Tourism demand forecasting with spatiotemporal features
Annals of Tourism Research
; 94:103384, 2022.
Article
in English
| ScienceDirect | ID: covidwho-1748287
ABSTRACT
Tourism demand forecasting is a crucial prerequisite for effective and efficient tourism management. This study develops a novel model based on deep learning methods for precise demand forecasting, namely, spatial-temporal fused graph convolutional network (ST-FGCN). ST-FGCN generates forecasts based on spatial effects extracted using graph convolutional network and temporal dependency captured through long short-term memory. A data-driven spatial matrix is used in our model to strengthen forecasting performance further. Two markedly different forecasting experiments verify the effectiveness of our model. Empirical results suggest that incorporating spatial effects can remarkably reduce forecasting errors. Furthermore, our model shows good applicability for data with different time granularity and different periods before and during the COVID-19 pandemic.
Full text:
Available
Collection:
Databases of international organizations
Database:
ScienceDirect
Language:
English
Journal:
Annals of Tourism Research
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS