Meta-learning: Can It Be Suitable to Automatise the KDD Process for the Educational Domain? Marta Zorrilla and Diego Garc´ ıa-Saiz Department of Computer Science and Electronics, University of Cantabria Avenida de los Castros s/n, 39005, Santander, Spain {marta.zorrilla,diego.garcias}@unican.es Abstract. The use of e-learning platforms is practically generalised in all educational levels. Even more, virtual teaching is currently acquir- ing a great relevance never seen before. The information that these sys- tems record is a wealthy source of information that once it is suitably analised, allows both, instructors and academic authorities to make more informed decisions. But, these individuals are not expert in data mining techniques, therefore they require tools which automatise the KDD pro- cess and, the same time, hide its complexity. In this paper, we show how meta-learning can be a suitable alternative for selecting the algorithm to be used in the KDD process, which will later be wrapped and deployed as a web service, making it easily accessible to the educational community. Our case study focuses on the student performance prediction from the activity performed by the students in courses hosted in Moodle platform. Keywords: Meta-learning, classification, predicting student performance. 1 Introduction Educational data mining is a recent field of research which rose as a result of the appearance of the current computer-supported interactive learning methods and tools (e.g. e-learning platforms, tutoring systems, games,etc.). These have given the opportunity to collect and analyze student data, to discover patterns and trends in this data, and to make new discoveries and test hypotheses about how students learn [12]. Although the contributions in this field are numerous, there is still a lot of work left to be done. One of these contributions is, what we name, the democratization of the use of data mining in the educational arena. That means that people involved in this field and, in particular, instructors, can gain richer insights into the increasingly amount of available data and take advantage of its analysis. However, non-expert users may find it complex to apply data mining techniques to obtain useful results, due to the fact that it is an intrinsically complex process [5]. In order to advance towards our end goal, in this paper, we still deal with the search of a mechanism which recommends us the predictive algorithm that better works in a certain problem at hand. We concretely address one of the oldest and M. Kryszkiewicz et al. (Eds.): RSEISP 2014, LNAI 8537, pp. 285–292, 2014. c  Springer International Publishing Switzerland 2014