Klasterisasi Produktivitas Daerah di Jawa Tengah Berdasarkan Ketenagakerjaan Menggunakan K-Means dan Average Linkage

Nashrullah, Ahmad Firqi
Mahardhika, Rivaldi Dwi
Rusdiyanto, Nur Rahmat
May Wara, Shindi Shella
Saputra, Wahyu Syaifullah Jauharis

Jurnal Diferensial
Vol 7 No 2 (2025): November 2025

This study employs K-Means and Agglomerative Clustering (Average Linkage) to group regions based on variables such as the number of residents, unemployment rate, and other supporting indicators. The data are normalized and evaluated using the Silhouette Score metric, yielding three optimal clusters. Average Linkage (0.3596) outperforms K-Means (0.2627). The Average Linkage results indicate that cluster 1 is characterized by stable productivity and low unemployment, cluster 2 consists solely of Semarang City with the highest Human Development Index and wages, and cluster 3 comprises underdeveloped areas with high unemployment and low wages. This clustering is highly beneficial for supporting more targeted data-driven regional development policies.