Graduate Prediction Using Ontology Approach

Abstract—The paper seeks to predict the completion of graduation of students studying in a University. The filtration of the redundant features will be done by Ranker method. The use of SVM method will also be taken into consideration for filtration of attributes. The decision tree algorithms C4.5/J48 and ID3 are used for generating the decision tree which will serve as a basis for the generation of an ontology. Moreover, the classification rules are extended by applying a semantic based approach for creating classification tree ontology. The ontology represents the classification rules that are used to enable machines to interpret and identify learner factors in process of prediction. The explanation of how ontological representation plays a role in classifying students to predictive target class is done. Semantic Web Rule Language is used for the specification of classification rules