PENGELOMPOKAN SISWA BERDASARKAN SKOR AKADEMIK (MATEMATIKA, MEMBACA, MENULIS) MENGGUNAKAN METODE K-MEANS & HIERARCHICAL CLUSTERING

<i>The variation in students' academic abilities within a single classroom presents a challenge for educators in delivering effective instruction. This study aims to cluster students based on their academic scores in Mathematics, Reading, and Writing using two unsupervised learning algorithms: K-Means and Hierarchical Clustering. The dataset was obtained from Kaggle and underwent preprocessing steps including cleaning, normalization, and feature selection. Clustering implementation was evaluated using the Elbow Method and Silhouette Score to determine the optimal number of clusters. The results showed that students could be grouped into three distinct clusters representing high, medium, and low academic performance. Further analysis revealed dominant learning styles in each group, such as analytical, verbal, or multimodal. These findings provide valuable insights for developing adaptive, data-driven learning strategies tailored to each cluster’s characteristics. This research contributes to the field of educational data mining by demonstrating the practical application of clustering algorithms in personalized learning design.</i>