The Application of Machine Learning in Student Performance Prediction in Higher Education Institutions: A Systematic Literature Review

The purpose of this review is the application of machine learning techniques in predicting student performance. We systematically review the trends, commonly used algorithms and their potential problems in this field. This review includes stages of planning (search objectives, research questions, inclusion and exclusion criteria), searching, selection, and literature consolidation. In terms of algorithms, although techniques such as Decision Tree, Random Forest, and Support Vector Machines (SVMs) have been widely used for student performance prediction, they still have some issues of data quality, accuracy, performance and data security when analysis complex data in educational settings. This review focuses on these challenges and suggests possible future research directions.