Exploration of classification using NBTree for predicting students' performance

The growth of academic data size in higher education institutions increases rapidly. This huge volume of data collection from many years contains hidden knowledge, which can assist the improvement of education quality and students performance. Students' performance is affected by many factors. In this study, the data used for data mining were students' personal data, education data, admission data, and academic data. NBTree classification technique, one of data mining methods, was adopted to predict the performance of students. Several experiments were performed to discover a prediction model for students' performance. The class labels of students' performance were students' status in study, graduates predicates, and length of study. The experiments were conducted with two-level classification, the university level and faculty level. The resulted model indicated that some attributes had significant influence over students' performance.