Forecasting tourism demand with multisource big data
Annals of Tourism ResearchPublished 24 April 2020Open access
Hengyun Li, Mingming Hu, Gang Li
Citations226
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Findings of this empirical study indicate that tourism demand forecasting based on internet big data from a search engine and online review platforms can significantly improve forecasting performance.
Abstract
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.
Keywords
Social SciencesBusiness, Management and Accounting
Machine LearningRandom Forests
126,192 Citations2001Leo Breiman
Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
IEEE Transactions on Automatic ControlA new look at the statistical model identification
50,732 Citations1974Hirotugu Akaike
The Nature of Statistical Learning Theory
39,279 Citations1995Vladimir Vapnik
Journal of the American Statistical AssociationDistribution of the Estimators for Autoregressive Time Series with a Unit Root
22,977 Citations1979David A. Dickey, Wayne A. Fuller
Machine LearningBagging predictors
16,377 Citations1996Leo Breiman
Tests on real and simulated data sets using classification and regression trees and subset selection in linear regression show that bagging can give substantial gains in accuracy.
Economic RecordPredicting the Present with Google Trends
2,304 Citations2012Hyunyoung Choi, Hal R. Varian
International Journal of ForecastingTesting the equality of prediction mean squared errors
1,996 Citations1997David I. Harvey, Stephen J. Leybourne +1 more
Journal of Interactive MarketingExploring the value of online product reviews in forecasting sales: The case of motion pictures
1,531 Citations2007Chrysanthos Dellarocas, Xiaoquan Zhang +1 more
This study shows that the addition of online product review metrics to a benchmark model that includes prerelease marketing, theater availability and professional critic reviews substantially increases its forecasting accuracy; the forecasting accuracy of the best model outperforms that of several previously published models.
IEEE Transactions on Power SystemsARIMA models to predict next-day electricity prices
1,529 Citations2003Javier Contreras, Rosa Espínola +2 more
Tourism ManagementTourism demand modelling and forecasting—A review of recent research
1,325 Citations2007Haiyan Song, Gang Li
International Journal of Hospitality ManagementThe impact of online user reviews on hotel room sales
1,260 Citations2008Qiang Ye, Rob Law +1 more
Computers & Operations ResearchForecasting stock market movement direction with support vector machine
1,113 Citations2004Wei Huang, Yoshiteru Nakamori +1 more
This paper investigates the predictability of financial movement direction with SVM by forecasting the weekly movement direction of NIKKEI 225 index and proposes a combining model by integrating SVM with the other classification methods.
OmegaA hybrid ARIMA and support vector machines model in stock price forecasting
1,002 Citations2004Ping‐Feng Pai, Chih-Sheng Lin
This investigation proposes a hybrid methodology that exploits the unique strength of the ARIMA model and the SVMs model in forecasting stock prices problems and results of computational tests are very promising.
IEEE Power Engineering ReviewARIMA Models to Predict Next-Day Electricity Prices
941 Citations2002Javier Contreras, Rosario Espinola +2 more
International Journal of Hospitality ManagementWhat can big data and text analytics tell us about hotel guest experience and satisfaction?
889 Citations2014Zheng Xiang, Zvi Schwartz +2 more
This study applies a text analytical approach to a large quantity of consumer reviews extracted from Expedia.com to deconstruct hotel guest experience and examine its association with satisfaction ratings, revealing several dimensions of guest experience that carried varying weights and have novel, meaningful semantic compositions.
Tourism ManagementForecasting Chinese tourist volume with search engine data
416 Citations2014Xin Yang, Bing Pan +2 more
The study demonstrated the value of search engine data, proposed a method for selecting predictive queries, and showed the locality of the data for forecasting tourism demand, as well as comparing the predictive power of the search data of two different search engines, Google and Baidu.
Annals of Tourism ResearchTourism demand forecasting: A deep learning approach
413 Citations2019Rob Law, Gang Li +2 more
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.
Forecasting with Univariate Box - Jenkins Models : concepts and cases
409 Citations1983Alan Pankratz
This work presents an introduction to Box--Jenkins Analysis of a Single Data Series, a single data series analysis of ARIMA Modeling, and some of the underlying statistical principles behind this work.
