Forecasting Daily Tourism Demand for Tourist Attractions with Big Data: An Ensemble Deep Learning Method

Abstract

Accurate forecasting of daily tourism demand is a meaningful and challenging task, but studies on this issue are scarce. To address this issue, multisource time series data, relating to past tourist volumes, web search information, daily weather conditions, and the dates of public holidays, are selected as the forecasting variables. To fully capture the relationship between these forecasting variables and actual tourism demand automatically, an ensemble of long short-term memory (LSTM) networks is proposed with a correlation-based predictor selection (CPS) algorithm. The effectiveness of the proposed method is verified in daily tourism demand forecasting for the Huangshan Mountain Area, benchmarked against 11 forecasting methods. This study contributes to the literature by (1) introducing the use of big data in daily tourism demand forecasting, (2) proposing an ensemble of LSTM networks for daily tourism demand forecasting, and (3) providing an effective predictor selection algorithm in ensemble learning.

Daily tourism forecasting through a novel method based on principal component analysis, grey wolf optimizer, and extreme learning machine

“…The model was applied to forecast daily tourist volume at Huangshan Scenic Spot in China and validated for its effectiveness. Bi, Li, Xu, and Li (2021) used historical data, online search data, weather data, and holiday data to propose a network integration of long‐term and short‐term memories based on relevant forecasting and selection algorithms. They also applied the model to forecast daily tourism demand at Huangshan and demonstrated the validity of using holiday data to improve the accuracy of tourism demand forecast.…”

“…Common predictive variables used in tourism forecasting studies are historical data of tourism volume and search engine data (Sun et al, 2017; Wen et al, 2020). Historical data reflect the changing trend of tourism volume, whereas search engine data reflect the travel intention of potential tourists (Bi, Li, Xu, & Li, 2021). As communication technology rapidly advances, the Internet has become the primary source for information.…”

“…According to the data released by some tourist attractions, tourism volume during statutory holidays such as Spring Festival and National Day is obviously higher than the normal because tourists have more time to travel. Therefore, holiday data are a potential variable for daily tourism demand forecasting, and some studies have successfully applied it to forecast tourism demand (Bi, Li, Xu, & Li, 2021; Li, Ge, et al, 2020). Weather is also a factor worth considering.…”

Tourism Demand Interval Forecasting Amid COVID-19: A Hybrid Model With a Modified Multi-Objective Optimization Algorithm

“…Compared with forecasting at time scales of months and years, daily tourism demand forecasting can provide more specific and targeted guidance for related organizations ( Li, Ge et al, 2020 ). For tourism industry practitioners and managers, accurate daily tourism demand forecasting can set reasonable prices, enhance the utilization rate of tourism-related services, and promote the efficient allocation of resources ( Bi, Li, Xu & Li, 2021 ). For local governments and relevant departments of destinations, accurate tourism demand forecasting helps in risk management, strategic planning, and reasonable dispatching ( Bi, Li et al 2021 ; Athanasopoulos et al 2018 ).…”

Fine-grained tourism demand forecasting: A decomposition ensemble deep learning model

“…To produce accurate fine-grained forecasts, it is necessary not only to reduce the complexity of tourism demand data, but also to capture the locally recurring patterns (e.g., the sensitivity and fluctuation of tourism demand) and the long-term dependencies (e.g., the seasonality and periodicity) of the data at the same time. Convolutional neural networks (CNNs) and long short-term memory (LSTM) networks are two kinds of deep learning models that have good performance in data feature extraction, among which CNNs are very suitable for capturing locally recurring patterns of data (Bi et al, 2021; Wang and Li, 2022), while LSTM networks are well suited to capturing the long-term dependencies within data (Bi et al, 2022; Law et al, 2019). Therefore, CNNs and LSTM networks are powerful tools to capture the locally recurring patterns and the long-term dependencies of the components obtained by CEEMDAN, respectively.…”