<![CDATA[This study aims to analyze bus and minibus (Hiace) ticket booking patterns using the Partitioning Around Medoids (PAM) clustering method to support the optimization of public transportation operations. Managing fleet allocation and departure schedules is crucial for maintaining operational efficiency due to varying passenger mobility. This research applies the Knowledge Discovery in Databases (KDD) framework to analyze historical booking data obtained from the Transportation Agency of Aceh Tamiang Regency. The systematic stages include data selection, preprocessing, data transformation, application of the PAM algorithm, and comprehensive evaluation of the clustering results. A total of 76 transaction data records covering 15 main travel routes were analyzed and grouped into three distinct clusters based on booking frequency: stable-demand, high-demand, and very high-demand clusters. The evaluation results demonstrate that the PAM algorithm successfully identifies specific demand patterns across different routes with a Total Cost value of 2.0, indicating a highly stable and well-structured clustering outcome. Furthermore, this model is integrated into a desktop-based system to facilitate efficient data processing. Ultimately, the findings provide valuable insights into passenger demand characteristics for each route, which can actively support strategic decision-making in scheduling, effective fleet allocation, and overall service management improvement.]]>
