Tourism Forecasting Research Articles

Tourism forecasting by mixed-frequency machine learning

This study aims to establish the nonlinear relationship between high frequency Baidu search volumes, low frequency tourist arrivals and dummy variables and proposes a mixed-frequency machine learning model: the Bidirectional Long Short-Term Memory Mixed Frequency Data Sampling (BiLSTM-MIDAS) model. The empirical results of forecasting weekly tourist arrivals to Kulangsu and Jiuzhaigou Valley in China demonstrate that (1) BiLSTM-MIDAS can outperform benchmark models, which is also confirmed during the COVID-19 pandemic period; (2) Compared with the MIDAS model, establishing the nonlinear relationship between high frequency Baidu search volumes, low frequency tourist arrivals and dummy variables using BiLSTM-MIDAS can improve the roles of high-frequency search engines in forecasting tourism demand. This study represents the first attempt to apply machine learning methods for tourism demand forecasting with mixed-frequency data.

A novel two-stage combination model for tourism demand forecasting

The tourism literature has shown that a combination of tourism forecasting models can provide better performance than individual models. In the literature, the models to be combined are usually subjectively selected and authors focus on the combination method. In this study, a new direction is represented by the integration of forecasts from several models using a two-stage forecasting system. In stage I, a subset of the best available models is objectively selected according to their performance. Then, in stage II, linear and nonlinear combination methods are utilized to integrate the forecast values of the optimal subset. The empirical study using tourist arrivals in Hong Kong from five major source markets indicates that the proposed two-stage tourism forecasting system with linear combination substantially improves forecasting performance compared with benchmarks. This study also finds that when combining forecasts from different models, the linear combination method is more suitable than nonlinear AI models.

Tourism forecasts after COVID-19: Evidence of Portugal

Based on a comprehensive tourism forecasting competition using Portugal's regional data, we study the impact of COVID-19 on the ability of time series models to forecast tourism demand. We find that the stable seasonal patterns observed before the pandemic did not persist in 2020, but regions with higher weights of domestic tourism showed much lower tourism declines and seasonal shifts. Although this change was temporary, it caused significant forecast breakdowns in all methods. However, the intensity of the break differed across models leading to important changes in model rankings, especially in the most affected regions. We discuss the effectiveness and implications of applying straightforward data adjustments and how they can attenuate the pandemic impact on ex-post assessment of tourism forecasts.

Adaptive tourism forecasting using hybrid artificial intelligence model: a case study of Xi’an international tourist arrivals

Accurate forecasting of tourist demand is important to both business practitioners and government policymakers. In the past decade of rapid development of deep learning, many artificial intelligence methods or deep learning models have been built to improve prediction accuracy. But data-driven end-to-end deep network models usually require large data sets to support. For tourism forecasting, the sample is insufficient and many models are difficult to apply. In this article, we propose a novel hybrid model GM-LSTM, which combines the advantages of gray models and neural networks to achieve self-adaptive prediction with small samples. Specifically, the overall trend of tourism demand is captured by a first-order gray model and the non-linear residual fluctuation is characterized using a long short-term memory (LSTM) network with a rolling mechanism. The model is validated through a case study of up to 38 years of data on annual international tourist arrivals in Xi’an, China. The proposed GM-LSTM model achieved a predicted MAPE value of 11.88%, outperforming other time series models. The results indicate that our proposed hybrid model is accurate and efficient.

Temporal Study of Trend Analysis of Tourism Flow in Kullu District, Himachal Pradesh from 2008-2022 and its Seasonality for Tourism Forecasting

Accelerating growth of the tourism industry in the Kullu district of Himachal Pradesh over the past decade, contributing substantially to the district economy, and creating employment opportunities for locals, attracts the attention of researchers to a greater extent. This research paper presents insights into tourism dynamism in the study area, spanning the period from 2008 to 2022. It mainly uses secondary data collected from various government departments, tourist records, and surveys to analyze the trend and seasonality of tourism and further explore their implications for tourism forecasting. The findings of the study reveal considerable fluctuations in tourist influx over an analyzed period which could be attributed to various economic, social, and climatic factors. Further research explores seasonality, including peak and off-peak seasons, and the factors responsible for them. Cartographical methods and statistical methods such as (simple average method, annual growth rate, and coefficient of determination) are used to quantify seasonality, propose a tourism forecasting model on the basis of the former, and further check the accuracy of the model. The results of the study help in understanding the tourism dynamism in Kullu district in a better way and provide valuable insights for the policymakers, tourism authorities, and local residents for developing various strategies to optimize tourism opportunities, manage the quality of tourism services, and ensure the development of the study area.

Tourism Forecasting of “Unpredictable” Future Shocks: A Literature Review by the PRISMA Model

This study delves into the intricate process of predicting tourism demand, explicitly focusing on econometric and quantitative time series analysis. A meticulous review of the existing literature is carried out to comprehensively understand the various methods for forecasting “unpredictable” shocks of tourism demand on an ex-ante basis. The PRISMA method has been implemented. Drawing on scholarly research, this study pinpoints the critical challenges in accurately predicting tourism demand, making it a valuable resource for tourism professionals and researchers seeking to stay on top of the latest forecasting techniques. Moreover, the study includes an overview of published manuscripts from the current decade, with mixed results from the 32 manuscripts reviewed. The study concludes that virtual tourism, augmented reality, virtual reality, big data, and artificial intelligence all have the potential to enhance demand forecasting in time series econometrics.

Forecasting tourist flows in the COVID‐19 era using nonparametric mixed‐frequency VARs

AbstractIt is widely recognized that the tourism industry is susceptible to crisis or natural disaster. Although some literature has studied the consequences of the crisis and disaster, there remains a lack of study on the effect of COVID‐19. Against this background, this paper investigates the tourist flow forecasting by adopting an advanced nonparametric mixed‐frequency vector autoregressions model using Bayesian additive regression trees. This is particularly suitable for forecasting the presence of extreme observations, for example, the COVID‐19 pandemic. We investigate tourism demand forecasting using a large number of predictors, including industrial production index, CPI, exchange rate, economic policy uncertainty, Google trends index, and COVID‐19 infection rate. The data used for this study relate to tourist flows in Chinese Hong Kong, Japan, and South Korea. Empirical study demonstrates that this novel model significantly outperforms the traditional mixed‐frequency vector autoregressions model to quarterly tourist flow forecasting. Therefore, this model can significantly enhance tourism forecast accuracy in the face of extreme events. This study contributes to the literature on tourism forecasting and provides policymakers with policy implications.

Forecasting the Tourist Arrival Volumes and Tourism Income with Combined ANN Architecture in the Post COVID-19 Period: The Case of Turkey

Accurate forecasting of tourism demand and income holds paramount importance for both the tourism industry and the national economy. This study aims to address several objectives: (1) specify the best forecasting model in the prediction of tourist arrival volumes and tourism income for Turkey; (2) assess the degree of impact exerted by various determinants on the tourism forecasts; (3) generate forecasts for tourist arrival volumes and tourism income using the most suitable models; and (4) examine potential scenarios illustrating the ramifications of the Russia-Ukraine war on tourist arrival volumes and tourism income. The forecasting models employed in this study encompass a comprehensive set of statistical methods, including ETS, ARIMA, TRAMO-SEATS, X13, X11, STL, Grey, and their combinations with ANN. In the ANN models, exogenous variables such as the global financial crisis, the Turkey-Russia warplane crash crisis, the COVID-19 pandemic, and USD/TRY exchange rates are incorporated. The results unveil the identification of five superior models: ETS, Grey, hybrid ETS-ANN, hybrid Grey-ANN, and hybrid ARIMA-ANN models, which exhibit the lowest MAPE and sMAPE values. Forecasts for the forthcoming quarters are examined under two scenarios: assuming the continuity or cessation of the Russia-Ukraine war. Comparative analysis of the relative effects of exogenous variables indicates that COVID-19 has the most substantial impact on tourist arrival volumes, and tourism income is primarily influenced by the USD/TRY exchange rate.

COVID-19 pre-pandemic tourism forecasts and post-pandemic signs of recovery assessment for Portugal

Over the last decades the tourism sector has played an increasingly important role in the socio-economic development of Portugal. We analyze data from the last fifty years from Portugal, comparing non-pandemic forecasts derived with ARIMA time series models for the triennium 2020–2022, that is, forecasts obtained under the assumption that the COVID-19 pandemic would not have happened, to actual pandemic values as means to assess the impact of the pandemic on the annual numbers of guests and overnight stays in that period. The results show that full recovery has been reached in Portugal for the number of overnight stays in 2022, and individually in each main region of the country (mainland Portugal, Madeira and the Azores). However, the same cannot be said of the recovery of the number of guests, except for Madeira in 2022, whose recorded value exceeded the corresponding non-pandemic forecast value.

