This study aims to examine the predictability of Support Vector Machine (SVM) and deep learning methods, which are Artificial Neural Network (ANN), and Recurrent Neural Network (RNN), and long short-term memory (LSTM). Tourism’s motivation reflected by the Search Intensity Indices (SII) is considered as the exogenous input in the forecasting model. Several forecasting criteria are implemented to measure the performance of these forecasting models. The models are applied to forecast the tourism demand, and the empirical results demonstrate that the deep learning approach, especially LSTM, seems to outperform the other learning models as well as the traditional regression model. Additionally, the forecasting performance of the forecasting models could be improved if the tourism’s motivation variable is augmented as the leading indicator in the model.
CITATION STYLE
Kaewsompong, N., Thongkairat, S., & Maneejuk, P. (2022). Application of Machine Learning Concept to Tourism Demand Forecast. In Studies in Computational Intelligence (Vol. 983, pp. 401–412). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-77094-5_31
Mendeley helps you to discover research relevant for your work.