Analysing the Academic Performance of Students Using Unsupervised Data Mining

Abstract

Educational Data Mining is an attractive interdisciplinary domain in which the main goal is to apply data mining techniques in educational environments in order to offer better insights into the educational related tasks. This paper analyses the relevance of two unsupervised learning models, self-organizing maps and relational association rule mining in the context of students’ performance prediction. The experimental results obtained by applying the aforementioned unsupervised learning models on a real data set collected from Babe¸s-Bolyai University emphasize their effectiveness in mining relevant relationships and rules from educational data which may be useful for predicting the academic performance of students.