Interpretable success prediction in a computer networks curricular unit using machine learning

Abstract

Today, higher education institutions are focused on understanding which factors are associated with the failure or success of students to, early on, be able to implement measures that can reduce the low performance of students and even dropout. The retention rate is positively and negatively influenced by factors belonging to several dimensions (personal, environmental, and institutional). We aim to use information from those dimensions to identify students enrolled in a Computer Networks course at risk of failing the subject. Besides, this needs to happen as early as possible, to be able to provide the students, for example, with extra support or resources to try to prevent that negative outcome. For predicting the grade level on the first test, the best accuracy obtained was 55%. However, most C-level grades were correctly classified, with 63% accuracy in predicting the students that are most at risk of failing, which is one of our main objectives. As for the prediction of the second test’s grade level, the best accuracy obtained was 89% and concerned data regarding the students’ interaction with the LMS together with students’ grades history. All the C-level grades were correctly classified (100% accuracy) and so we were able to correctly predict every student at a high risk of failing. Using the procedure described in this paper, we are able to anticipate the students needing extra support, and provide them with different resources, to try to prevent their negative outcome.