Forecast combination using grey prediction with fuzzy integral and time-varying weighting in tourism

PurposeTourism demand forecasting is vital for the airline industry and tourism sector. Combination forecasting has the advantage of fusing several forecasts to reduce the risk of inappropriate model selection for analyzing decisions. This paper investigated the effects of a time-varying weighting strategy on the performance of linear and nonlinear forecast combinations in the context of tourism.Design/methodology/approachThis study used grey prediction models, which did not require that the available data satisfy statistical assumptions, to generate forecasts. A quality-control technique was applied to determine when to change the combination weights to generate combined forecasts by using linear and nonlinear methods.FindingsThe empirical results showed that except for when the Choquet fuzzy integral was used, forecast combination with time-varying weights did not significantly outperform that with fixed weights. The Choquet integral with time-varying weights significantly outperformed that with fixed weights for all model combinations, and had a superior forecasting accuracy to those of other combination methods.Practical implicationsThe tourism sector can benefit from the use of the Choquet integral with time-varying weights, by using it to formulate suitable strategies for tourist destinations.Originality/valueCombining forecasts with time-varying weights may improve the accuracy of the predictions. This study investigated incorporating a time-varying weighting strategy into combination forecasting by using CUSUM. The results verified the effectiveness of the time-varying Choquet integral for tourism forecast combination.

Tourism in a Unique Destination

Tourism in Antarctica has been dynamically developed in recent decades, although it is located in a small geographical part of continent. The main reason that visitors plan a trip to the destination, when the opportunity is given, is the natural landscape and wildlife. In addition, overheating of the planet that causes ice to melt has enhanced the feeling of fear as there is severe environmental concern for the coming years. Space and seasonal exclusions make it even more special and the tourist product which is offered by this continent is expensive and requires a lot of preparation. Tourism activity in such a fragile environment has sparked several reactions in the past, mainly from the scientific community, as it is the main recipient of the negative effects of tourism. Furthermore, organized efforts have been made so that the offered product will promote more environmentally friendly trips that will affect the ecosystem as little as possible.
 The main objective of this research is to analyze this kind of tourism because of the need for new forms. The positive and negative impacts that tourism can have on the environment and the statistics on arrivals and countries of origin of tourists in recent years are analyzed. Moreover, the tourist packages that seem to be in the greatest demand of visitors are presented. The main research question of this paper is whether this destination can host intense tourism activity. Following an extensive bibliographic review, the research makes it clear that the study area cannot support strong tourism activity even though future tourism forecasts report an additional increase in arrivals.

Tourism forecasting research: a bibliometric visualization review (1999–2022)

Purpose This paper aims to analyze the research highlights, evolutionary process and future research directions in the field of tourism forecasting. Design/methodology/approach This study used CiteSpace to conduct a bibliometric analysis of 1,213 tourism forecasting articles. Findings The results show that tourism forecasting research has experienced three stages. The institutional collaboration includes transnational collaboration and domestic institutional collaboration. Collaboration between countries still needs to be strengthened. The authors’ collaboration is mainly based on on-campus collaboration. Articles with high co-citation are primarily published in core tourism journals and other relevant publications. The research content mainly pertains to tourism demand, revenue management, hotel demand and tourist volumes. Ex ante forecasting during the COVID-19 pandemic has broadened existing tourism forecasting research. The future forecasting research focuses on the rational use of big data, improving the accuracy of models and enhancing the credibility of forecasting results. Originality/value This paper uses CiteSpace to analyze tourism forecasting articles to obtain future research trends, which supplements existing research and provides directions for future research.

Daily tourism forecasting through a novel method based on principal component analysis, grey wolf optimizer, and extreme learning machine

AbstractAccurate forecasting tourism demand is crucial for improving the economic benefits of tourist attractions, but it is a challenging task. In this paper, we propose an effective daily tourism forecast model, principal component analysis‐grey wolf optimizer‐extreme learning machine (PCA‐GWO‐ELM), based on Baidu index data, holiday data, and weather data. Our model uses PCA to reduce the dimensionality of the data and employs the GWO to optimize the number of neural networks in the hidden layer of the ELM model, improving its forecast performance. We conduct an empirical study using the collected tourist data of Mount Siguniang. The results show that the proposed hybrid forecasting model outperforms other models in daily tourism demand forecasting, making it a potential candidate method for practitioners and researchers studying tourism demand forecasting.

Daily tourism demand forecasting before and during COVID-19: data predictivity and an improved decomposition-ensemble framework

ABSTRACT The global tourism industry is struggling to recover from the COVID-19 pandemic. During the COVID-19 pandemic, daily tourism forecasting is more critical than ever before in supporting decisions and planning. Considering the changes in tourist psyche and behaviour caused by COVID-19, this study attempts to investigate whether the statistical modelling methods can work reliably under the new normal when travel restrictions are eased or lifted. To this end, we first compare the predictivity of daily tourism demand data before and during COVID-19, and observe heterogeneous impacts across different geographical scales. Then an improved multivariate & multiscale decomposition-ensemble framework is proposed to forecast daily tourism demand. The empirical study indicates the superiority and practicability of the proposed framework before and during COVID-19. Finally, we call for more research on the comparability of tourism demand forecasting.

