Pengklasteran Terbaik Kabupaten/Kota Berdasarkan Tingkat Kemiskinan Menggunakan Metode Hierarki Agglomerative dan Validitas Koefisien Silhouette

Abstract

Poverty is a complex and multidimensional development problem that has a direct impact on people's welfare. This study aims to cluster districts/cities in West Sumatra using the agglomerative hierarchy method based on indicators of poverty causes and evaluate the clustering results formed by the silhouette coefficient validity method. The research data are secondary data obtained from BPS publications that include eight variables from the four most influential indicators: education, economy, housing and employment. Agglomerative hierarchy cluster analysis was conducted for district/city clustering. The clustering results were validated using the silhouette coefficient method to determine the best method and the optimal number of clusters. The results show that all agglomerative hierarchy methods are the best methods. And cluster k = 3 is the optimal number of clusters among other clusters.