Community Satisfaction Segmentation of Services at the Kudus Regency Population and Civil Registration Office Using K-Means Clustering

The Community Satisfaction Survey is an instrument used to evaluate the quality of public services. Although the Community Satisfaction Index of the Kudus Regency Population and Civil Registration Office (Disdukcapil Kabupaten Kudus) has consistently been classified as excellent, analyses based solely on average scores are insufficient to capture variations in satisfaction levels across different community groups. This study aims to segment community satisfaction using the K-Means Clustering algorithm and to generate evidence-based recommendations for service quality improvement. The dataset comprised 11,883 SKM records collected from the first quarter of 2024 to the fourth quarter of 2025, covering nine service quality indicators (U1–U9). The optimal number of clusters was determined using the Elbow Method and subsequently validated through the Silhouette Score and Davies-Bouldin Index. The results indicate that the optimal clustering solution is k = 2, yielding a Silhouette Score of 0.6410 and a Davies-Bouldin Index of 0.8265. The segmentation identified Cluster 1, consisting of 9,618 respondents (80.9%) with relatively high satisfaction levels, and Cluster 2, consisting of 2,265 respondents (19.1%) with relatively lower satisfaction levels. Service processing time, service requirements, service products, staff competency, and complaint handling were identified as the primary areas requiring improvement. The findings were subsequently implemented in a web-based analytics system to support evidence-based evaluation and decision-making for the continuous improvement of public service quality.