An Ensemble-Based Decision Tree Approach for Educational Data Mining

Nowadays, data mining and machine learning techniques are applied to a variety of different topics (e. g., healthcare and disease, security, decision support, sentiment analysis, education, etc.). Educational data mining investigates the performance of students and gives solutions to enhance the quality of education. The aim of this study is to use different data mining and machine learning algorithms on actual data sets related to students. To this end, we apply two decision tree methods. The methods can create several simple and understandable rules. Moreover, the performance of a decision tree is optimized by using an ensemble technique named Rotation Forest algorithm. Our findings indicate that the Rotation Forest algorithm can enhance the performance of decision trees in terms of different metrics. In addition, we found that the size of tree generated by decision trees ensemble were bigger than simple ones. This means that the proposed methodology can reveal more information concerning simple rules.