Novel deep learning approach for forecasting daily hotel demand with agglomeration effect

Huang, Liyao; Zheng, Weimin

doi:10.1016/j.ijhm.2021.103038

Cited by 32 publications

(40 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The spatial-temporal module is responsible for extracting spatial and temporal dependencies from given hotel demand data and spatial relationships. The module consists of two deep learning algorithms with strong capacity of feature extraction and can contribute to better spatiotemporal feature extraction and forecasting improvement compared with existing spatiotemporal models, such as spatial econometric models (Jiao et al , 2020) and spatial-weighted LSTM model (Huang and Zheng, 2021). The external factor module captures competitive factors on the basis of price and online rating and thus helps in improving forecasting performance.…”

Section: Methodsmentioning

confidence: 99%

“…Law (1998) was the first to introduce neural networks into hotel demand forecasting. With the application of big data, characterized by complexity and dynamics, in demand forecasting, researchers introduced various types of AI-based models, such as artificial neural network (ANN) (Bigné et al , 2019) and long short-term memory (LSTM) (Huang and Zheng, 2021). Notwithstanding the many new models introduced to improve prediction accuracy, no model can maintain superiority for any situation (Pan and Yang, 2017).…”

Section: Literature Reviewmentioning

confidence: 99%

“…Schwartz et al (2016) included the competitive set of hotels to improve predictive performance by a recursive algorithm, where the competitive set contains four hotels. Huang and Zheng (2021) simultaneously predicted daily demand for hotels in the region by incorporating demand from other hotels. Compared with the tourism context, the hotel industry faces a more competitive environment because of its core products’ high similarity and substitutability (i.e.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The optimal parameter combinations of these models are selected on the basis of the exhaustive grid search approach as described above. The DLM-ST model is developed in Huang and Zheng (2021), and we followed the same architecture and parameter settings to replicate their model. Considering that these four single models generate forecasts on the basis of temporal correlations of historical demand, the effectiveness of spatial effects to forecast improvement can be demonstrated by comparing their forecasting results with that of the STGCN-GRU.…”

Section: Empirical Studymentioning

confidence: 99%

“…The rapid development of tourism has contributed to the prosperity of the hotel industry (Huang and Zheng, 2021), but its fragile nature has also been exposed (Zheng et al , 2020). Economic crises (Webb et al , 2020), unexpected events (Qiu et al , 2021) and fierce competition within the industry (Tang et al , 2015) would have an incalculable impact on the development of the hospitality industry.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Daily hotel demand forecasting with spatiotemporal features

Huang

Zheng

2022

IJCHM

Self Cite

View full text Add to dashboard Cite

Purpose Given the importance of spatial effects in improving the accuracy of hotel demand forecasting, this study aims to introduce price and online rating, two critical factors influencing hotel demand, as external variables into the model, and capture the spatial and temporal correlation of hotel demand within the region. Design/methodology/approach For high practical implications, the authors conduct the case study in Xiamen, China, where the hotel industry is prosperous. Based on the daily demand data of 118 hotels before and during the COVID-19 period (from January to June 2019 and from January to June 2021), the authors evaluate the prediction performance of the proposed innovative model, that is, a deep learning-based model, incorporating graph convolutional networks (GCN) and gated recurrent units. Findings The proposed model simultaneously predicts the daily demand of multiple hotels. It effectively captures the spatial-temporal characteristics of hotel demand. In addition, the features, price and online rating of competing hotels can further improve predictive performance. Meanwhile, the robustness of the model is verified by comparing the forecasting results for different periods (during and before the COVID-19 period). Practical implications From a long-term management perspective, long-term observation of market competitors’ rankings and price changes can facilitate timely adjustment of corresponding management measures, especially attention to extremely critical factors affecting forecast demand, such as price. While from a short-term operational perspective, short-term demand forecasting can greatly improve hotel operational efficiency, such as optimizing resource allocation and dynamically adjusting prices. The proposed model not only achieves short-term demand forecasting, but also greatly improves the forecasting accuracy by considering factors related to competitors in the same region. Originality/value The originalities of the study are as follows. First, this study represents a pioneering attempt to incorporate demand, price and online rating of other hotels into the forecasting model. Second, integrated deep learning models based on GCN and gated recurrent unit complement existing predictive models using historical data in a methodological sense.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Empirical Studymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Daily hotel demand forecasting with spatiotemporal features

Huang

Zheng

2022

IJCHM

Self Cite

View full text Add to dashboard Cite

show abstract

What online review features really matter? An explainable deep learning approach for hotel demand forecasting

Zhang

2023

Asso for Info Science & Tech

View full text Add to dashboard Cite

Accurate demand forecasting plays a critical role in hotel revenue management. Online reviews have emerged as a viable information source for hotel demand forecasting. However, existing hotel demand forecasting studies leverage only sentiment information from online reviews, leading to capturing insufficient information. Furthermore, prevailing hotel demand forecasting methods either lack explainability or fail to capture local correlations within sequences. In this study, we (1) propose a comprehensive framework consisting of four components: expertise, sentiment, popularity, and novelty (ESPN framework), to investigate the impact of online reviews on hotel demand forecasting; (2) propose a novel dual attention-based long short-term memory convolutional neural network (DA-LSTM-CNN) model to optimize the model effectiveness. We collected online review data from Ctrip.com to evaluate our proposed ESPN framework and DA-LSTM-CNN model. The empirical results show that incorporating features derived from the ESPN improves forecasting accuracy and our DA-LSTM-CNN significantly outperforms the state-of-the-art models. Further, we use a case study to illustrate the explainability of the DA-LSTM-CNN, which could guide future setups for hotel demand forecasting systems. We discuss how stakeholders can benefit from our proposed ESPN framework and DA-LSTM-CNN model.

show abstract

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

Zhang

Tian

2023

Journal of Forecasting

View full text Add to dashboard Cite

Accurate forecasting tourism demand is crucial for improving the economic benefits of tourist attractions, but it is a challenging task. In this paper, we propose an effective daily tourism forecast model, principal component analysis‐grey wolf optimizer‐extreme learning machine (PCA‐GWO‐ELM), based on Baidu index data, holiday data, and weather data. Our model uses PCA to reduce the dimensionality of the data and employs the GWO to optimize the number of neural networks in the hidden layer of the ELM model, improving its forecast performance. We conduct an empirical study using the collected tourist data of Mount Siguniang. The results show that the proposed hybrid forecasting model outperforms other models in daily tourism demand forecasting, making it a potential candidate method for practitioners and researchers studying tourism demand forecasting.

show abstract

Novel deep learning approach for forecasting daily hotel demand with agglomeration effect

Cited by 32 publications

References 49 publications

Daily hotel demand forecasting with spatiotemporal features

Daily hotel demand forecasting with spatiotemporal features

What online review features really matter? An explainable deep learning approach for hotel demand forecasting

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

Contact Info

Product

Resources

About