<![CDATA[State receivables management is one of the strategic functions in state financial management aimed at maintaining the quality of state assets and supporting the optimization of state revenue. Differences in performance characteristics among receivables management units necessitate an approach capable of objectively identifying performance groups as a basis for formulating more effective management strategies. This study aims to analyze the performance segmentation of state receivables management based on performance indicators, namely administrative fee revenue, reduction in outstanding receivables, and settlement of state receivables case files, using a K-Means Clustering approach. The study employs a quantitative method with data mining analysis on 64 observations obtained from state receivables management data. The optimal number of clusters was determined using the Davies-Bouldin Index (DBI). The results show that the best model was obtained with three clusters (K=3), with a DBI value of 0.856, the lowest value compared to other cluster alternatives. The segmentation results produced three performance groups with distinct characteristics. The first cluster consists of 45 observations (70.3%), showing moderate performance characteristics. The second cluster consists of 9 observations (14.1%) with relatively high levels of administrative fee revenue, reduction in outstanding receivables, and case file settlement, categorizing it as a high-performing group. Meanwhile, the third cluster consists of 10 observations (15.6%), showing high case file settlement productivity but relatively lower reduction in outstanding receivables. The findings indicate that the K-Means Clustering method can provide a more comprehensive performance mapping and support the formulation of more targeted managerial strategies according to the characteristics of each group to improve the effectiveness of state receivables management.]]>
Copyrights © 2026
