PENERAPAN CLUSTERING PADA PENDUDUK YANG MEMPUNYAI KELUHAN KESEHATAN DENGAN DATAMINING K-MEANS

Abstract

This study aims to utilize Clushtering Algorithm in grouping the number of people who have health complaints with the K-means algorithm in Indonesia. The source of this research data was collected based on the documents of the provincial population which had health complaints produced by the National Statistics Agency. The data used in this study are data from 2013-2017 consisting of 34 provinces. The method used in this research is K-means Algorithm. Data will be processed by clushtering in 3 clushter, namely clusther high health complaints, clusther moderate and low health complaints. Centroid data for high population level clusters 37.48, Centroid data for moderate population level clusters 27.08, and Centroid data for low population level clusters 14.89. So that obtained an assessment based on the population index that has health complaints with 7 provinces of high health complaints, namely Central Java, Yogyakarta, Bali, West Nusa Tenggara, East Nusa Tenggara, South Kalimantan, Gorontalo, 18 provinces of moderate health complaints, and 9 other provinces including low health complaints. This can be an input to the government to give more attention to residents in each region who have high health complaints through improving public health services so that the Indonesian population becomes healthier without health complaints.Keywords: data mining, health complaints, clustering, K-means, Indonesian residents