Citation

Ahmad, Intan Khairina Adlina and Ting, Choo Yee and Goh, Hui Ngo and Quek, Albert and Cham, Chin Leei (2024) Predicting graduate-on-time using machine learning. In: 3rd International Conference on Computer, Information Technology, and Intelligent Computing (CITIC2023), 26–28 July 2023, Virtual Conference.

Full text not available from this repository.

Abstract

Predicting academic performance is a crucial task for educators and institutions because it enables the early identification of at-risk students and helps provide targeted interventions to improve their academic outcomes. Existing research often focuses on predicting academic performance using CGPA; less work, however, has used graduate-on-time (GOT) as a dependent variable. In this study, the objective was to (i) determine the optimal set of features that influence the predictions, (ii) construct a predictive model that predicts academic performance focusing on graduating on time (GOT). The data, obtained from the Ministry of Higher Education Graduates Tracer Study, contains information about graduated MMU students. It has 2382 entries and 95 columns, which include records of Graduate On Time (GOT), Cumulative Grade Point Average, Estimated Terms, and many more. This paper employed machine learning techniques such as Gaussian Naive Bayes, Decision Tree, Logistic Regression, Random Forest, Gradient Boosting, Stacking Ensemble methods and Multilayer Perceptron. The results showed that among all the techniques, the Ensemble method model exhibits the highest accuracy (84.03%), precision (84.86%), and recall (90.57%), as well as a f1-score of 87.62%. The Random Forest model and the Logistic Regression model both have a f1-score of 84%, which comes in second place after the strong results of the Ensemble technique.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	01 Aug 2024 06:26
Last Modified:	01 Aug 2024 06:26
URII:	http://shdl.mmu.edu.my/id/eprint/12725

Downloads

Edit (login required)