Our academic systems generate a wide array of data that can help us to predict the behaviour of our students in front of our academic plans.

And the development of methods for exploring those unique types of data that come from educational settings is the main concern of one of the main branches of study of the GRETEL, the Educational Data Mining, also represented by acronym EDM.


We propose two main lines of research related to the EDM branch:

  • Learning Analytics (LA): LA addresses the management and analysis of the educational data in order for the improvement of learning: “Using analytics we need to think about what we need to know and what data is most likely to tell us what we need to know”.

We can affirm that LA has become the main topic of educational conferences, and it is more than a simple trend in education.

Ferguson defined LA as “the measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning and the environments in which it occurs".


  • Academic Analytics (AA): While LA are focused in the course-level and departmental data (in order to improve the students and the faculty), AA are more focused to study the indicators that study the learner profiles, performance of academics, knowledge flow and comparisons between different learning systems (institutional, regional or national/international levels), clearly in the same direction that our research framework. In this way, AA marries the data with statistical techniques, and in a second stage with predictive modelling to help students, teachers, faculty and advisors to determinate which contents can be improved or which students needs a support.