Analisis Cluster Provinsi Indonesia Berdasarkan Produksi Bahan Pangan Menggunakan Algoritma K-Means

Abstract

Food is material produced through agricultural products which has a great influence on human survival. Having agriculture spread throughout Indonesia, making Indonesia a country that always produces raw food. Raw food can be in the form of fruits, vegetables, rice, peanuts, and others. Clustering algorithm is applied to group the number of provinces according to the results of food production with K-Means. The data from this study were sourced from information on the number of provinces according to the results of food production produced by the National Statistics Agency. There are 34 provinces that will be used in this study. There are 5 variables used, namely corn production, peanut production, soybean production, rice production, and cassava production. The data collected will be processed by clustering in 3 clusters, namely high foodstuff production clusters, medium foodstuff production clusters, and low foodstuff production clusters. In its implementation using rapidminer software. The results obtained can be input for the government in analyzing the provinces according to food production.