Implementation of K-Means Clustering for Student Learning Outcome Analysis Using the Elbow Method at SDN 2 Tegalrejo

Education serves as a critical effort to enhance individual skills, primarily achieved through structured learning. Ensuring equitable access to education within schools is a key approach, which can be facilitated by analyzing students' academic achievements. SD Negeri 2 Tegal Rejo, as a formal educational institution, observes significant variations in the average performance scores among its students. To address this, a grouping method is necessary to better understand and cater to the diverse learning abilities of the students. This study employs the K-Means Clustering Algorithm, a prominent technique in the fields of data analysis and data mining. Data mining involves the systematic collection and processing of data to uncover valuable insights. Specifically, this study utilizes the K-Means algorithm to categorize students based on their average scores, aiming to extract reliable and actionable information. The research methodology includes several stages: data collection, preprocessing, transformation, and clustering analysis using the K-Means algorithm, followed by evaluation through the Elbow method to identify the optimal number of clusters. The findings reveal two distinct clusters Cluster 0: Comprising 14 students with an average score of 53.8%. Cluster 1: Comprising 12 students with an average score of 46.2%. The clustering results offer a comprehensive understanding of the distribution of students' academic abilities. These insights serve as a basis for designing targeted and effective teaching strategies, contributing to improved educational outcomes and the overall quality of learning experiences