Collaborative forecasting of tourism demand for multiple tourist attractions with spatial dependence: A combined deep learning model

Abstract

To forecast the tourism demand across a set of tourist attractions with spatial dependence, a new model is proposed, which has three stages: tourist attraction selection, base predictor generation, and base predictor combination. In stage 1, a method for selecting associated attractions based on multi-dimensional scaling is used to determine the strength of the spatial dependence between each pair of attractions. In stage 2, a hybrid base predictor based on LSTM networks and Autoregressive model is developed, where the LSTM networks are used to capture the spatial dependence among attractions, and the Autoregressive model is used capture the scale of tourist volume at each attraction. In stage 3, a strategy for combining these base predictors is proposed; it can alleviate the overfitting problem of LSTM and improve the stability of forecasts. Finally, the superiority of the model is verified through the data on tourist volumes at 77 attractions in Beijing.

Investigating spatial patterns and determinants of tourist attractions utilizing POI data: A case study of Hubei Province, China

“…However, existing studies have focused primarily on specific attractions [ 49 ], lacking an analysis of the distributional tendencies of touristic site within regions. Meanwhile, the traditional statistical survey data used in related research are limited in quantity and lack timeliness, while the emerging POI data, characterized by strong timeliness and large volume, are underutilized.…”

Forecast combination using grey prediction with fuzzy integral and time-varying weighting in tourism

“…AI-based methods have drawn considerable attention due to their ability of nonlinear modeling (Qiu et al ., 2021). Examples include bootstrap aggregation (Athanasopoulos et al ., 2017), time series bagging (Liu et al ., 2023), NNs (Cang, 2014; Claveria et al ., 2015a, b, 2017; Hu et al ., 2019; Hu, 2021), deep learning (Bi et al ., 2021, 2023; Han et al ., 2023; Law et al ., 2019; Xue et al ., 2023) and the support vector regression (SVR) (Chen, 2011). Wang et al .…”

“…AI-based methods have drawn considerable attention due to their ability of nonlinear modeling (Qiu et al, 2021). Examples include bootstrap aggregation (Athanasopoulos et al, 2017), time series bagging (Liu et al, 2023), NNs (Cang, 2014;Claveria et al, 2015aClaveria et al, , b, 2017Hu et al, 2019;Hu, 2021), deep learning (Bi et al, 2021(Bi et al, , 2023Han et al, 2023;Law et al, 2019;Xue et al, 2023) and the support vector regression (SVR) (Chen, 2011). Wang et al (2023) proposed a multi-objective optimization algorithm for interval forecasting, Claveri and Torra (2014) showed that the ARIMA outperformed NNs over short horizons, and Volchek et al (2019) showed that NNs were more accurate than the seasonal autoregressive moving average with explanatory variables.…”

Investigating the Spatial-Temporal Variation of Pre-Trip Searching in an Urban Agglomeration

“…The current TIS study mainly focuses on time series data, revealing that different tourism-based factors have short, medium, or long timescale effects [34,35]. For example, the weather proved to be a short-term impact on tourist volume [36,37]; extreme events proved to be a medium-term impact [8]; and scenic spots had a long-term impact [38]. In the post-COVID-19 era, examining the role of search data in travel has also become an important topic [39].…”