Classterization Of Village Welfare Levels With The K-Means Algorithm For Planning Quality Of Life Improvement Program

Abstract

This research applies the concept of big data and the data mining process and aims to provide clustered data on village welfare levels which can help local governments to properly plan programs to improve the quality of life of village communities. Research case study in District XYZ whose area includes 11 villages. The clustering process is carried out using the K-Means algorithm which groups data based on similar characteristics. The data analysis process was carried out using the RStudio tool and Microsoft Excel as a comparison. The data set used has 10 attributes, namely village name, number of Pre-Prosperous families, economic reasons (Alek) in the Pre-Prosperous column, non-economic reasons (Bulek) in the Pre-Prosperous column, number of Prosperous Families I (KS I), Alek in the KS column I, Bulek in column KS I, number of Prosperous Families (KS II), number of Prosperous Families (KS III) and number of Prosperous Families (KS III) Plus. Data processing with both tools show the same results, namely that there are 2 clusters. Cluster 1 is a cluster with a high level of welfare, consisting of 4 villages and Cluster 2 is a cluster with a low level of welfare, consisting of 7 villages.