Penerapan Metode K-Means Dalam Mengelompokkan Banyaknya Desa/ Kelurahan Menurut Keberadaan Permukiman Di Bantaran Sungai Berdasarkan Provinsi

Abstract

The research aims to classify the settlements along the river banks by province. To solve this problem, the researchers applied the K-Means Algorithm method. Where the source of research data was collected based on documents explaining the number of villages / sub-districts according to the existence of settlements on the river banks produced by the Central Statistics Agency (BPS). The data used in the study are data from 2014 - 2018 which consists of 34 provinces. The data will be processed by clustering in 2 clusters, namely the settlement level cluster on the high riverbank and the settlement level cluster on the low riverbank. The high cluster consists of 11 data, namely the provinces of Aceh, North Sumatra, Jambi, South Sumatra, West Java, Central Java, East Java, West Kalimantan, Central Kalimantan, South Kalimantan, and South Sulawesi. By conducting the research, it can provide input and as a solution to related parties in charge of dealing with settlement problems along the river banks, especially for the government, in order to get more attention in provinces with high riverbank settlement rates.