MACHINE LEARNING AS A STRATEGY TO SUPPORT ACADEMIC MANAGEMENT:

Abstract

Student dropout in higher education constitutes a recurring challenge for educational institutions, affecting indicators of student retention, completion, and academic efficiency. This article presents a literature review on the application of Machine Learning techniques for predicting dropout in undergraduate programs, with emphasis on studies that employ Educational Data Mining. National and international works that use classification algorithms—such as Decision Trees, Random Forest, Support Vector Machine, and XGBoost—are discussed, highlighting their performance, the most relevant attributes, and their contributions to academic management. As an illustrative reference, a widely cited case study conducted at the Federal University of Rio Grande (UFRG) is analyzed, demonstrating the potential of these techniques for the early identification of students at risk of dropout. It is concluded that the application of machine learning methods represents a promising strategy to support decision-making systems and institutional student retention policies.