Enhanced Student Admission Procedures at Universities Using Data Mining and Machine Learning Techniques

Abstract

The progress of technology has played a crucial role in enhancing various fields such as education. Universities in Saudi Arabia offer free education to students and follow specific admission policies. These policies usually focus on features and scores such as the high school grade point average, general aptitude test, and achievement test. The main issue with current admission policies is that they do not fit with all majors, which results in high rates of failure, dropouts, and transfer. Another issue is that all mentioned features and scores are cumulatively calculated, which obscures some details. Therefore, this study aims to explore admission criteria used in Saudi Arabian universities and the factors that influence students’ choice of major. First, using data mining techniques, the research analyzes the relationships and similarities between the university’s grade point average and the other student admission features. The study proposes a new Jaccard model that includes modified Jaccard and approximated modified Jaccard techniques to match the specifications of students’ data records. It also uses data distribution analysis and correlation coefficient analysis to understand the relationships between admission features and student performance. The investigation shows that relationships vary from one major to another. Such variations emphasize the weakness of the generalization of the current procedures since they are not applicable to all majors. Additionally, the analysis highlights the importance of hidden details such as high school course grades. Second, this study employs machine learning models to incorporate additional features, such as high school course grades, to find suitable majors for students. The K-nearest neighbor, decision tree, and support vector machine algorithms were used to classify students into appropriate majors. This process significantly improves the enrolment of students in majors that align with their skills and interests. The results of the experimental simulation indicate that the K-nearest neighbor algorithm achieves the highest accuracy rate of 100%, while the decision tree algorithm’s accuracy rate is 81% and the support vector machine algorithm’s accuracy rate is 75%. This encourages the idea of using machine learning models to find a suitable major for applicants.