Content uploaded by Bing Pan
Author content
All content in this area was uploaded by Bing Pan on Nov 06, 2014
Content may be subject to copyright.
A preview of the PDF is not available
Predicting Hotel Demand Using Destination Marketing Organization’s Web Traffic Data
Abstract and Figures
This study uses the web traffic volume data of a destination marketing organization (DMO) to predict hotel demand for the destination. The results show a significant improvement in the error reduction of ARMAX models, compared with their ARMA counterparts, for short-run forecasts of room nights sold by incorporating web traffic data as an explanatory variable. These empirical results demonstrate the significant value of website traffic data in predicting demand for hotel rooms at a destination, and potentially even local businesses' future revenue and performance. The implications for future research on using big data for forecasting hotel demand is also discussed.
Figures - uploaded by Bing Pan
Author content
All figure content in this area was uploaded by Bing Pan
Content may be subject to copyright.
... Researchers have used online search data for different applications within the tourism industry. While some have focused on forecasting the hotel demand for particular cities or countries [6][7][8], others such as Feng et al. [9] and Gawlik et al. [10] have assessed the effectiveness of search data in forecasting the number of tourists rather than hotel demand. ...
... Several research works have successfully employed Internet data to forecast the demand for hotel rooms and flights for different forecasting horizons [6][7][8]32]. Similar to unemployment forecasting, tourism research has been extended to predict the volume of visitors to cities [33,34] and countries [5,9,10,25,26]. ...
This study examined whether the behaviour of Internet search users obtained from Google Trends contributes to the forecasting of two Australian macroeconomic indicators: monthly unemployment rate and monthly number of short-term visitors. We assessed the performance of traditional time series linear regression (SARIMA) against a widely used machine learning technique (support vector regression) and a deep learning technique (convolutional neural network) in forecasting both indicators across different data settings. Our study focused on the out-of-sample forecasting performance of the SARIMA, SVR, and CNN models and forecasting the two Australian indicators. We adopted a multi-step approach to compare the performance of the models built over different forecasting horizons and assessed the impact of incorporating Google Trends data in the modelling process. Our approach supports a data-driven framework, which reduces the number of features prior to selecting the best-performing model. The experiments showed that incorporating Internet search data in the forecasting models improved the forecasting accuracy and that the results were dependent on the forecasting horizon, as well as the technique. To the best of our knowledge, this study is the first to assess the usefulness of Google search data in the context of these two economic variables. An extensive comparison of the performance of traditional and machine learning techniques on different data settings was conducted to enable the selection of an efficient model, including the forecasting technique, horizon, and modelling features.
... Mahmood and Mubarik (2020) Supply chains (Aryal et al., 2018;Bansal et al., 2020;Baryannis et al., 2019;Brinch, 2018;Chehbi-Gamoura et al., 2020;Gawankar et al., 2020;Gunasekaran et al., 2017;Huang et al., 2018;Ivanov et al., 2019;Kache and Seuring, 2017;Li and Wang, 2017;Mukherjee andSinha, 2018, 2018b;Ö berg and Graham, 2016;Roβmann et al., 2018;Sanders, 2016) Multiple use cases (Bȃlan, 2018;Chen, 2018;Corbett, 2018;Elia et al., 2020;Fisher and Raman, 2018;Foster et al., 2018;Martin, 2016 (Dong and Yang, 2020;Erevelles et al., 2016;Jabbar et al., 2020;Martin, 2016;Sivarajah et al., 2020;Trusov et al., 2016;Wedel and Kannan, 2016;Xu et al., 2016;Yang et al., 2014Yang et al., , 2020 Operations and production (Chien et al., 2017;Choi et al., 2018;Cohen, 2018;Farooqui et al., 2020;Frank et The use of big data in private organizations is also related to the business area of supply chains (Chehbi-Gamoura et al., 2020, 2020bÖ berg and Graham, 2016), where the management of vast amounts of information is particularly useful to discover new collaboration partners and improve the use of green resources (Melander and Pazirandeh, 2019). Additional benefits are associated with reducing uncertainty in supply chain operations and increasing transparency between various stakeholders (Roβmann et al., 2018;Chubing Zhang et al., 2020). ...
... This preliminary analysis allows firms to increase their knowledge of their customer base. Finally, in the study by (Yang et al., 2014), the interpretation of web traffic data improved the prediction of hotel demand, revenues, and performance. ...
... Kwok and Yu (2012) observed that the use of photos and statuses by the restaurant chain owners was far more effective in getting the attention of the customers. Web traffic data can be a source of estimating the demand for a product (Yang et al., 2013). It could become a useful source of data for implementing targeted promotional activities for the industry. ...
