This paper is to produce different scenarios in forecasts for international tourism demand, in light of the COVID-19 pandemic. By implementing two distinct methodologies (the Long Short Term Memory ...neural network and the Generalized Additive Model), based on recent crises, we are able to calculate the expected drop in the international tourist arrivals for the next 12 months. We use a rolling-window testing strategy to calculate accuracy metrics and show that even though all models have comparable accuracy, the forecasts produced vary significantly according to the training data set, a finding that should be alarming to researchers. Our results indicate that the drop in tourist arrivals can range between 30.8% and 76.3% and will persist at least until June 2021.
•We forecast international tourist arrivals from July 2020 to June 2021.•We use a GAM model and an LSTM network.•The training sets include three recent crises and a worst-case scenario.•The drop in tourist flows ranges from 30.8% to 76.3%.•Different training sets yield different forecasts.
Forecasting tourism recovery amid COVID-19 Zhang, Hanyuan; Song, Haiyan; Wen, Long ...
Annals of tourism research,
March 2021, 2021-Mar, 2021-03-00, 20210301, Letnik:
87
Journal Article
Recenzirano
Odprti dostop
The profound impact of the coronavirus disease 2019 (COVID-19) pandemic on global tourism activity has rendered forecasts of tourism demand obsolete. Accordingly, scholars have begun to seek the best ...methods to predict the recovery of tourism from the devastating effects of COVID-19. In this study, econometric and judgmental methods were combined to forecast the possible paths to tourism recovery in Hong Kong. The autoregressive distributed lag-error correction model was used to generate baseline forecasts, and Delphi adjustments based on different recovery scenarios were performed to reflect different levels of severity in terms of the pandemic's influence. These forecasts were also used to evaluate the economic effects of the COVID-19 pandemic on the tourism industry in Hong Kong.
Display omitted
•A mixed approach is proposed to forecast tourism demand in light of COVID-19.•Quantitative methods are integrated with qualitative, judgmental adjustments.•The ARDL-ECM is used to produce baseline forecasts of tourist arrivals to Hong Kong.•A scenario-based Delphi approach is used to adjust the forecasts in view of crises.•Forecasting recovery potential and tourism income losses benefits crisis management.
Advances in tourism demand forecasting immensely benefit tourism and other sectors, such as economic and resource management studies. However, even for novel AI-based methodologies, the challenge of ...limited available data causing model overfitting and high complexity in forecasting models remains a major problem. This study proposes a novel group-pooling-based deep-learning model (GP–DLM) to address these problems and improve model accuracy. Specifically, with our group-pooling method, we advance the tourism forecasting literature with the following findings. First, GP–DLM provides superior accuracy in comparison with benchmark models. Second, we define the novel dynamic time warping (DTW) clustering quantitative approach. Third, we reveal cross-region factors that influence travel demands of the studied regions, including “travel blog,” “best food,” and “Air Asia.”
•Our AI-based deep-learning approach contributes to higher forecasting accuracy.•Our innovative deep-learning model alleviates the limited data availability.•With our new pooling method, we significantly reduce model overfitting.•We reveal similar cross-country demand patterns for the Asia-Pacific regions.
This study proposes a hierarchical pattern recognition method for tourism demand forecasting. The hierarchy consists of three tiers: the first tier recognizes the calendar pattern of tourism demand, ...identifying work days and holidays and integrating “floating holidays.” The second tier recognizes the tourism demand pattern in the data stream for different calendar pattern groups. The third tier generates forecasts of future tourism demand. Evidence from daily tourist visits to three attractions in China shows that the proposed method is effective in forecasting daily tourism demand. Moreover, the treatment of “floating holidays” turns out to be more effective and flexible than the commonly adopted dummy variable approach.
Based on internet big data from multiple sources (i.e., the Baidu search engine and two online review platforms, Ctrip and Qunar), this study forecasts tourist arrivals to Mount Siguniang, China. Key ...findings of this empirical study indicate that (a) tourism demand forecasting based on internet big data from a search engine and online review platforms can significantly improve forecasting performance; (b) compared with tourism demand forecasting based on single-source data from a search engine, demand forecasting based on multisource big data from a search engine and online review platforms demonstrates better performance; and (c) compared with tourism demand forecasting based on online review data from a single platform, forecasting performance based on multiple platforms is significantly better.
•This study forecasts weekly tourism arrivals to a national park in China.•Internet big data from a search engine and online review platforms are employed.•Findings suggest the superiority of multiple-source big data forecasting.•Forecasting based on online review data from multiple platforms is preferred.
The tourism sector, with its perishable nature of products, requires precise estimation of demand. To this effect, we propose a deep learning methodology, namely Bayesian Bidirectional Long ...Short-Term Memory (BBiLSTM) network. BiLSTM is a deep learning model, and Bayesian optimization is utilized to optimize the hyperparameters of this model. Five experiments using the tourism demand data of Singapore are conducted to ascertain the validity and benchmark the proposed BBiLSTM model. The experimental findings suggest that the BBiLSTM model outperforms other competing models like Long Short-Term Memory (LSTM) network, Support Vector Regression (SVR), Radial Basis Function Neural Network (RBFNN) and Autoregressive Distributed Lag Model (ADLM). The study contributes to tourism literature by proposing a superior deep-learning method for demand forecasting.
•A novel deep learning model is proposed for tourism demand forecasting.•Bayesian optimization is employed to optimize the hyperparameters.•The effectiveness of the proposed model is validated via robustness analysis with multiple experiments.•The effect of multi-lagged variables on model performance is studied.
