RESUMOSchool dropout is a matter of great relevance due to its significantsocial, economic, and personal repercussions. This study focuseson the issue of course attrition in higher education, a significantcontributing factor to dropout rates. Here, we present the analysisof 216 results, obtained from combining nine different preprocessingand three sampling methods, as well as eight machine learningalgorithms, based on student attendance, grades, and completion ofevaluative activities, extracted from the MOODLE learning environment.The results of this study, obtained through implicit analysis,reveal a combination of methods capable of identifying studentattrition with a recall of 95.31% and accuracy of 92.67% in just 25%of semester’s duration.