Implementation Of Kmeans Clustering On SIPP-KLING Dashboard Applications

This study focused on classifying rumah_sehat data into five categories, namely Healthy, Very Healthy, Unhealthy, Unhealthy, Very Unhealthy. The criteria that will be the input parameters for K-Means calculation are 17 criteria. The implementation of the K-Means Clustering will help in classifying healthier homes that are more filtered, based on 8969 data. Data obtained from the results of clustering k-means can help analyze what parts of a house should be handled more, or which areas have lower levels of health. The test results show that from 8969 data, there were 3303 Very Healthy homes, 2496 Healthy homes, 792 Unhealthy houses, 1706 Unhealthy houses, and 667 Very Unhealthy houses. The test results using confusion matrix showed that the accuracy of this method was 87.05%, with precision of 95.64% and 75, 81%, and recall of 83.82% and 92, 98%. Based on ROC the level of diagnostic value accuracy of 87.05% includes good clustering.