A Decision Tree Approach for Predicting Student Grades in Research Project using Weka

Data mining in education is an emerging multidiscipline research field especially with the upsurge of new technologies used in educational systems that led to the storage of massive student data. This study used classification, a data mining process, in evaluating computer engineering student’s data to identify students who need academic counseling in the subject. There were five attributes considered in building the classification model. The decision tree was chosen as the classifier for the model. The accuracy of the decision tree algorithms, Random Tree, RepTree and J48, were compared using cross-validation wherein Random Tree returned the highest accuracy of 75.188%. Waikato Environment for Knowledge Analysis (WEKA) data mining tool was used in generating the classification model. The classification rules extracted from the decision tree was used in the algorithm of the Research Project Grade Predictor application which was developed using Visual C#. The application will help research instructors or advisers to easily identify students who need more attention because they are predicted to have low grades.