<![CDATA[Student academic performance is a key indicator of successful study program management. Detection of academic performance can help study program managers monitor and take proactive action against students who are potentially experiencing difficulties. Machine learning can be a solution to this challenge by assisting in the classification and detection of students' academic abilities. Machine learning techniques have proven to be very effective in analyzing complex data and uncovering hidden patterns that are difficult to detect by humans. This research aims to explore the implementation of machine learning algorithms in detecting students' academic performance, especially in the Mathematics Education Study Program at Nias University. With the advancement of technology, machine learning has proven to be effective in classifying data and detecting hidden patterns that traditional methods cannot identify. This research uses the Support Vector Machine (SVM) algorithm to predict student academic performance based on a dataset collected from student primary data. The dataset includes factors such as GPA, attendance, participation, and use of learning resources. The analysis results show that the SVM model used has an accuracy of 77.59%, with a bias that is more inclined to the class of students with good academic performance. The results of this study are expected to make a practical contribution in the development of more effective learning methods and personalization of academic interventions in higher education.]]>
Copyrights © 2024
