ABSTRACT
Tourism trend prediction facilitates estimation of tourism investment and revenue. Studies on tourism prediction have primarily relied on linear models and historical visitors; however, relationships between tourism trends and their factors may be nonlinear. This study constructed factors from internet search data and predicted tourism trends using a spatiotemporal framework based on the extreme gradient boosting (XGBoost) method. The study first sorted Baidu index data that is computed by weighting the search frequency. The spatial cluster analysis was conducted to incorporate spatial characteristics, and principal component analysis was further performed to identify factors. The next step derived variables using the weighted moving average method to reduce the lag effect between tourism internet search and actual behavior. We applied the proposed spatiotemporal XGBoost composite model to predict Beijing’s tourism trends. The R2 scores of the simple XGBoost model, the autoregressive integrated moving average model, the spatial XGBoost model, and the spatiotemporal XGBoost composite model were 0.517, 0.625, 0.791, and 0.940, respectively. Compared to predictions from different models, the spatiotemporal XGBoost composite model has the best prediction ability. The findings also suggest that machine learning methods may not perform well without considering spatial properties, such as spatial autocorrelation and spatial heterogeneity.
Acknowledgments
We thank Dr. Shenjun Yao for her valuable comments on the revision of the manuscript. We are also grateful to Prof. May Yuan, Dr. Michela Bertolotto, and the three anonymous referees for their valuable comments and suggestions.
Data and codes availability statement
The data and core codes that support the findings of this study are available in https://doi.org/10.6084/m9.figshare.14511657.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
Junfeng Kang
Junfeng Kang is an associate professor of Geographic Information Science at Jiangxi University of Science and Technology, Ganzhou, China. He is interested in high-performance GIS algorithms and applications. Email: [email protected]
Xingyu Guo
Xingyu Guo is a researcher on information science at Nanchang Hangkong University, Nanchang, China. His research interests include location-based services (LBS), spatial cognition, urban informatics, and big data. ID: https://orcid.org/0000-0003-4710-3659; Email: [email protected]
Lei Fang
Lei Fang is a postdoctoral researcher on the application of Geographical Information Science in the Department of Environmental Science and Engineering, Fudan University, Shanghai, China. His research works focus on spatio-temporal analysis and big data. ID: https://orcid.org/0000-0001-8902-1817; Email: [email protected]
Xiangrong Wang
Xiangrong Wang is a Professor in the Department of Environmental Science and Engineering, Fudan University, China. His research interests include ecological evaluation, virtual reality, and informatization of urban ecology. Email: [email protected]
Zhengqiu Fan
Zhengqiu Fan is an associate professor in the Department of Environmental Science and Engineering, Fudan University, China. His research interests include urban planning, spatio-temporal analysis of soil pollution. ID: https://orcid.org/0000-0002-2908-811X; Email: [email protected]