Please use this identifier to cite or link to this item:
Title: Machine learning in internet search query selection for tourism forecasting
Authors: Li, X
Li, H 
Pan, B
Law, R 
Issue Date: Jul-2021
Source: Journal of travel research, 1 July 2021, v. 60, no. 6, p. 1213-1231
Abstract: Prior studies have shown that Internet search query data have great potential to improve tourism forecasting. As such, selecting the most relevant information from large amounts of search query data is crucial to enhancing forecasting accuracy and reducing overfitting; however, such feature selection methods have not been considered in the tourism forecasting literature. This study employs four machine learning–based feature selection methods to extract useful search query data and construct relevant econometric models. We examined the proposed methods based on monthly forecasting of tourist arrivals in Beijing, China, along with weekly forecasting of hotel occupancy in the city of Charleston, South Carolina, USA. Our findings indicate that the forecasting model with the selected search keywords outperformed the benchmark ARMAX model without feature selection in forecasting tourism demand and hotel occupancy. Therefore, machine learning methods can identify the most useful search query data to significantly improve forecasting accuracy in tourism and hospitality.
Keywords: Feature selection
Hotel occupancy
Machine learning
Search query data
Tourism forecasting
Publisher: SAGE Publications
Journal: Journal of travel research 
ISSN: 0047-2875
EISSN: 1552-6763
DOI: 10.1177/0047287520934871
Rights: This is the accepted version of the publication Li X, Li H, Pan B, Law R. Machine Learning in Internet Search Query Selection for Tourism Forecasting. Journal of Travel Research. 2021;60(6):1213-1231. Copyright © 2020 (The Author(s)). DOI: 10.1177/0047287520934871
Appears in Collections:Journal/Magazine Article

Files in This Item:
File Description SizeFormat 
Li_Machine_Learning_Internet.pdfPre-Published version1.49 MBAdobe PDFView/Open
View full-text via PolyU eLinks SFX Query
Show full item record
PIRA download icon_1.1View/Download Full Text

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.