Supervised Learning in the Context of Educational Data Mining to Avoid University Students Dropout

Abstract

Educational data mining is a research field that looks for extracting useful information from large educational datasets. This area provides tools for improving student retention rates around the world. In this paper we propose a computational approach using educational data mining and different supervised learning techniques (Decision Trees, K-nearest Neighbor, Neural Networks, Support Vector Machines, Naive Bayes and Random Forests) to evaluate the behaviour of different prediction models in order to identify the profile of at-risk university students in a Brazilian university environment. The results of this paper indicate that some algorithms can be used as tools for supporting decisions that reduce school dropout.