Published Paper Details:

Student attrition, the premature withdrawal of students from educational programs, poses a significant challenge to higher education institutions globally. This research This study examines the application of predictive analytics, leveraging machine learning and data mining techniques, to identify at-risk students and implement timely interventions aimed at improving retention and academic success. We systematically review existing literature on predictive learning analytics (PLA) in higher learning, examining various methodological approaches, predictive models, and the factors influencing student attrition. The analysis highlights the advantages and disadvantages of various prediction models, emphasizing the need for responsible AI frameworks to address ethical concerns and ensure equitable outcomes. Furthermore, we discuss the integration of PLA with motivational interventions and the role of data warehousing in facilitating data-driven decision-making for enhanced student support. Finally, we identify key research gaps and propose future directions for refining PLA strategies to create more effective and inclusive learning environments