Interpretable Success Prediction in Higher Education Institutions Using Pedagogical Surveys

The indicators of student success at higher education institutions are continuously analysed to increase the students’ enrolment in multiple scientific areas. Every semester, students respond a pedagogical survey that aims collect opinion curricular units terms content and teaching methodologies. Using this information, we intend anticipate higher-level courses prevent dropouts. Specifically, paper contributes with an interpretable classification method. proposed solution relies on (i) student’s opinions; (ii) statistical data analysis validate reliability survey; (iii) machine learning algorithms classify student. In addition, method includes explainable mechanism interpret classifications their main factors. This transparent pipeline was designed have implications both digital sustainable education, impacting three pillars sustainability, i.e.,economic, social, environmental, where transparency is cornerstone. work assessed dataset from Portuguese institution, contemplating different departments. most promising results were achieved Random Forest presenting 98% accuracy F-measure.