Revenue management reinvented: Leveraging technical know-how to unlock hotel efficiency

Purpose – Revenue management (RM) is no longer just a tool for optimizing revenue but a strategic framework for driving net profits and sustainable growth. This study reimagines RM in green hotels as a dynamic, innovation-driven process, leveraging digitalization to create smarter, data-driven decision-making ecosystems. It explores the role of RM enablers—organizational culture (OC), demand prediction (DP), distribution networks (DN), competition analysis (CA), tailored pricing (TP), and regular evaluations (RE)—in boosting hotel efficiency. Additionally, it investigates how technical know-how (TKH) acts as a catalyst, mediating the link between RM practices and hotel efficiency. Methodology/Design/Approach – A multiple case study approach was applied, targeting green hotels in Saudi Arabia. Data were collected through 405 self-designed questionnaires distributed among hotel executives. Data envelopment analysis (DEA) was employed to calculate hotel efficiency scores. The random forest (RF) algorithm was utilized as a machine learning tool to predict model performance and identify feature importance metrics. Finally, structural equation modeling (SEM) was used to test the proposed hypotheses and mediation effects. Findings – The study identified a significant positive relationship between RM enablers and hotel efficiency. TP, DP, and CA emerged as the most influential enablers, with high contributions to model accuracy and node purity. While, OC, DN, and RE showing limited effects. Machine learning analysis confirmed the predictive accuracy and feature importance of the proposed model. The mediation analysis revealed that TKH strengthens the relationship between RM actions and hotel efficiency. Originality of the research – This study integrates advanced machine learning techniques with RM enablers to provide a comprehensive framework for enhancing hotel efficiency. It highlights the mediating role of TKH, offering new perspectives for RM literature.