Forecasting daily attraction demand using big data from search engines and social media

被引:38
作者
Tian, Fengjun [1 ]
Yang, Yang [2 ]
Mao, Zhenxing [3 ]
Tang, Wenyue [4 ]
机构
[1] Jiangxi Univ Finance & Econ, Sch Tourism & Urban Management, Nanchang, Jiangxi, Peoples R China
[2] Temple Univ, Dept Tourism & Hospitality Management, Philadelphia, PA 19122 USA
[3] Calif State Polytech Univ Pomona, Collins Coll Hospitality Management, Pomona, CA 91768 USA
[4] Jiangxi Univ Finance & Econ, Inst Ecol Civilizat, Nanchang, Jiangxi, Peoples R China
关键词
Social media; Tourism forecasting; Baidu index; Big data predictors; Elastic net; Lasso regression; USER-GENERATED CONTENT; TOURISM DEMAND; MODEL SELECTION; DATA ANALYTICS; REGRESSION; ARRIVALS; BEHAVIOR; VOLUME;
D O I
10.1108/IJCHM-06-2020-0631
中图分类号
F [经济];
学科分类号
02 ;
摘要
Purpose - This paper aims to compare the forecasting performance of different models with and without big data predictors from search engines and social media. Design/methodology/approach - Using daily tourist arrival data to Mount Longhu, China in 2018 and 2019, the authors estimated ARMA, ARMAX, Markov-switching auto-regression (MSAR), lasso model, elastic net model and post-lasso and post-elastic net models to conduct one- to seven-days-ahead forecasting. Search engine data and social media data from WeChat, Douyin and Weibo were incorporated to improve forecasting accuracy. Findings - Results show that search engine data can substantially reduce forecasting error, whereas social media data has very limited value. Compared to the ARMAX/MSAR model without big data predictors, the corresponding post-lasso model reduced forecasting error by 39.29% based on mean square percentage error, 33.95% based on root mean square percentage error, 46.96% based on root mean squared error and 45.67% based on mean absolute scaled error. Practical implications - Results highlight the importance of incorporating big data predictors into daily demand forecasting for tourism attractions. Originality/value - This study represents a pioneering attempt to apply the regularized regression (e.g. lasso model and elastic net) in tourism forecasting and to explore various daily big data indicators across platforms as predictors.
引用
收藏
页码:1950 / 1976
页数:27
相关论文
共 71 条
[51]   Forecasting Destination Weekly Hotel Occupancy with Big Data [J].
Pan, Bing ;
Yang, Yang .
JOURNAL OF TRAVEL RESEARCH, 2017, 56 (07) :957-970
[52]   Forecasting hotel room demand using search engine data [J].
Pan, Bing ;
Wu, Doris Chenguang ;
Song, Haiyan .
JOURNAL OF HOSPITALITY AND TOURISM TECHNOLOGY, 2012, 3 (03) :196-210
[53]   Analysis of the prediction capability of web search data based on the HE-TDC method aEuro' prediction of the volume of daily tourism visitors [J].
Peng, Geng ;
Liu, Ying ;
Wang, Jiyuan ;
Gu, Jifa .
JOURNAL OF SYSTEMS SCIENCE AND SYSTEMS ENGINEERING, 2017, 26 (02) :163-182
[54]   A dynamic linear model to forecast hotel registrations in Puerto Rico using Google Trends data [J].
Rivera, Roberto .
TOURISM MANAGEMENT, 2016, 57 :12-20
[55]   ESTIMATING DIMENSION OF A MODEL [J].
SCHWARZ, G .
ANNALS OF STATISTICS, 1978, 6 (02) :461-464
[56]  
Song H., 2003, Journal of Travel Research, V42, P65, DOI 10.1177/0047287503253939
[57]   Tourism demand modelling and forecasting - A review of Recent research [J].
Song, Haiyan ;
Li, Gang .
TOURISM MANAGEMENT, 2008, 29 (02) :203-220
[58]   A review of research on tourism demand forecasting [J].
Song, Haiyan ;
Qiu, Richard T. R. ;
Park, Jinah .
ANNALS OF TOURISM RESEARCH, 2019, 75 :338-362
[59]   Forecasting tourist arrivals with machine learning and internet search index [J].
Sun, Shaolong ;
Wei, Yunjie ;
Tsui, Kwok-Leung ;
Wang, Shouyang .
TOURISM MANAGEMENT, 2019, 70 :1-10
[60]   Understanding intraday electricity markets: Variable selection and very short-term price forecasting using LASSO [J].
Uniejewski, Bartosz ;
Marcjasz, Grzegorz ;
Weron, Rafai .
INTERNATIONAL JOURNAL OF FORECASTING, 2019, 35 (04) :1533-1547