<![CDATA[The development of human resources (HR) competencies in hospitals has become increasingly important in the era of digital healthcare transformation, which requires healthcare professionals to possess adaptive and data-driven capabilities. However, competency planning still faces several challenges, including limited training data (data sparsity), high variability in competency needs, and the limitations of conventional recommendation systems that are not yet capable of providing personalized and contextual recommendations. This study aims to develop a hybrid recommendation model, namely the Hierarchical Hybrid Knowledge-Based Recommendation Model (HHKBRM), to support more effective competency planning for hospital HR. This research adopts a quantitative experimental approach using secondary data, including HR profiles, training data, training histories, organizational data, and competency standards. The proposed model integrates knowledge-based, content-based filtering, and collaborative filtering approaches, supported by a competency level categorization technique. The analytical process includes data preprocessing, semantic mapping using term weighting and similarity measurement, and hybrid score computation to generate relevant training recommendations. The evaluation results indicate that the model achieves a Precision@10 of 0,054, Recall@10 of 0,300, NDCG@10 of 0,299, Hit Rate@10 of 0,300, and Diversity@10 of 0,849. These results demonstrate that the model is capable of providing relevant recommendations with good ranking quality and high diversity. Overall, the proposed model is effective in supporting data-driven competency planning for hospital human resources by balancing recommendation relevance and diversity.]]>
Copyrights © 2026
