Analysis of the K-Means Algorithm on Clean Water Customers Based on the Province

Abstract

Abstract One of the important needs of environmental health is clean water. Clean water is the most important necessity of living beings in supporting survival. The study aimed to cluster the number of cleaned water customers by province (1995-2015). The method used is data mining clustering using k-means. The sample data used 34 provinces with attribute assessment of the number of cleaned water customers by province. The clustering process is done with 3 clusters, namely (C1) Cluster High, (C2) Cluster Normal and (C3) Cluster Low, for the number of cleaned water customers who are low on the need of clean water. The results showed, C1: 6 provinces, C2: 4 provinces and C3: 24 provinces. The end centroid values used are: C1 (296587.22), C2 (995898.56) and C3 (70832.29). The results obtained on the Davies-Bouldin index for “the number of cleaned water consumers” are -0.470. based on performance results, it can be concluded that k-means algorithm is best because it has the smallest Davies-Bouldin index value. Based on research results, 70% of Indonesian people are still low awareness of the need for clean water.