Population Density Cluster Analysis in DKI Jakarta Province Using K-Means Algorithm

Abstract

This study aims to analyze clusters based on the area and population density of the area and population density of the area in DKI Jakarta Province in 2015 using the data mining method by clustering as the first step in planning for population equality. The subject of analysis in this study is a village located in the province of DKI Jakarta which is recorded based on the area and population density in each sub-district until 2015 with several stages, namely data understanding, data processing or cleansing, cluster tendency assessment, clustering, cluster review. From this study, the results were obtained that the data tended to be clustered because the statistical value of Hopkins was close to the value of 0 and in VAT there was a vague picture of clusters that might be formed. Based on this, cluster creation is carried out using the K-Means Algorithm.  Based on the results, there are 3 clusters formed, namely cluster 0 (not densely populated), cluster 1 (medium population density), and cluster 2 (densely populated). These results can be used as a basis for policy making in population management.