K-MEANS CLUSTER COUNT OPTIMIZATION WITH SILHOUETTE INDEX VALIDATION AND DAVIES BOULDIN INDEX (CASE STUDY: COVERAGE OF PREGNANT WOMEN, CHILDBIRTH, AND POSTPARTUM HEALTH SERVICES IN INDONESIA IN 2020)

One of the causes increasing maternal mortality rate in Indonesia is declining performance health services each Indonesian province. To overcome decline performance, namely by determining advance provinces that need to be prioritized for grouping 34 Indonesia. This study aims obtain best provincial results so it can prioritize right provinces. methods are suitable K-Means because simple and easy implement. The disadvantage sensitive number initial clusters, Silhouette Index Davies Bouldin validation used optimal clusters with stable consistent results. healthcare data pregnant women, childbirth, postpartum K=2, 3, 4 as cluster number. objects grouped similarities using Euclidean Manhattan distances. result obtained was K=2 Manhattan, where highest value 0,658685 lowest 0,3561214 which met criteria cluster.