Comparison of clustering analysis of K-means, K-medoids, and fuzzy C-means methods: case study of school accreditation in west java

This research aims to analyze school accreditation data in West Java using clustering methods: K-Means, K-Medoids, and Fuzzy C-Means, to identify patterns and groups of schools based on similar characteristics. K-Means, known for its simplicity, suggests an optimal two-cluster solution based on silhouette values but employs three clusters for detailed analysis. K-Medoids, noted for its robustness against outliers, achieves the best clustering with a lowest Davies-Bouldin Index (DBI) of 0.8 and the highest Silhouette Information (SI) value of 0.46. Fuzzy C-Means, which assigns membership degrees to each data point across clusters, performs reasonably well with a DBI of 0.87 and an SI value of 0.40, while K-Means shows the highest DBI of 0.9 and the lowest SI value of 0.39. The findings highlight K-Medoids as the superior method for clustering. Regions with lower educational quality, such as Bekasi and Cianjur regions, require priority interventions, whereas areas with better quality, like Bandung and Bekasi regions, can serve as models. Data-driven approaches, inter-regional collaboration, and continuous monitoring and evaluation are recommended to optimize educational policies and enhance overall educational quality in West Java.