Forecasting hotel room prices in selected GCC cities using deep learning. (March 2020)

• Record Type: Journal Article
• Authors: Al Shehhi, Mohammed; Karathanasopoulos, Andreas
• Is Part Of: Journal of hospitality and tourism management. Volume 42(2019)
• Page Start: 40
• Page End: 50
• Publication Date: 2020-03
• Subjects: Hotel forecasting -- Analytics -- Deep learning -- Artificial intelligence; Hospitality industry -- Management -- Periodicals; Tourism -- Management -- Periodicals; Hospitality industry -- Australia -- Management -- Periodicals; Tourism -- Australia -- Management -- Periodicals; Hospitality industry -- Management; Tourism -- Management; Australia; Electronic journals; Periodicals; 338.4791068
• DOI: 10.1016/j.jhtm.2019.11.003
• Languages: English
• ISSNs: 1447-6770

Abstract

Abstract: This paper extends the research on hotel room prices using traditional and non-traditional statistical models following the analysis by Karathanasopoulos and Shehhi (2018), which discusses how hotel prices can be easily predicted. In this paper, we employed four forecasting models: the seasonal autoregressive integrated moving average (SARIMA) model, the restricted Boltzmann machine as a deep belief network model, the polynomial smooth support vector machine model, and finally, the adaptive network fuzzy interference system (ANFIS) model. Research data was obtained from Smith Travel Research. In this study, we apply advanced forecasting models based on machine learning and artificial intelligence to the hospitality sector. Some of the models used in this study, such as the ANFIS model, contribute to the research conducted in GCC region. The goal of the research was to contribute to the academic literature and assist hotel operators and decision-makers in setting appropriate strategies.