Abstract
This systematic literature review aims to identify the recent research trend, most studied factors, and methods used to predict student academic performance from 2015 to 2021. The PRISMA framework guides the study. The study reviews 58 out of 219 research articles from Lens and Scopus databases. The findings indicate that the research focus of current studies revolves around identifying factors influencing student performance, data mining (DM) algorithms performance, and DM related to e-Learning systems. It also reveals that student academic records and demographics are primary aspects that affect student performance. The most used DM approach is classification and the Decision Tree classifier is the most employed DM algorithm.
Highlights
Student academic performance is a significant aspect in determining educational success at all levels [1, 2, 3]
Regression analysis, discriminant analysis, and cluster analysis are examples of classical statistics approaches used in this area [9]. Artificial intelligence methods such as Backpropagation, Support Vector Regression, Gradient Boosting Classifier [10], Bayesian Classifier, Artificial Neural Network, and Decision Tree [11] are later employed. The latter involves a mix of advanced statistical methods and artificial intelligence heuristics and has contributed to the growth of educational data mining (EDM), which adds to our understanding of how to predict student academic performance [12, 13, 14, 15, 16]
From the 58 selected articles, this SLR extracted three categories of research focus. These include identifying factors influencing student performance, DM algorithms performance, and DM related to e-Learning systems
Summary
Student academic performance is a significant aspect in determining educational success at all levels [1, 2, 3]. Regression analysis, discriminant analysis, and cluster analysis are examples of classical statistics approaches used in this area [9] Artificial intelligence methods such as Backpropagation, Support Vector Regression, Gradient Boosting Classifier [10], Bayesian Classifier, Artificial Neural Network, and Decision Tree [11] are later employed. The latter involves a mix of advanced statistical methods and artificial intelligence heuristics and has contributed to the growth of educational data mining (EDM), which adds to our understanding of how to predict student academic performance [12, 13, 14, 15, 16]. EDM research studies [17] applied data mining (DM) techniques to data obtained from diverse educational systems to improve the quality of education [18] Such mining is significant as it enables educators to take necessary interventions to achieve optimal student performance [19]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Emerging Technologies in Learning (iJET)
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
