Application of Data Mining in Student Retention Strategy Using Decision Tree Module
Dr. Yang Huo
This paper addresses the issue of why students want to drop out from a course and suggest appropriate strategies to enhance student retention. We empirically examine with a sample of 261 hospitality management students, drawing on Tinto’s theory and applying a behavior on student departure. We apply the data mining &decision tree using Classification and Regression Trees method as an analytic tool to identify a group, discover relationship between groups and predict future events and for segmentation. The results regarding the demographics indicate that the most effective attributes are job situation, earned credit hour. In need, our findings provide empirical evidence that financial situation and quality of teaching are the most effective attributes. Finally, we argue that students’ financial situation and job availability during COVID-19 crisis can negatively impact on potential dropout decision and may be an important consideration of planned behavior.