BIG DATA TECHNOLOGY FOR VILLAGE STATUS CLASSIFICATION BASED ON VILLAGE INDEX BUILDING INVOLVING K-MEANS ALGORITHM IN PROGRAMS TO SUPPORT THE WORK OF THE MINISTRY OF THE VILLAGE

The problem that is used as part of the research is village status data which is only used and utilized in the current year and has been going on since 2014 so that there is an accumulation of data in the database and no in-depth analysis has been carried out to obtain information related to village status. This research aims to analyze the village status group using the k-means algorithm and provide the best cluster information using the Elbow Method by finding the SSE (sum of squared-error) value by utilizing the cluster closest to the elbow on the graph. The Ministry of Villages has described the method of solving problems using secondary data through the website https://idm.kemendesa.go. Id/ followed by the application of the K-means algorithm and determining the best cluster. The results obtained in the study are a comparison of sets from the village ministry with cluster information provided by the K-Means algorithm, namely the status of independent villages has increased by 761 villages, developed villages from 202 experienced an increase in data of 1095 data, growing villages with the K-Means algorithm decreased. With a difference of 1150 villages, underdeveloped villages decreased based on the K-Means Algorithm with a difference of 1158, and very disadvantaged villages increased up to a difference of 452. Testing with the Elbow Method provides information and offers the best cluster for grouping village status. The number of groups is four groups with an independent position, Forward, Develop, lag.