Original scientific paper
https://doi.org/10.37741/t.73.3.1
Forecasting Trends in Foreign Tourism by Machine Learning
Jirapond Muangprathub
; Faculty of Science and Industrial Technology, Prince of Songkla University, Suratthani Campus, Surat Thani, Thailand
Patthamaphon Kaewmanee
; Faculty of Science and Industrial Technology, Prince of Songkla University, Suratthani Campus, Surat Thani, Thailand
Jarunee Sealee
; Faculty of Science and Technology, Prince of Songkla University, Pattani Campus, Pattani, Thailand
Pattaraporn Warintarawej
; Faculty of Science and Industrial Technology, Prince of Songkla University, Suratthani Campus, Surat Thani, Thailand
Wichuta Sae-jie
orcid.org/0000-0001-7056-7529
; Faculty of Science and Industrial Technology, Prince of Songkla University, Suratthani Campus, Surat Thani, Thailand
*
* Corresponding author.
Abstract
Tourists frequently use online search engines for travel planning, making search data a valuable predictor
of future tourism volume. This study employs machine learning to analyse the predictive power of keyword
search data for forecasting tourist arrivals, incorporating a lag time between searches and arrivals. The dataset
is collected and prepared from two sources: a search engine and government agencies, covering the years
2014-2019, to be analysed by machine learning. The SARIMA model effectively forecasts trends in keyword
searches and tourist numbers, while SVM (Support Vector Machine) and Random Forest outperform other
methods in predicting arrivals. This research supports tourism operators and stakeholders in planning for
future tourists, utilising the obtained keywords to enhance visibility in tourist searches through SEO.
Keywords
tourism volume forecasting; tourist arrivals prediction; machine learning; search engine data; tourist data analysis
Hrčak ID:
333686
URI
Publication date:
15.7.2025.
Visits: 667 *