Exploiting Academic Records for Predicting Student Drop Out: a case study in Brazilian higher education

Students’ drop out is a major concern of the Brazilian higher education institutions as it may cause waste of resources and decrease graduation rates. The early detection of students with high probability of dropping out, as well as understanding the underlying causes, are crucial for defining more effective actions toward preventing this problem. In this article, we cast the drop out detection problem as a classification problem. We use a large sample of academic records of students across 76 courses from a public university in Brazil in order to derive and select informative features for the employed classifiers. We create two classification models that either consider the specific course to which the target student is formally enrolled or not, respectively. We contrast both models and show that we have better results by not distinguishing the students by course.