Caecilia Safira Ferini Marcellina Mitang Mitang
Universitas Gadjah Mada

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

PENGELOMPOKAN USAHA PERTANIAN PERORANGAN TANAMAN PANGAN DI KABUPATEN FLORES TIMUR DENGAN ALGORITMA K-MEANS DAN K-MEDOIDS Virgilius Daton Balamakin; Maryo Yoseph Ambarto Dwi Sili Osan Osan; Caecilia Safira Ferini Marcellina Mitang Mitang
Jurnal Statistika Terapan (ISSN 2807-6214) Vol 5 No 2 (2025): Jurnal Statistika Terapan
Publisher : Badan Pusat Statistik Provinsi NTT

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64930/jstar.v5i2.124

Abstract

The introduction explains that agriculture is the main sector supporting the economy of the community in East Flores Regency, East Nusa Tenggara, with the majority of the population depending on individual food crop farming such as rice, corn, cassava, sweet potatoes, and peanuts. However, there are variations in production between subdistricts due to differences in land potential, agroclimatic conditions, and cultivation practices. Background Problems shows that there is an imbalance in commodity distribution based on the 2023 Agricultural Census, in which upland rice and corn are dominant, while paddy rice and sweet potatoes are relatively low. Without clear mapping, development policies risk being inconsistent with regional needs. The novelty of this research lies in the use of a clustering approach comparing the K-Means and K-Medoids algorithms, which are rarely applied in the context of agriculture in remote areas, as well as quality evaluation using the Davies-Bouldin Index (DBI) accompanied by cluster profiling. Research Methods used secondary data from Statistics Indonesia (BPS) from the 2023 Phase II Agricultural Census with six main commodities, analyzed through Z-Score normalization, application of K-Means and K-Medoids, DBI evaluation, and interpretation of results through profiling. The results show that K-Means produces three clusters with a DBI of 1.1696, while K-Medoids produces two clusters with a DBI of 0.7058, which is more optimal. Profiling shows that 15 subdistricts have a balanced pattern in rice and sweet potatoes, while two subdistricts, Ile Boleng and Witihama, are more dominant in corn, cassava, and peanuts. These findings form the strategic basis for agricultural development policies in East Flores.