Grade 9 Student Grade Data Analysis Based on Grades Knowledge to Determine Outstanding Students with K-Means Clustering (Case Study of SMPN 2 Sindang)

Increasing student academic achievement is one of the main challenges in the world of education. Students have diverse abilities, so a directed learning approach is needed that suits each individual's needs. At SMPN 2 Sindang, this challenge is of particular concern in improving the achievement of grade 9 students.This research aims to overcome this problem by applying the K-Means Clustering algorithm to group students based on their academic score patterns. The data used includes midterm exam scores and attendance. The K-Means algorithm was used to identify three main groups: Cluster 1 (high value), Cluster 0 (medium value), and Cluster 2 (low value). The research results show that the K-Means algorithm is effective in identifying groups of students with similar learning needs. This grouping allows schools to design learning programs that are more effective and suit the needs of each group of students. Thus, this research makes an important contribution to the development of data-based learning methods, especially at the secondary education level.