Production and Operations ManagementThe Operational Value of Social Media Information
389 Citations2017Ruomeng Cui, Santiago Gallino +2 more
This study empirically studying whether using publicly available social media information can improve the accuracy of daily sales forecasts finds that using social media information results in statistically significant improvements in the out‐of‐sample accuracy of the forecasts, with relative improvements ranging from 12.85% to 23.23% over different forecast horizons.
Tourism ManagementSupport vector regression with genetic algorithms in forecasting tourism demand
376 Citations2006Kuan‐Yu Chen, Cheng-Hua Wang
This study proposes a novel approach, known as genetic algorithm (GA)-SVR, which searches for SVR's optimal parameters using real value GAs, and then adopts the optimal parameters to construct the SVR models.
Tourism ManagementForecasting tourism demand with composite search index
362 Citations2016Xin Li, Bing Pan +2 more
Findings suggest that the proposed framework and procedure for creating a composite search index adopted in a generalized dynamic factor model improves the forecast accuracy better than two benchmark models: a traditional time series model and a model with an index created by principal component analysis.
Tourism ManagementForecasting tourist arrivals with machine learning and internet search index
359 Citations2018Shaolong Sun, Yunjie Wei +2 more
Tourism ManagementCan Google data improve the forecasting performance of tourist arrivals? Mixed-data sampling approach
324 Citations2014Prosper Bangwayo-Skeete, Ryan W. Skeete
The twelve month forecasts reveal that Google Trends information offers significant benefits to forecasters, particularly in tourism, and policymakers and business practitioners especially in the Caribbean can take advantage of the forecasting capability of Google search data for their planning purposes.
Tourism ManagementA comparison of three different approaches to tourist arrival forecasting
317 Citations2003Vincent Cho
This paper investigates the application of three time-series forecasting techniques, namely exponential smoothing, univariate ARIMA, and Elman's Model of Artificial Neural Networks (ANN), to predict travel demand from different countries to Hong Kong.
Journal of Business ResearchProduct sales forecasting using online reviews and historical sales data: A method combining the Bass model and sentiment analysis
314 Citations2017Zhi‐Ping Fan, Yu-Jie Che +1 more
A novel method that combines the Bass/Norton model and sentiment analysis while using historical sales data and online review data is developed for product sales forecasting.
International Journal of Contemporary Hospitality ManagementNew developments in tourism and hotel demand modeling and forecasting
306 Citations2017Doris Chenguang Wu, Haiyan Song +1 more
Economic ModellingForecasting tourism demand to Catalonia: Neural networks vs. time series models
271 Citations2013Oscar Clavería, Salvador Torra
It is found that forecasts of tourist arrivals are more accurate than forecasts of overnight stays, and autoregressive integrated moving average models outperform self-exciting threshold autoregressions and artificial neural network models, especially for shorter horizons.
Tourism ManagementA meta-analysis of international tourism demand forecasting and implications for practice
254 Citations2014Bo Peng, Haiyan Song +1 more
IEEE Transactions on Knowledge and Data EngineeringMining Online Reviews for Predicting Sales Performance: A Case Study in the Movie Domain
241 Citations2011Xiaohui Yu, Yang Liu +2 more
A case study in the movie domain is conducted, and it is shown that both the sentiments expressed in the reviews and the quality of the reviews have a significant impact on the future sales performance of products in question.
Tourism ManagementEffective tourist volume forecasting supported by PCA and improved BPNN using Baidu index
236 Citations2018Shaowen Li, Tao Chen +2 more
The results indicate the proposed PCA-ADE-BPNN always outperforms other models in terms of forecasting accuracies, and is a potential candidate for the effective forecasting of tourist volume.
Journal of Travel ResearchPredicting Hotel Demand Using Destination Marketing Organization’s Web Traffic Data
231 Citations2013Yang Yang, Bing Pan +1 more
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, demonstrating 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.
Tourism ManagementThe Baidu Index: Uses in predicting tourism flows –A case study of the Forbidden City
228 Citations2016Xiankai Huang, Lifeng Zhang +1 more
The study shows that there is a long-term equilibrium relationship and Granger causal relation between the observed number of tourists and a set of related keywords in the Baidu Index and a positive correlation between the increasing BaidU keyword search index and the increasing observed tourist flow.
