Enhancing the accuracy of revenue management system forecasts: The impact of machine and human learning on the effectiveness of hotel occupancy forecast combinations across multiple forecasting horizons

• Zvi Schwartz ^[1] ; Timothy Webb ^[1] ; Jean-Pierre van der Rest ^[2] ; Larissa Koupriouchina ^[3]
  1. [1] University of Delaware

     University of Delaware

     Estados Unidos

     
  2. [2] Leiden University

     Leiden University

     Países Bajos

     
  3. [3] Hotelschool The Hague, the Netherlands

  Mostrar afiliaciones +
• Localización: Tourism economics: the business and finance of tourism and recreation, ISSN 1354-8166, Vol. 27, Nº. Extra 2, 2021 (Ejemplar dedicado a: The Economics of Revenue Management in Hospitality and Tourism), págs. 273-291
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • Reporting on three separate studies in the context of hotel revenue management systems, this article explores the interaction between two established methods of accuracy enhancement—forecast combinations and learning. In line with theoretical considerations, our empirical investi-gation suggests that as learning occurs, the capacity of combinations to improve forecast accuracydiminishes in scenarios where the combined elements are independent of each other. Conversely,in the more realistic typical scenario of user overrides of system forecasts, where the elements ofthe combinations are dependent, the learning-driven efficacy of forecast combinations appears tovary across forecasting horizons. We find no impact of learning on combination effectiveness in the shorter forecasting horizons of 21 days or less and a surprisingly positive impact in the longerhorizons. This counterintuitive finding has important practical implications for hotel revenue management practices.