Short and Long Term Tourism Demand Forecasting Based on Baidu Search Engine Data

With the increasing contribution of tourism in economic development, how to improve the forecasting accuracy has become the focus of researchers and practicer.Statistical data can hardly reflect the useful information in tourism demand, and its role in forecasting tourism demand is very limited.In order to reflect tourists' tourism behavior more comprehensively, many studies have proved the role of online search data in tourism demand forecasting.Further, this study aims to forecasting the volume of tourists from mainland China to Macao, Hong Kong and Thailand based on Baidu Search Index, and applies seasonal autoregressive integrated moving average with explanatory variable (SARIMAX), so the forecasting model called Principal Component Analysis-Seasonal Autoregressive Integrated Moving Average with exogenous variable (PCA-SARIMAX) model is proposed, and the empirical results show that the proposed model has better forecasting effect compared with the benchmark models, and search engine data plays a positive role in forecasting tourism demand.