A SYSTEMATIC REVIEW OF ANALYZING STUDENT PERFORMANCE USING MACHINE LEARNING

Abstract

Student performance analysis is a prime component of educational data mining and outcome-based education. Educational Data Mining and Machine Learning techniques have received significant attention to predict student performance and support data-driven decision-making in higher education. Previous work has applied artificial intelligence (AI) and machine learning (ML) models to predict grades, improve learning outcomes and identify at-risk students. The study demonstrates the potential of advanced Machine Learning techniques to improve data-driven decision-making in education. This paper presents a comprehensive review of research on student performance analysis. We describe the review of previous work, methodologies and algorithms used in previous studies, and identify gaps in current practice. Based on this review, we introduce new findings using ensemble learning methods and transformer-based models applied to real and synthetic student datasets and define the significant gaps including small dataset limitations, lack of explainability, minimal remedial interventions, and ethical concerns.