3) Data mining. At this stage, DM algorithms are applied to
predict student failure like a classification problem. To
do this task, we propose to use classification algorithms
based on rules and decision trees. These are“white box”
techniques that generate easily interpretable models. In
addition, a cost sensitive classification approach is also
used in order to solve the imbalanced data problem.
Finally, different algorithms have been executed, evaluated
and compared in order to determine which one
obtains the best results.