Journal of Travel ResearchForecasting Destination Weekly Hotel Occupancy with Big Data
224 Citations2016Bing Pan, Yang Yang
Time-series models incorporating several tourism big data sources, including search engine queries, website traffic, and weekly weather information, are tested in order to construct an accurate forecasting model of weekly hotel occupancy for a destination and show the superiority of ARMAX models with both search search queries and website traffic data in accurate forecasting.
Journal of Hospitality and Tourism TechnologyForecasting hotel room demand using search engine data
203 Citations2012Bing Pan, Doris Chenguang Wu +1 more
AlgorithmsVariable Selection in Time Series Forecasting Using Random Forests
194 Citations2017Hristos Tyralis, Georgia Papacharalampous
The highest predictive performance of RF is observed when using a low number of recent lagged predictor variables, which could be useful in relevant future applications, with the prospect to achieve higher predictive accuracy.
Annals of Tourism ResearchForecasting city arrivals with Google Analytics
181 Citations2016Ulrich Gunter, İrem Önder
The ability of 10 Google Analytics website traffic indicators from the Viennese DMO website to predict actual tourist arrivals to Vienna is investigated, and combined forecasts based on Bates–Granger weights, on forecast encompassing tests, and on a novel fusion of these two perform best.
Tourism EconomicsTourism forecasting: A review of methodological developments over the last decade
158 Citations2018Eden Xiaoying Jiao, Jason Li Chen
Results in different studies proved superiority of combination forecasts over average single forecasts performance, which are rapidly developed in the past decade and hybrid AI models are becoming a new trend.
Lecture notes in computer scienceInfluence of Hyperparameters on Random Forest Accuracy
153 Citations2009Simon Bernard, Laurent Heutte +1 more
This work evaluates the Forest-RI algorithm on several machine learning problems and with different settings of K in order to understand the way it acts on RF performance, and shows that default values of K traditionally used in the literature are globally near-optimal, except for some cases for which they are all significatively sub-optical.
Journal of Travel ResearchModeling and Forecasting Regional Tourism Demand Using the Bayesian Global Vector Autoregressive (BGVAR) Model
144 Citations2018A. George Assaf, Gang Li +2 more
Decision Support SystemsUsing social network and semantic analysis to analyze online travel forums and forecast tourism demand
144 Citations2019Andrea Fronzetti Colladon, Barbara Guardabascio +1 more
This research applied methods and tools of social network and semantic analysis to study user-generated content retrieved from online communities which interacted on the TripAdvisor travel forum to present a new methodology of analysis of tourism-related big data and a set of variables which could be integrated into traditional forecasting models.
Tourism ManagementGoogle Trends and tourists' arrivals: Emerging biases and proposed corrections
127 Citations2017Theologos Dergiades, Eleni Mavragani +1 more
It is found that the corrected aggregate search engine volume index, adjusted for different search languages and different search platforms, is preferable in forecasting international visitor volumes compared to the non-adjusted index.
Tourism ManagementA dynamic linear model to forecast hotel registrations in Puerto Rico using Google Trends data
117 Citations2016Roberto Rivera
A Dynamic Linear Model is proposed that treats SQV data as a representation of an unobservable process and provides better inference on the association between the number of hotel nonresident registrations and Google Trends SQV than using Google Trends data retrieved only on one occasion.
arXiv (Cornell University)Predicting the direction of stock market prices using random forest
117 Citations2016Luckyson Khaidem, Snehanshu Saha +1 more
A novel way to minimize the risk of investment in stock market by predicting the returns of a stock using a class of powerful machine learning algorithms known as ensemble learning, which is an ensemble of multiple decision trees.
Tourism EconomicsForecasting tourist arrivals at attractions: Search engine empowered methodologies
112 Citations2018Katerina Volchek, Anyu Liu +2 more
This study investigates how the accuracy of tourism demand forecasting can be improved at the micro level and the predictive powers of Naïve I, seasonal Naïve, seasonal autoregressive moving average, seasonalAutoregressiveMoving average with explanatory variables, SARMAX-mixed frequency data sampling and artificial neural network models are compared.
