<![CDATA[The decision-making process in admitting new students is a crucial aspect that can influence the quality and efficiency of academic administration in higher education. This research aims to analyze the role of Machine Learning methods, especially Support Vector Machines (SVM), in increasing the efficiency of the decision-making process for new student admissions at the Panca Budi Development University, Medan. The data used in this research includes information from the student admissions process for the odd semester of the 2022/2023 academic year, which includes various variables such as Registration Number, School of Origin, Registration Payment, and others. The data is divided into a training set (70%) and a testing set (30%). The Support Vector Machine (SVM) model that was built was evaluated using metrics such as accuracy, precision, recall, and F1-Score. The research results show that the SVM model achieves an accuracy of 100%, with high precision and recall for both classes. Precision for both classes reached 1.00, while recall for the minority class (class 1) reached 0.91, indicating excellent model performance in classification. The conclusion of this research is that the Support Vector Machine (SVM) model can significantly increase efficiency and accuracy in the decision-making process for new student admissions at the Panca Budi Development University in Medan compared to conventional methods. These findings indicate that the application of Machine Learning methods can provide substantial benefits in the context of academic administration.]]>
Copyrights © 2024
