Human resource evaluation plays a crucial role in supporting organizational performance, particularly in determining outstanding employees objectively and efficiently. At Permata Keluarga Hospital, the employee performance assessment process was still conducted manually, resulting in time-consuming data processing and unmeasured accuracy levels. This study aims to implement a data mining approach using the C5.0 decision tree algorithm to classify employee performance and support decision-making in selecting outstanding employees. The research employed the CRISP-DM methodology, including business understanding, data understanding, data preparation, modeling, evaluation, and deployment stages. The dataset consisted of 250 employee performance records with attributes such as competence, intellectual ability, accuracy, communication, loyalty, teamwork, discipline, initiative, and attitude. Data were processed through preprocessing and split validation with an 80:20 ratio for training and testing. The modeling results indicate that the C5.0 algorithm successfully generated a decision tree with 12 classification rules, where teamwork emerged as the root node, followed by discipline, initiative, and attitude. The implementation of the model into a web-based system enabled automatic classification and improved the efficiency and objectivity of performance evaluation. Overall, the application of the C5.0 algorithm effectively supports decision-making in determining outstanding employees.