The paper aims to synthesise the knowledge on novel digital technologies that have brought a transformation in the tourism and hospitality’s products, pricing, place, and promotional (together known as marketing mix) strategies. The paper carries out a bibliometric analysis using VOSviewer, Science of Science (Sci2), and Gephi on 1424 journal papers published in Web of Science-indexed journals from 1995 to 2022. The descriptive analysis suggests that there has been a sudden increase in the publication trend and much of the focus of academics is on the influence of digital transformation (DT) on the promotion of tourism. The results from thematic analysis highlight a lack of research on using technology to extend the life cycle of products, moving up in product layers, balancing the 4Ps in the tourism marketing mix, and increasing marketing mix effectiveness. The paper recommends studying digitalisations effects on the tourism product line, pricing policy, knowledge sharing, and technology-led co-creation.
... In recent years' internet search engines and social media have become important in the way people inform themselves. When people type in queries on search engines or use search query through social media they implicitly express their interest in the object of the query (Yang et al., 2014;Yang et al., 2015). This research provides a framework for predicting tourism demands using Google Trends. ...
This article explores the usefulness of information from Google trends to predict the tourism demands. When a tourist interacts with the internet through a search engine, a website, or a social media platform, the traces of the interaction can be captured, stored, and analyzed. Research on most visited cities on the world showed how Amsterdam become a standout among the most visited city on the planet. Related works demonstrated that Google Trends have some values to predict the tourism industry, our new idea for this study is to utilize our model Hidden Markov Model (HMM) with Google Trends data and historical data from the electronic database Central Bureau Statistic (CBS) StatLine 2018 to predict the tourism demands in Amsterdam and to compare our method with existing methods. The search engine user needs to utilize search queries (keywords) identified with the tourism industry in Amsterdam will be extracted using application programming interface(API). We have trained and tested data by the Hidden Markov Model to predict next month tourists number in Amsterdam, For the two existing methods we tune their parameters to get the best results. Our experiments over real data from CBS StatLine demonstrate that our method not only outperforms the traditional and existing methods but also provides controllability to tourism prediction.
... The rich data could provide a competitive advantage to any business that knows how to utilize it properly. For example, studies have demonstrated the efficacy of using search engine queries or a local destination marketing organization's web traffic data to forecast local hotels' occupancy rates (Yang, Pan, and Song 2014). Many websites exist for mining social media mentions for businesses and destinations. ...
Also known as travel technology or "eTravel", eTourism refers to a phenomenon and research area in which the adoption of information and communication technology (ICT) by tourists and businesses transforms the processes and the value chains in the industry. This development changes the process within a business or organization while reconfiguring the landscape of tourism commerce (Buhalis 2003). As a service industry, tourism is specifically influenced and transformed by ICT development. Typically, its products are complex and intangible; their production and consumption are inseparable; its inventories of goods and services are perishable; and the consumption experience varies depending on individual tourists at different times. In addition, the industry is composite in nature and requires great effort in coordinating different types of services and the delivery of rich information in order to reduce the uncertainty during service encounters. Its businesses need to act swiftly to sell unsold inventories to maximize revenue and profit. As an information-intensive industry, tourism requires ICT, and the two influence each other. Development of eTourism The dynamic of eTourism is closely related to the development of ICT. In the past, airlines manually managed reservations through a card system, and hotels tracked inventories through colored tapes posted on walls. As soon as the first electronic general-purpose computer, ENIAC, appeared in 1946, airlines started the wave of adoption: American Airlines installed the first automated booking system in the same year. Other airlines and hotel chains started to build computer reservation systems in the 1960s and 1970s. In the 1980s, such airline and hotel systems started to merge into global distribution systems, allowing travel agencies to book multiple services. During the 1990s, the wide adoption of the internet created new avenues of distribution and ways of reaching tourists directly, causing the internet to start reconfiguring the structure of tourism (Buhalis and Law 2008). In the early 21 st century, social media and mobile technologies
... Önder (2017) compares four forecasting models with Google Trends, the research results confirm the effect of Google Trends. In general, the role of Google trend as an explanatory variable in improving the prediction accuracy has been confirmed (Önder & Gunter, 2016;Yang, Pan, & Song, 2014). ...
... Several studies have considered internet data as a complement to traditional data and as a new feature; hence, they employed big data to understand tourist satisfaction [35]. One of the major advantages of online data provided by search engines and social media is that it is real-time [36]. Two kinds of online data have emerged in the tourist arrivals prediction literature: search engine data and social media data [13]. ...
