Abstract
The arrival tourism numbers have a positive increase after the COVID-19 pandemic all around the world, especially in Vietnam where China began to open to the boundary and lift the foreign travel limitation. This study utilizes deep learning long short-term memory (LSTM) to monthly predict the arrival of domestic and international tourism numbers in Vietnam. The monthly number of new COVID-19 cases in Vietnam and in the world are also collected as promising input, combined with the monthly gross domestic product (CPI), the monthly consumer price index (CPI), the number of monthly international holidays, the number of the monthly domestic holiday. The Pearson correlations between collected data and target variables are also calculated to select the most appropriate input features. The deep learning LSTM is compared with other traditional methodologies, including gate recurrent unit (GRU), the recurrent neural network (RNN), and the convolution neural network (CNN), by various evaluating benchmarks, comprising the mean square error (MSE), means absolute error (MAE), and mean absolute percentage error (MAPE). The empirical experiments prove that the proposed LSTM methodologies outperform the GRU, CNN, and RNN methodologies with the maximum improvement of 81.44% MSE, 78.82% validating MSE, 32.30% MAE, 47.91% validating MAE, 60.54% MAPE, and 57.95% validating MAPE. The monthly accurate international and domestic arrival tourism could be utilized for efficient resource planning, which could enhance the quality of tourism in Vietnam.
Thông tin:
| Thuộc danh mục | |
| Hội thảo quốc tế | 2023 International Conference on Science, Education, and Viable Engineering |
| Tổ chức | Taiwan Association for Academic Innovation (TAAI) IEEE Electron Devices Society (IEEE EDS) University of Economics Ho Chi Minh City |
| Trang | 134 |
| ISBN | 978-604-80-7896-6 |
| Ngày tổ chức hội thảo | 12-16/04/2023 |
| Ngày xuất bản | 18/04/2023 |
| Link | ttps://drive.google.com/drive/folders/1v806uXc_xa3_sBqvAazHURcGnnmiYvEE |