Electronic Theses and Dissertation

Agglomerative merupakan salah satu metode hierarchical clustering yang menerapkan pendekatan dari bawah ke atas dalam pengelompokan data. terdapat beberapa metode pengukuran jarak dalam agglomerative, seperti single linkage, complete linkage, dan average linkage. data yang digunakan dalam penelitian ini adalah data indeks pembentuk idm, yaitu indeks ketahanan sosial (iks), indeks ketahanan ekonomi (ike), dan indeks ketahanan lingkungan (ikl). data tersebut mencakup 260 desa di kabupaten aceh selatan pada tahun 2023. penelitian ini bertujuan untuk menentukan metode agglomerative terbaik, jumlah cluster optimal dari metode terbaik, serta karakteristik dari setiap cluster. metode agglomerative terbaik dipilih berdasarkan nilai cophenetic correlation coefficient (ccc) tertinggi. cluster optimal ditentukan berdasarkan nilai internal measure dan stability measure, sedangkan karakteristik cluster dianalisis menggunakan nilai rata-rata dari setiap indeks dalam masing-masing cluster. hasil penelitian menunjukkan bahwa metode average linkage lebih baik dibandingkan single linkage dan complete linkage, dengan nilai ccc pada average linkage sebesar 0,766, single linkage sebesar 0,659, dan complete linkage sebesar 0,541. berdasarkan nilai internal measure dan stability measure, jumlah cluster optimal dari metode average linkage sebesar 3 cluster, dengan jumlah desa untuk setiap cluster yaitu cluster 1 sebanyak 235 desa, cluster 2 sebanyak 12 desa, dan cluster 3 sebanyak 13 desa. setiap cluster memiliki karakteristik berbeda, di mana cluster 1 memerlukan penguatan aspek ekonomi, cluster 2 berfokus pada keberlanjutan pembangunan, dan cluster 3 memerlukan perhatian khusus terhadap aspek ekonomi dan lingkungan. temuan ini diharapkan dapat menjadi acuan dalam perumusan kebijakan pembangunan desa yang lebih tepat sasaran dan berbasis data.

Agglomerative is one of the hierarchical clustering methods that employs a bottom-up approach in grouping data. This method includes several types of linkage criteria, such as single linkage, complete linkage, and average linkage. The data used in this study consist of the component indices of the Village Development Index (IDM), namely the Social Resilience Index (IKS), Economic Resilience Index (IKE), and Environmental Resilience Index (IKL). The dataset covers 260 villages in South Aceh Regency for the year 2023. The purpose of this research is to determine the best agglomerative method, identify the optimal number of clusters based on that method, and analyze the characteristics of each resulting cluster. The best agglomerative method is selected based on the highest cophenetic correlation coefficient (CCC). The optimal number of clusters is determined using internal and stability measures, while the cluster characteristics are analyzed based on the average value of each index within the respective clusters. The results show that the average linkage method performs better than both single and complete linkage, with CCC values of 0.766 for average linkage, 0.659 for single linkage, and 0.541 for complete linkage. Based on the internal and stability measures, the optimal number of clusters for the average linkage method is three, with 235 villages in cluster 1, 12 villages in cluster 2, and 13 villages in cluster 3. Each cluster exhibits distinct characteristics: cluster 1 requires strengthening in the economic aspect, cluster 2 focuses on sustainable development, and cluster 3 demands special attention to both economic and environmental resilience. These findings are expected to serve as a data-driven reference for formulating more targeted and effective village development policies.