EXPLORING THE EFFECTIVENESS OF AI POWERED PERSONALIZED LEARNING SYSTEMS ON STUDENT ACADEMIC PERFORMANCE IN HIGHER EDUCATION

Abstract

This study aims to explore the effectiveness of an Artificial Intelligence (AI)-based personalized learning system on student academic performance in higher education. The approach used is systematic narrative review against literature obtained from reputable databases, namely Scopus, Web of Science, ERIC, and Google Scholar. The synthesis of findings shows that AI-based adaptive learning systems tend to improve academic outcomes, engagement, and student retention through adjusting content, speed, and learning methods to individual needs.However, the effectiveness of AI personalization is influenced by various factors. Moderating factors, including student characteristics (e.g., motivation and prior knowledge), the AI ​​strategies implemented (such as adaptive feedback and intelligent tutoring), and the institutional context (including technology infrastructure and faculty support). The review also identified research gaps, such as the limitations of longitudinal studies, variations in effectiveness across disciplines, and the lack of integration of a robust theoretical framework for learning.This research strengthens the theoretical basis of adaptive learning and provides practical recommendations for universities to implement AI strategically and evidence-based. Overall, the findings suggest that AI can improve the quality of learning, but successful implementation depends on attention to contextual factors and appropriate system design.