Human resources play an important role in improving organizational performance, including in the North Sumatra Province Youth and Sports Agency (Dispora). This study aims to measure the effect of competence on employee performance using the K-Means Clustering algorithm, known as an unsupervised data clustering method. The dataset consists of 700 employee data with 15 attributes covering technical, managerial, and social competencies. Data were collected through direct surveys and processed using Python with a normalization process through the StandardScaler method to ensure data consistency. The elbow method was used to determine the optimal number of clusters, resulting in five clusters: best performance, very good, and average. The results of the analysis show that the clustering results group employees into five clusters, namely Cluster 0 with 145 employees who have high technical competence, Cluster 1 with 160 employees who excel in social and managerial competence, Cluster 2 with 125 employees who show average competence in all aspects, Cluster 3 with 135 employees who have moderate technical competence but excel in social competence, and Cluster 4 with 135 employees who have great potential for development. This research provides practical benefits in the form of identifying competency patterns for developing group-based training needs, as well as more objective strategic decision-making in human resource management. Thus, this research is expected to support improving employee performance through an effective data-based approach.