Bridging Tradition and Technology: A Systematic Review of Statistical and Machine Learning Applications in Hospitality Management

This systematic review examines the evolution, adoption, and impact of statistical analysis and machine learning (ML) techniques in the hospitality industry over the last two decades, with a particular emphasis on heritage tourism destinations in emerging economies. By analyzing peer-reviewed literature from Scopus, Web of Science, and leading hospitality journals (2000–2024), this paper identifies core application areas such as forecasting, dynamic pricing, customer segmentation, and guest review analysis. The review applies the Technology Acceptance Model (TAM), Diffusion of Innovation (DOI), and Organizational Readiness frameworks to explore adoption dynamics, barriers, and enabling factors. Findings reveal that while ML delivers superior predictive performance, statistical methods remain crucial for interpretability, low-data environments, and governance. Adoption challenges include skill gaps, infrastructure limitations, and perceived complexity, particularly in mid-market and heritage properties. The paper proposes a research agenda addressing functional suitability, interpretability, and policy-driven capacity building.