Selection of Best Decision Tree Algorithm for Prediction and Classification of Students’ Action
Year: 2017
Type: preprint
Abstract: Since the student’s success rate reflects the success of educational organizations, so the trend of increasing student’s success became the goal of all educational organizations. Besides that, the student’s willingness of studying higher education after complete secondary school is one of the most important goals to the educational Organizations. Many reasons affect this willingness and revealing these reasons may enhance the student’s will. Data mining tools (especially Decision Tree Algorithms) can be considered as the best choice to find the hidden patterns in order to achieve these goals. The experimental dataset used in this work is data set about Portuguese student on two courses (Mathematics (395 instances) and Portuguese (Portuguese language course which holds 659 instances)) which was collected and analyzed by Paulo Cortez and Alice Silva, University of Minho, Portugal. Three Decisions Tree algorithms (J48, RepTree and Hoeffding Tree (VFDT)) are applied and experimented in this work. The results showed that J48 algorithm mostly proper to classify and predict both students’ willingness to complete higher education and success in courses.
Source: SSRN Electronic Journal
Author: Alaa Khalaf Hamoud
Institution: University of Basrah
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W3199654895