Online review data attracts the attention of researchers and practitioners in various fields, but its application in tourism is still limited. The social media data can finely reflect tourist arrivals forecasting. Accurate prediction of tourist arrivals is essential for tourism decision-makers. Although current studies have exploited deep learning and internet data (especially search engine data) to anticipate tourism demand more precisely, few have examined the viability of using social media data and deep learning algorithms to predict tourism demand. This study aims to find the key topics extracted from online reviews and integrate them into the deep learning model to forecast tourism demand. We present a novel forecasting model based on TripAdvisor reviews. Latent topics and their associated keywords are captured from reviews through Latent Dirichlet Allocation (LDA), These generated features are then employed as an additional feature into the deep learning (DL) algorithm to forecast the monthly tourist arrivals to Hong Kong from USA. We used machine learning models, artificial neural networks (ANNs), support vector regression (SVR), and random forest (RF) as benchmark models. The empirical results show that the proposed forecasting model is more accurate than other models, which rely only on historical data. Furthermore, our findings indicate that integration of the topics extracted from social media reviews can enhance the prediction.
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.
The purpose of this chapter is to compile accumulated evidence of research on big data in the hotel industry, in order to generate a documentary reference of its possible applications in business strategy. A systematic literature review was chosen through the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) methodology. This methodology includes the steps of identification, screening, eligibility, and inclusion. In addition, a bibliometric and content analysis was applied to the documents with the support of Excel and VOSviewer software. A total of 295 articles were identified in the Scopus database, published in the period from 2013 to 2022. The selected documents met thematic relevance criteria, and 51 studies were examined. The results show the recent and emerging development of big data as a research topic in hotel companies. Additionally, the thematic analysis resulted in two categories: (a) big data research focus and (b) big data applications in the hospitality industry. Exploring customer satisfaction through the analysis of online reviews has been the most recurrent purpose of research. In the end, proposals are made for application in the hotel industry including the implementation of recommendation systems to meet the current needs of tourists, initiatives and interventions for the improvement of statistical data quality and transfer mechanisms, as well as the training of specialists in big data for decision-making and problem-solving.KeywordsBig dataHotel companiesLiterature reviewBusiness strategy
This study examines the determinants of tourist arrivals at hotels and short-stay accommodations for nine EU countries from January 2010 to March 2022. We identify four driving channels of foreign and domestic tourism flows: a traditional, a sentiment, a technological and a health channel. The latter comprises two novel variables: the museum search interest and the infectious disease equity market volatility tracker. The results reveal that traditional and new drivers related to market sentiments and interest in online tourism experiences affect arrivals. Notably, there is a substitution effect between online and in-presence tourism, and the larger the uncertainty, the more substantial the reduction in tourist arrivals. COVID-19 has affected especially Spain and Italy and more foreign than domestic tourists.
This paper describes early work trying to predict stock market indicators such as Dow Jones, NASDAQ and S&P 500 by analyzing Twitter posts. We collected the twitter feeds for six months and got a randomized subsample of about one hundredth of the full volume of all tweets. We measured collective hope and fear on each day and analyzed the correlation between these indices and the stock market indicators. We found that emotional tweet percentage significantly negatively correlated with Dow Jones, NASDAQ and S&P 500, but displayed significant positive correlation to VIX. It therefore seems that just checking on twitter for emotional outbursts of any kind gives a predictor of how the stock market will be doing the next day.
The paper provides a comprehensive review of the recent development of revenue management in different industries. We discuss research on different revenue management strategies including pricing, auctions, capacity control, overbooking and forecasting. Related issues such as economic concerns, customer perception, competition and consolidation, implementation, performance evaluation, and common techniques and approaches used for solving revenue management problems are also discussed. Finally, we give our suggestion on some important areas that warrant further research.
Tourism demand is the foundation on which all tourism-related business decisions ultimately rest. Governments and companies such as airlines, tour operators, hotels, cruise ship lines, and recreation facility providers are interested in the demand for their products by tourists. The success of many businesses depends largely or totally on the state of tourism demand, and ultimate management failure is quite often due to the failure to meet market demand. This book introduces students, researchers and practitioners to the modern developments in advanced econometric methodology within the context of tourism demand analysis, and illustrates these developments with actual tourism applications. The concepts and computations of modern advanced econometric modelling methodologies are introduced at a level that is accessible to specialists and non-specialists alike. The methodologies introduced include general-to-specific modelling, cointegration, vector autoregression, time varying parameter modelling, panel data analysis and the almost ideal demand system (AIDS). In order to help the reader understand the various methodologies, extensive tourism demand examples are provided throughout the volume.
Smith Travel Research's estimates of lodging occupancy in Virginia Beach have improved over time, most likely because its sampling accuracy has increased.
