548-3681|EISBN13: 9781799893868|DOI: 10.4018/IJeC.304373
Cite Article Cite Article

MLA

El-Deeb, Osama Mohammed, et al. "The Effect of Imbalanced Classes on Students' Academic Performance Prediction: An Evaluation Study." IJEC vol.18, no.1 2022: pp.1-17. http://doi.org/10.4018/IJeC.304373

APA

El-Deeb, O. M., Elbadawy, W., & Elzanfaly, D. S. (2022). The Effect of Imbalanced Classes on Students' Academic Performance Prediction: An Evaluation Study. International Journal of e-Collaboration (IJeC), 18(1), 1-17. http://doi.org/10.4018/IJeC.304373

Chicago

El-Deeb, Osama Mohammed, Walid Elbadawy, and Doaa Saad Elzanfaly. "The Effect of Imbalanced Classes on Students' Academic Performance Prediction: An Evaluation Study," International Journal of e-Collaboration (IJeC) 18, no.1: 1-17. http://doi.org/10.4018/IJeC.304373

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Imbalanced classes in data mining have more challenges in the educational data mining field. This is because most of the datasets collected from educational records are imbalanced by nature. Some classes dominate others and cause bias predictions. This paper studies the effects of the imbalanced classes on the performance of seven different classifiers, which are J48, Random Forest, k-Nearest Neighbors, Naïve Bayes, Random Tree, SVM, and Linear Regression. Moreover, the effectiveness of the SMOTE technique for handling imbalanced data is evaluated against these classifiers. This will be done through the proposal of an early predictive model that predicts student’s academic performance and recommends their appropriate department in a multi-disciplinary institute. According to our results, the Random Forest technique is the best and has the highest level of accuracy is 94.585%.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.