Applying Representation Learning for Educational Data Mining

Milagro Teruel, Laura Alonso Alemany

Abstract:

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.

Conflicts: unc.edu.ar