<![CDATA[Abstrak−Differences in academic abilities among junior high school students often pose a challenge for schools in conducting class groupings objectively and efficiently. Many educational institutions, including SMP Negeri Y, still rely on manual grouping methods that are subjective and do not accurately reflect the actual conditions of students. Inaccurate grouping may lead to imbalanced learning processes, where students with high and low academic abilities are placed in the same group without considering their performance variations. Therefore, a data-driven approach is needed to represent student characteristics comprehensively and flexibly. This study aims to apply the Fuzzy C-Means (FCM) method to cluster students of SMP Negeri Y based on four main attributes: Academic Average, Attitude Score, Activeness Score, and Attendance. The FCM method was chosen for its ability to handle data uncertainty and assign multiple membership degrees to each student across different clusters. Prior to clustering, the data underwent a preprocessing stage involving data cleaning, normalization using StandardScaler, and scale adjustment across attributes to improve the accuracy of Euclidean distance calculations. The analysis results revealed the formation of two main clusters representing student academic performance levels. Cluster 0 has an average academic score of 78.37 with moderate attitude and activeness levels, while Cluster 1 shows a higher academic average of 82.18 accompanied by better attitude, activeness, and attendance scores. Based on the highest membership degree, 38 students were assigned to Cluster 0 and 26 students to Cluster 1. Model evaluation using Fuzzy Partition Coefficient (FPC), Modified Partition Coefficient (MPC), and Silhouette Score indicated the optimal configuration at a fuzziness level of m = 2, yielding FPC = 0.680, MPC = 0.359, and Silhouette Score = 0.334. These findings demonstrate that FCM is effective in representing variations in student abilities more realistically, while also providing an objective foundation for schools to design adaptive learning strategies and implement data-driven academic policies.]]>
