How to capture tourists’ search behavior in tourism forecasts? A two-stage feature selection approach

作者：

Highlights：

• A two stage-based feature selection approach for forecasting is proposed.

• The approach relies on machine learning model combined with feature selection method.

• With different forecasting horizons and datasets, results are predominant.

• The study confirms the value of exploring the more effective keywords subset.

• The results provide some implications for forecasting using multisource data.

摘要

•A two stage-based feature selection approach for forecasting is proposed.•The approach relies on machine learning model combined with feature selection method.•With different forecasting horizons and datasets, results are predominant.•The study confirms the value of exploring the more effective keywords subset.•The results provide some implications for forecasting using multisource data.

论文关键词：Tourism demand forecasting,Search engine data,Two-stage feature selection,Genetic algorithm,Kernel extreme learning machine

论文评审过程：Received 25 July 2022, Revised 10 September 2022, Accepted 21 September 2022, Available online 29 September 2022, Version of Record 12 October 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118895