Forecasting hourly attraction tourist volume with search engine and social media data for decision support

Developing a tourism forecasting function in decision support systems has become critical for businesses and governments. The existing forecasting models considering spatial relations contain insufficient information, and the spatial aggregation of simple tourist volume series limits the forecasting accuracy. Using human-generated search engines and social media data has the potential to address this issue. In this paper, a spatial aggregation-based multimodal deep learning method for hourly attraction tourist volume forecasting is developed. The model first extracts the daily features of attractions from search engine data; then mines the spatial aggregation relationships in social media data and multi-attraction tourist volume data. Finally, the model fuses hourly features with daily features to make forecasting. The model is tested using a dataset containing several attractions with real-time tourist volume at 15-minute intervals from November 27, 2018, to March 18, 2019, in Beijing. And the empirical and Diebold-Mariano test results demonstrate that the proposed framework can outperform state-of-the-art baseline models with statistically significant improvements at the 1% level. Compared with the best baseline model, the MAPE values are reduced by 50.0% and 27.3% in 4A attractions and 5A attractions, respectively; and the RMSE values are reduced by 48.3% and 26.1%, respectively. The method in this paper can be used as a function embedded in the decision support system to help multi-department collaboration.

Diverse feature extraction techniques in internet search query to forecast tourism demand: An in-depth comparison

AbstractIt is an effective approach to improve forecasting by extracting effective information from large panels of search query data. Feature extraction techniques (FETs) can extract information from all features by creating new fewer features based on algebraic transformation; however, they have not been extensively investigated and compared for tourism forecasting. We employ five FETs to process multi-dimensional search query data, and build a bunch of models based on econometrics, machine learning, ensemble learning and hybrid methods. The improving performances of FETs based on tourism demand forecasting in Sanya after COVID-19 and in Macau before COVID-19 are evaluated. The results show that forecasting models with FETs outperform the benchmark model SARIMAX without FETs, which demonstrates the efficacy of FETs in search query data extraction. This study provides meaningful guidance for improving the quality of multi-dimensional data and optimizing tourism forecasting.

Data-Oriented Intelligent Judgment Platform for Red Tourism Industry in Northeast Guangdong Based on Tourism Big Data Clustering Algorithm

Defining big data in the context of tourism forecasting, summarizes the changes it brings to tourism business decision-making. The experimental part deals with the tourism metadata shared by the website, and applies a suitable clustering algorithm to generate the density pattern of the most frequently visited places by tourists. At the same time, it proposes a method to obtain local core categories through the discovery of maximal cliques, and proposes a parallelization of the maximal clique discovery algorithm. strategy, and then propose a parallel strategy for the entire algorithm and experiment on real datasets. Realize the intelligence, intelligence, and semantics of the video surveillance network, so that the police can be freed from the labor of watching video surveillance. Through the extraction and correlation of data feature attributes, the collision can obtain "object laws", so as to make efficient and accurate decisions.

An exploratory and comparative assessment of the tourist circulation at the level of some countries of the South-Eastern European union in the current pandemic context

The coronavirus epidemic (COVID19) has affected the global economy and the services sector. Quarantine measures related to travel restrictions have led to an unprecedented decline in the tourism industry with repercussions on tourism service providers, transport companies and state budgets. Travel is necessary for tourism, therefore, any factor that prevents travel can have a profound impact on the tourism industry. In the current pandemic context, the forecast in the field of tourist travel has played an important role in supporting the revival of this sector. In this study, econometric and interpretive methods were combined to predict the demand. In this study we approached a prediction model that is based on the seasonal stationary and adjustment of observed and FFT data. Experimental results show that the proposed prediction model has demonstrated a good medium-term forecast and can be used successfully in short and medium periods of time. For a certification of the exploratory evaluation of tourism forecasts there were comparatively analyzed the results obtained for three countries in south-eastern Central Europe, countries with similar natural and anthropic tourist resources (Bulgaria, Croatia and Romania).

Impact of decomposition on time series bagging forecasting performance

Time series bagging has been deemed an effective way to improve unstable modelling procedures and subsequent forecasting accuracy. However, the literature has paid little attention to decomposition in time series bagging. This study investigates the impacts of various decomposition methods on bagging forecasting performance. Eight popular decomposition approaches are incorporated into the time series bagging procedure to improve unstable modelling procedures, and the resulting bagging methods' forecasting performance is evaluated. Using the world's top 20 inbound destinations as an empirical case, this study generates one-to eight-step-ahead tourism forecasts and compares them against benchmarks, including non-bagged and seasonal naïve models. For short-term forecasts, bagging constructed via seasonal extraction in autoregressive integrated moving average time series decomposition outperforms other methods. An autocorrelation test shows that efficient decomposition reduces variance in bagging forecasts.

Editorial for Special Issue: “Tourism Forecasting: Time-Series Analysis of World and Regional Data”

This Special Issue was honored with six contribution papers embracing the subject of tourism forecasting [...]