Croatia is an important and widely recognizable tourist destination. The importance of tourism in Croatia is manifested in many aspects, and the share of income from tourism in BDP in Croatia is ...around 20%. The most numerous guests in Croatia are foreign guests, mostly from Germany, Austria, Slovenia, Italy and Poland. In this paper, foreign tourism demand in the Republic of Croatia was analyzed and impact of five selected variables on foreign tourism demand is estimated: gross domestic product of countries from which tourists come from, prices in Croatia, prices in competing countries, distance between countries and accommodation capacities. The analysis was carried out for the nine-year time period from 2010 to 2018 based on data for 32 countries from which tourists come, and OLS model, a panel model with fixed effects and a panel model with random effects were estimated. The adequacy of the model was tested with the Hausman test, Breusch-Pagan Lagrange test and F-test. A panel model with Driscoll-Kraay standard errors was estimated. The estimated model showed that the gross domestic product of the countries from which the tourists arrive has a statistically significant and positive influence on the foreign tourism demand in Croatia, while at a significance level of 10% the accommodation capacity in Croatia has a positive and statistically significant influence. The impact of other variables taken into account was not statistically significant.
Hrvatska je važna i nadaleko prepoznatljiva turistička destinacija. Važnost turizma u Hrvatskoj se očituje kroz mnoge aspekte, a udio prihoda od turizma u BDP-u Hrvatske se kreće oko 20%. Najbrojniji gosti u Hrvatskoj su inozemni gosti i to pretežito iz Njemačke, Austrije, Slovenije, Italije te Poljske. U ovom radu analizirana je inozemna turistička potražnja u Republici Hrvatskoj te je za pet odabranih varijabli procijenjen njihov utjecaj na inozemnu turističku potražnju: bruto domaći proizvod zemalja iz kojih turisti dolaze, cijene u Hrvatskoj, cijene u konkurentskim zemljama, udaljenost zemalja i smještajni kapaciteti. Analiza je provedena za devetogodišnje vremensko razdoblje od 2010. do 2018. godine na temelju podataka za 32 zemlje iz koji turisti dolaze u Hrvatsku, a procijenjeni su združeni OLS model te panel model s fiksnim efektima i panel model sa slučajnim efektima. Prikladnost modela ispitana je Hausmanovim testom, Breusch-Pagan Lagrangeovim testom te F-testom. Procijenjen je panel model s Driscoll-Kraay standardnim pogreškama. Procijenjenim modelom pokazalo se da statistički značajan i pozitivan utjecaj na dolazak inozemnih turista u Hrvatsku ima bruto domaći proizvod zemalja iz kojih turisti dolaze, dok na razini značajnosti od 10% pozitivan i statistički značajan utjecaj ima i varijabla smještajnog kapaciteta u Hrvatskoj. Utjecaj ostalih varijabli uzetih u obzir se nije pokazao statistički značajnim.
•Theoretical foundations for gravity models in the context of tourism are provided.•Gravity models for tourism demand are derived from consumer choice theory.•Gravity models are linked to aggregated ...tourism demand equations.•Estimation procedures for gravity models are suggested.
Neglected by the tourism demand literature for the last decades, gravity models have re-emerged as a way for modeling tourism demand when the role of structural factors on tourism has to be evaluated. From the initial formulation of the gravity model, more sophisticated specifications have been developed including a more complete set of explanatory variables and allowing differentiation between origin and destination countries. In this paper, we propose a theoretical background to the gravity model for bilateral tourism flows derived from the individual utility theory. The issues in distinguishing the recent versions of gravity models from aggregated demand models are shown and the suitability of this methodology when structural factors have to be evaluated and quantified in the context of tourism demand is discussed.
The novel coronavirus (COVID-19) is challenging the world. With no vaccine and limited medical capacity to treat the disease, nonpharmaceutical interventions (NPI) are the main strategy to contain ...the pandemic. Unprecedented global travel restrictions and stay-at-home orders are causing the most severe disruption of the global economy since World War II. With international travel bans affecting over 90% of the world population and wide-spread restrictions on public gatherings and community mobility, tourism largely ceased in March 2020. Early evidence on impacts on air travel, cruises, and accommodations have been devastating. While highly uncertain, early projections from UNWTO for 2020 suggest international arrivals could decline by 20 to 30% relative to 2019. Tourism is especially susceptible to measures to counteract pandemics because of restricted mobility and social distancing. The paper compares the impacts of COVID-19 to previous epidemic/pandemics and other types of global crises and explores how the pandemic may change society, the economy, and tourism. It discusses why COVID-19 is an analogue to the ongoing climate crisis, and why there is a need to question the volume growth tourism model advocated by UNWTO, ICAO, CLIA, WTTC and other tourism organizations.
Traditional tourism demand forecasting models may face challenges when massive amounts of search intensity indices are adopted as tourism demand indicators. Using a deep learning approach, this ...research studied the framework in forecasting monthly Macau tourist arrival volumes. The empirical results demonstrated that the deep learning approach significantly outperforms support vector regression and artificial neural network models. Moreover, the construction and identification of highly relevant features from the proposed deep network architecture provide practitioners with a means of understanding the relationships between various tourist demand forecasting factors and tourist arrival volumes.
This article also launches the Annals of Tourism Research Curated Collection on Tourism Demand Forecasting, a special selection of research in this field
•A deep learning method is presented to forecast tourist demand.•The introduced method represents an automated approach to feature engineering.•The method overcomes the linearity limitations of existing lag order detection.•The case study on Macau confirms the superior performance of the proposed approach.•The introduced method can be applied to different tourism destinations.