The Family Planning (KB) program in Kalirejo Lawang Village faces challenges in the process of clustering active participants, which is time-consuming and prone to errors. Based on these challenges, a clustering solution using the K-Means algorithm was proposed. Experiments were conducted by testing the number of clusters from 2 to 8 and evaluating them using the silhouette score. The results of the study showed that the optimal number of clusters is two, as indicated by a silhouette score of 0.447. This value represents the best clustering quality compared to other cluster numbers, where the scores for clusters 3 to 8 did not exceed this value. This demonstrates that clustering into two groups provides the most optimal results. Lower scores for clusters 3 to 8 indicate that dividing the clusters into more groups did not create clear separations or worsened the cohesion within clusters. The conclusion of this study shows that the K-Means method can be applied and is reliable for clustering active KB participants in Kalirejo Lawang Village. With its speed and accuracy, K-Means offers a significant solution to improving the efficiency of the KB program at the village level. The practical implication of this research is to provide a more structured basis for planning and decision-making in the KB program at the village level. These findings mark an important step in optimizing the management of KB program data, opening opportunities for broader implementation in other areas.
Read full abstract