Predicting Academic Success and Identifying At-Risk Students: A Systematic Review of Data Analytics and Machine Learning Approaches in Higher Education Institutions

Main Article Content

Patrick Ngulube
Mthokozisi Masumbika Ncube

Abstract

This systematic review aimed to assess the application of data analytics and machine learning techniques in Higher Education Institutions (HEIs) to predict student success and identify those at risk of academic difficulty. While previous research has explored these approaches, a comprehensive synthesis of their effectiveness and limitations has been absent. Moreover, addressing issues such as student attrition and inequitable support is crucial given the global commitment to achieving the Sustainable Development Goals (SDGs), particularly SDG 4, which prioritises inclusive and equitable quality education. A systematic literature review was conducted adhering to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, encompassing four major databases to bridge this knowledge gap. Studies were included if they utilised data analytics and machine learning techniques to predict student success or identify at-risk students within higher education contexts. A quality assessment using the Critical Appraisal Skills Programme (CASP) Checklist was employed to ensure the rigour of the included studies. The review uncovered a diverse range of approaches, encompassing traditional methods such as logistic regression and support vector machines and more advanced techniques like ensemble methods and neural networks. These approaches were applied to various data sources, including administrative, learning management systems, and survey data. The findings underscored the potential of data analytics and machine learning to revolutionise higher education by facilitating the early identification of at-risk students, tailoring support services to individual needs, and optimising resource allocation. Consequently, leveraging these technologies, HEIs can make data-driven decisions to enhance student success, improve teaching and learning practices, and contribute to attaining the Sustainable Development Goals.

Downloads

Download data is not yet available.

Article Details

How to Cite
Patrick Ngulube, & Mthokozisi Masumbika Ncube. (2025). Predicting Academic Success and Identifying At-Risk Students: A Systematic Review of Data Analytics and Machine Learning Approaches in Higher Education Institutions. Educational Administration: Theory and Practice, 31(1), 117–134. https://doi.org/10.53555/kuey.v31i1.8447
Section
Articles
Author Biographies

Patrick Ngulube

Department of Interdisciplinary Research and Postgraduate Studies, University of South Africa, Pretoria, South Africa

Mthokozisi Masumbika Ncube

Department of Interdisciplinary Research and Postgraduate Studies, University of South Africa, Pretoria, South Africa