Applying Representation Learning for Educational Data Mining

Educational Data Mining is an area of growing interest, given the increase of available data and generalization of online learning environments. In this paper we present a first approach to integrating Representation Learning techniques in Educational Data Mining by adding autoencoders as a preprocessing step in a standard performance prediction problem. Preliminary results do not show an improvement in performance by using autoencoders, but we expect that a fine tuning of parameters will provide an improvement. Also, we expect that autoencoders will be more useful combined with different kinds of classifiers, like multilayer perceptrons.