Abstract (EN):
Predicting the success or failure of a student in a course or a program is a problem that has recently been addressed using data mining techniques. However, the literature shows that there is still no consensus on what is the best set of variables that may lead to accurate models. Moreover, the problem is quite complex and appears to be very dependent on the data set used (Kabakchieva, 2013). It is related to student attrition, a research area of Educational Data Mining. This paper presents the results of preliminary experiments in this research area at the University of Porto. The experiments were carried out using automated approaches on administrative data. Although the number of courses is small, initial conclusions were drawn.
Language:
English
Type (Professor's evaluation):
Scientific