Classification of Student Grade Data Using the K-Means Clustering Method

The fourth industrial revolution has brought significant changes in various sectors, and education has been greatly affected by technological advances. Automation, particularly in data processing, has simplified educational processes, particularly in managing student grade data. However, the increasing volume of data poses challenges in efficient processing. This research explores the application of K-Means clustering, a data mining technique, to cluster student grade data. This research uses the Elbow Method to determine the optimal number of clusters. The dataset, sourced from the Information Systems Study Program at the Telkom Institute of Technology Purwokerto, includes attributes such as Credits Taken, GPA, Number of Ds, Number of Es, and Credits Not Taken. The results identified three groups of students: "High Achievers," "Average Performance," and "Needs Improvement." Recommendations include academic challenges for high performers, better learning methods for average performers, and remedial programs for those who need improvement. This research demonstrates the efficacy of K-Means clustering in improving educational strategies and support systems based on student characteristics.