Advanced tourist arrival forecasting: a synergistic approach using LSTM, Hilbert-Huang transform, and random forest

Abstract

An advanced synergistic approach for forecasting tourist arrivals is presented, integrating long short-term memory (LSTM), Hilbert-Huang transform (HHT), and random forest (RF). LSTM is leveraged for its capability to capture long-term dependencies in sequential data. Additional data from Google Trends (GT) is processed with HHT for feature extraction, followed by feature selection using the RF algorithm. The combined HHT-RF-LSTM model delivers highly accurate forecasts. Evaluation employs regression analysis with metrics such as root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and mean square error (MSE), highlighting the effectiveness of this innovative approach in predicting tourist arrivals. This methodology provides a robust framework for handling limited datasets and improving forecast reliability. By incorporating diverse data sources and advanced preprocessing techniques, the model enhances prediction performance, demonstrating the strong performance of RF in feature selection.