Scenario Forecasting for Global Tourism

Abstract

This study provides innovative forecasts of the probabilities of certain scenarios of tourism demand. The scenarios of interest are constructed in relation to tourism growth and economic growth. The probability forecasts based on these scenarios provide valuable information for destination policy makers. The time-varying parameter panel vector autoregressive (TVP-PVAR) model is adopted for scenario forecasting. Both the accuracy rate and the Brier score are used to evaluate the forecasting performance. A global set of 25 tourism destinations is empirically examined, and the results confirm that the TVP-PVAR model with a time-varying error covariance matrix is generally a promising tool for forecasting. Our study contributes to tourism forecasting literature in advocating the use of scenario forecasting to facilitate industry decision making in situations wherein forecasts are defined by two or more dimensions simultaneously. In addition, it is the first study to introduce the TVP-PVAR model to tourism demand forecasting.

Tourism recovery amid COVID-19: The case of Lombardy, Italy

“…Overall, these initial attempts to forecast tourism recovery after the pandemic indicate the value of judgmental assessment and scenario forecasting in a context of high uncertainty and in line with other studies (Wu et al, 2020) highlight the value that this type of modeling can bring to policy makers. Moreover, the studies clearly indicate that more detailed information and accurate data would be essential to improve the models and provide greater value to decision makers.…”

“…In the case of no protective effect of the currently available vaccinations, the high likelihood of the "COVID new wave" scenario would increase with the disastrous effects forecasted in this proposed analysis. According to Wu et al (2020), scenario forecasting modeling can be divided into two main types: (1) a modeling approach that forecasts tourism demand given certain conditions or scenarios; and (2) the other approach that aims to predict the probability of a given scenario or condition. This research focuses on the first type.…”

The impact of public health emergencies on hotel demand - Estimation from a new foresight perspective on the COVID-19

“…Single forecasting mainly includes three types. The first is regression analysis based on statistics, and the representatives are VAR ( Wu, Cao, Wen, & Song, 2021 ) and ARMA family, i.e., ARIMA ( Jin et al, 2019 ), SARIMA ( Qiu et al, 2021 ), ARIMAX ( Hu, Qiu, Wu, & Song, 2021 ), and SARIMAX ( Song, Qiu, & Park, 2019 ; Wu, Song, & Shen, 2017 ). They are of better adaptability to linear data.…”

Tourism demand nowcasting using a LASSO-MIDAS model

“…independent variables), some studies have shown that a series of economic indicators including the destination's tourism prices, tourism prices of competitive destinations, tourist income and exchange rates are the most important factors affecting tourism demand (Song and Li, 2008). The most commonly used econometric models to analyze the causal relationship between tourism demand and its influencing factors include the autoregressive distributed lag (hereinafter, ARDL) model (Song et al, 2012), the error-correction model (hereinafter, ECM) (Goh, 2012), the vector autoregressive (VAR) model (Witt et al, 2004) and the time-varying parameter (hereinafter, TVP) model (Li et al, 2006;Wu et al, 2020).…”