Abstract
Purpose
The impact of demand fluctuation during crisis eventsis crucial to the dynamic pricing and revenue
management tactics of the hospitality industry. The aim of this paper is to improve the accuracy
of hotel demand forecast during periods of crisis or volatility, taking the 2019 social unrest in Hong
Kong as an example.
Methodology
Crisis severity, approximated by social media data, is combined with traditional time-series models,
including SARIMA, ETS and STL models. Models with and without the crisis severity
intervention are evaluated to determine under which conditions a crisis severity measurement
improves hotel demand forecasting accuracy.
Findings
Crisis severity is found to be an effective tool to improve the forecasting accuracy of hotel demand
during crisis. When the market is volatile, the model with the severity measurement is more
effective to reduce the forecasting error. When the time of the crisis lasts long enough for the time
series model to capture the change, the performance of traditional time series model is much
improved. The findings of this research is the incorporating social media data does not universally
improve the forecast accuracy. Hotels should select forecasting models accordingly during crises.
Originality
The originalities of the study are as follows. First, this is the first study to forecast hotel demand
during a crisis which has valuable implications for the hospitality industry. Second, this is also the
first attempt to introduce a crisis severity measurement, approximated by social media coverage,
into the hotel demand forecasting practice thereby extending the application of big data in the
hospitality literature.