A system for knowledge discovery in e-learning environments within the European Higher Education Area - Application to student data from Open University of Madrid, UDIMA

In today's open and dynamic learning environment, a significant percentage of students have a preference for flexible learning systems whereby they can reconcile their academic pursuits with their job responsibilities and family obligations.Non face-to-face educational models, like e-learning (electronic learning), evolved in order to offer such flexibility. E-learning systems have major strengths but also pose major challenges to the educational community.One such challenge is the large spatial and temporal gap between the teacher and student, which is an obstacle to student follow-up by teachers. The information generated by virtual learning systems sometimes overwhelms instructors who are unable to process the data without the support of special-purpose techniques and tools that are useful for analysing large dataflows. Student supervision is essential for detecting student behaviours that can lead to course dropout.The use of time analysis techniques promises to be a good option for evaluating educational data.The proposal that we present is able to identify students that are likely to drop out.The proposed system outperforms all of on the analysed proposals.The number of students correctly classified by our system describes a logarithmic behaviour.