Nowadays as more and more teachers beside face-to-face education take online courses, at least partly in electronic learning environment, the usability of e-learning systems is one of the important questions in education. These e-learning systems accumulate a vast amount of information which is very valuable for analyzing students’ behavior. However it is difficult to manage this kind of data manually.

This work describes educational data mining and student modeling as part of this area. We collected real educational data from Programming course in e-learning system Moodle. The objective is to preprocess the collected data and build a model, which will give the course educator information about possible course adaptation and learning recommendations based on the students learning behavior.