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

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.