Citation

Law, Theng Jia and Ting, Choo Yee and Ng, Hu and Goh, Hui Ngo and Albert, Quek (2024) A Review of Graduate on Time Prediction. International Journal on Advanced Science, Engineering and Information Technology (IJASEIT), 14 (6). pp. 1957-1966. ISSN 2088-5334

Text Microsoft Word - Theng [127]-AAP.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

In education, predicting students who can graduate on time is difficult. Identifying the significant variables is challenging to predict on-time graduation because human intervention in variable selection is required and time-consuming. It is essential to allow educational institutions to improve student learning experiences by focusing on the significant variables. Researchers have applied various methods, such as Artificial Intelligence, to predict graduation on time. This review has attempted to (i) summarize and compare the diverse methods used by researchers in predicting students who are likely to graduate on time, (ii) identify the gaps and central issues in the existing literature related to predicting on-time graduation, and (iii) establish future potential directions for research in predicting students who are likely to graduate on time, contributing to the ongoing discourse on enhancing educational outcomes. Drawing from an extensive literature analysis across diverse conferences and journals, a notable gap is underscored: the limited focus on predicting graduating on time among postgraduate students. The review addresses issues in learning from small amounts of data and variables, although the researchers demonstrated various techniques for predicting timely graduation, including their strengths and limitations. Future research direction is to consider additional features and improve the performance of predictive models by conducting a comparative analysis of different class treatment methods. As the educational landscape evolves, these considerations are paramount to developing more effective strategies and interventions to ensure timely graduation and foster positive educational outcomes.

Item Type:	Article
Uncontrolled Keywords:	Artificial intelligence; feature selection; machine learning.
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	13 Jan 2025 04:32
Last Modified:	13 Jan 2025 04:32
URII:	http://shdl.mmu.edu.my/id/eprint/13316

Downloads

Edit (login required)