Student Graduation Prediction Model using Deep Learning Convolutional Neural Network (CNN)

Abstract

Students are the most important part of a university's life cycle. When compared to the number of students obtained in the same academic year, the number of students graduating from a university often has a small ratio. This low student graduation rate can be attributed to a variety of factors, including the abundance of student activities, as well as economic and other considerations. This necessitates the existence of a model that can determine whether or not a student will be able to graduate on time. Student graduation on time is one of the most important factors in determining a university. With the same ratio, the higher the level of new students at a university, the more students who graduate on time. If many students do not graduate on time from all registered students, the number of student data and academic data increases. As a result, the university's profile and reputation will suffer, potentially jeopardizing the university's accreditation value. To address this, we need a model that can predict student graduation and then be used to inform policy decisions. The goal of this research is to propose a Deep Learning classification model that uses the Convolutional Neural Network (CNN) algorithm to predict student graduation. The classification model with the CNN algorithm produced a high accuracy value of 87.44 %.