Clustering of imbalanced moodle data for early alert of student failure

This paper is an attempt of applying EDM methods on Moodle data in order to detect specific behaviours within student groups with the tendency to fail the course. The research is conducted on Moodle logs gathered in the blended course Programming 1. Extracting and using crucial information on time can be a turning point for students in at-risk stage, which is what we tried to achieve in this research.