Badruttamam Badruttamam
Universitas Malikussaleh

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

Found 1 Documents
Search

K-Means Application to Rice Production with DBI Evaluation Badruttamam Badruttamam; Mukti Qamal; Nunsina Nunsina
SISTEMASI Vol 15, No 7 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i7.6510

Abstract

Rice production is a key indicator of regional food security, making it essential to analyze production patterns and identify differences in productivity across districts. This study aims to apply the K-Means clustering algorithm to classify rice production data in Bireuen Regency and evaluate the quality of the resulting clusters using the Davies–Bouldin Index (DBI). The study employed secondary data from 2020 to 2024 covering 17 districts, with four variables: cultivated area, harvested area, productivity, and total rice production. The K-Means algorithm was used to partition the data into three clusters representing high, medium, and low production levels based on similarities in their characteristics. The results indicate that the clustering process consistently classified the districts across the five-year observation period. Cluster quality evaluation using the Davies–Bouldin Index yielded values of 0.9147 in 2020, 0.8292 in 2021, 0.6119 in 2022, 0.8821 in 2023, and 0.8597 in 2024. The best clustering performance was achieved in 2022, as indicated by the lowest DBI value, reflecting a more compact and well-separated clustering structure. These findings provide valuable insights for supporting agricultural planning, improving rice production strategies, and informing policy decisions related to agricultural development in Bireuen Regency.