To search, Click below search items.


All Published Papers Search Service


A Comparative Analysis of Exam Timetable Using Data Mining Techniques


Bilal Sowan


Vol. 17  No. 1  pp. 73-80


Knowledge discovery and data mining is an emerging practice that is applied in a wide range domain fields, for the purpose of extracting implicit knowledge from a huge database. This knowledge helps in making a decision in particular fields. It is one of the important developing applications is the higher education field. This paper proposes a data mining model, which is based on different and well-known classification algorithms. The model is able to extract implicit knowledge from the higher education dataset, specifically the dataset concerns the student satisfaction of courses-exams timetable. The courses-exams timetable satisfaction is considered as one of the complex and main significant factors that effects the student passing of exams. The paper also studies the reasons behind the student exam passing. Therefore, the application of data mining model in this phenomenon improves the decision making process and considers an automated analytical tool that provides better and clearer knowledge. The importance of this knowledge is to provide a feedback for the higher educational institution management related to the courses-exams timetable satisfaction for further decision quality improvements. The proposed model is validated with several experiments for the purpose of comparing different classification algorithms to select the fitting one on the dataset that is used in this research. J48, REPTree, MLP, SVM, SVM, JRip, and Prism are applied to evaluate the performance of the proposed model. As a result, both, MLP and Prism, outperformed the other algorithms.


Data mining, Classification algorithms, Knowledge, Higher education.