Journal of Travel ResearchForecasting Tourism Demand with Decomposed Search Cycles
104 Citations2019Xin Li, Rob Law
Results indicate the proposed methodology can outperform the benchmark model in the out-of-sample forecasting evaluation of Choi and Varian (2012) and demonstrate that the proposed method is superior in forecasting turning points.
Annals of Tourism ResearchSpatial-temporal forecasting of tourism demand
91 Citations2019Yang Yang, Honglei Zhang
The results indicate that spatial-temporal forecasting outperforms the a-spatial counterpart in terms of average forecasting error, and Auxiliary regression finds the relative error of spatial- Temporal forecasting to be lower in regions characterized by a stronger level of local spatial association.
Journal of Travel ResearchUtilizing Facebook Statistics in Tourism Demand Modeling and Destination Marketing
88 Citations2019İrem Önder, Ulrich Gunter +1 more
Tourism ManagementA novel approach to model selection in tourism demand modeling
88 Citations2014Melda Akın
This study considers Seasonal AutoRegressive Integrated Moving Average, ν-Support Vector Regression, and multi-layer perceptron type Neural Network models and optimize their parameters using different techniques for each and compares their performances on monthly tourist arrival data to Turkey from different countries.
MIS QuarterlyUsing Forum and Search Data for Sales Prediction of High-Involvement Projects1
67 Citations2017Tomer Geva, Gal Oestreicher-Singer +2 more
Predictive capacity according to " premium " and " value " car brand characteristics based on price, perceived quality, and willingness to recommend metrics using NN algorithm and MSE criteria is presented.
Journal of Travel ResearchPooling in Tourism Demand Forecasting
64 Citations2018Long Wen, Chang Liu +1 more
ACM Transactions on Information SystemsVolunteerism Tendency Prediction via Harvesting Multiple Social Networks
49 Citations2016Xuemeng Song, Zhaoyan Ming +3 more
This article proposes a scheme that is able to predict users’ volunteerism tendency from user-generated contents collected from multiple social networks based on a conceptual volunteering decision model and conducts comprehensive experiments to investigate the effectiveness and discuss its generalizibility and extendability.
Tourism EconomicsExploring the predictive ability of LIKES of posts on the Facebook pages of four major city DMOs in Austria
48 Citations2018Ulrich Gunter, İrem Önder +1 more
arXiv (Cornell University)Using Social Media to Predict the Future: A Systematic Literature Review
37 Citations2017Lawrence Phillips, Chase Dowling +3 more
It is found that SM forecasting is limited by data biases, noisy data, lack of generalizable results, a lack of domain-specific theory, and underlying complexity in many prediction tasks, but recurring findings and promising results continue to galvanize researchers and demand continued investigation.
Tourism AnalysisForecasting Tourist Arrivals with the Help of Web Sentiment: A Mixed-frequency Modeling Approach for Big Data
36 Citations2019İrem Önder, Ulrich Gunter +1 more
This study shows that utilizing online news media coverage as an indication of destination image can improve tourism demand forecasting, and destination management organizations (DMOs) should add models incorporating web sentiment data to their forecast modeling toolkit to further improve the accuracy of their tourism demand forecasts.
Journal of Systems Science and Systems EngineeringAnalysis of the prediction capability of web search data based on the HE-TDC method ‒ prediction of the volume of daily tourism visitors
35 Citations2016Geng Peng, Ying Liu +2 more
A new integrative method that combines Hurst Exponent and Time Difference Correlation analysis to select keywords with powerful predictive ability to predict the volume of tourism visitors in the Jiuzhai Valley scenic area is presented.
Proceedings of the AAAI Conference on Artificial IntelligenceFusing Social Networks with Deep Learning for Volunteerism Tendency Prediction
23 Citations2016Yongpo Jia, Xuemeng Song +4 more
A framework for multiple social network learning is presented, whose core is a novel model that fuses social networks using deep learning with source confidence and consistency regularization that outperforms several state-of-the-art approaches in terms of precision, recall and F1-score.