Journal of Computer Science

Classifying and Predicting Students’ Performance using Improved Decision Tree C4.5 in Higher Education Institutes

Mohammed Hikmat Sadiq and Nawzat Sadiq Ahmed

DOI : 10.3844/jcssp.2019.1291.1306

Journal of Computer Science

Volume 15, Issue 9

Pages 1291-1306


Students’ information in higher education institutions increases yearly. It is hard for them to extract meaningful information from the huge amount of data manually. Such information can support academic staff to stop students from dropping out at the end of courses. This can be done by evaluating the students’ performance for the course and also by predicting their performance in the final exam early by using classification algorithms. Four classification algorithms, which are Decision Tree C4.5, Random Forest, Support Vector Machine (SVM) and Naive Bayes, were used in this research in order to classify and predict the students' performance. Furthermore, this research aimed at improving the Decision Tree C4.5 algorithm by adding a grid search function in order to improve prediction accuracy in classifying and predicting the students’ performance. Also, the features of this evaluation have been extracted through the interviews with academic staff of three universities (University of Zakho, Duhok Polytechnic University and University of Duhok), in Duhok province, Kurdistan Region, Iraq and through the review of the literature. A new prototype has been proposed as a tool to classify and predict the students’ performance by using Accrod.Net library. Three datasets were utilized in this research in order to test the improved Decision Tree C4.5 with the traditional C4.5 and three other selected algorithms. The results showed that the improved Decision Tree C4.5 outperformed the traditional C4.5 and also performed better when compared to C4.5 (J48) in Weka tool and other algorithms used in this research.


© 2019 Mohammed Hikmat Sadiq and Nawzat Sadiq Ahmed. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.