The advent of big data has led to increased recognition of the benefits of machine learning models in the field of demand prediction. However, the limited transparency and interpretability of most existing machine learning models raises concerns regarding their applicability and effectiveness in facilitating informed decision making. Based on Subjective Expected Utility Theory, the present study attempts to address this challenge by proposing an interpretable machine learning framework, which contains a prediction module and an interpretation module. Results show that the framework enables accurate predictions and offers explanations of the predictions from the following four perspectives: feature importance, feature contribution, nonlinear relationship, and feature interaction. This study validated the prediction accuracy and interpretability of our framework through an ex-post analysis of demand data from two hotels in Xiamen, China. This study contributes to the hotel demand prediction literature and improves management decision making and resource optimization.
AmpountolasA (2018) Forecasting hotel demand uncertainty using time series Bayesian VAR models. Tourism Economics25(5): 734–756.
2.
AthanasopoulosGHyndmanRSongH, et al. (2009) Revised the tourism forecasting competition. International Journal of Forecasting27: 822–844.
3.
Ben JabeurSMefteh-WaliSVivianiJ-L (2021) Forecasting gold price with the XGBoost algorithm and SHAP interaction values. Annals of Operations Research334: 679–699.
4.
BiJ-WLiuYLiH (2020) Daily tourism volume forecasting for tourist attractions. Annals of Tourism Research83: 102923.
5.
BreimanL (2001) Random forests. Machine Learning45(1): 5–32.
6.
CaporinMCorazziniLCostolaM (2018) Measuring the behavioural component of the s&p 500 and its relationship to financial stress and aggregated earnings surprises. British Journal of Management30: 712–729.
7.
ChenTGuestrinCAssoc CompM (2016) XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco California USA, August 13 - 17, 2016, 785–794.
8.
ChenSWangXKZhangHY, et al. (2021) Customer purchase forecasting for online tourism: a data-driven method with multiplex behavior data. Tourism Management87: 104357.
9.
ContessiDViveritLPereiraL, et al. (2024) Decoding the future: proposing an interpretable machine learning model for hotel occupancy forecasting using principal component analysis. International Journal of Hospitality Management121: 103802.
CoussementKDe BockKGeuensS (2021) A decision-analytic framework for interpretable recommendation systems with multiple input data sources: a case study for a European e-tailer. Annals of Operations Research315(2): 671–694.
12.
De CaignyACoussementKVerbekeW, et al. (2021) Uplift modeling and its implications for B2B customer churn prediction: a segmentation-based modeling approach. Industrial Marketing Management99: 28–39.
13.
DieboldFMarianoR (2002) Comparing predictive accuracy. Journal of Business & Economic Statistics20: 134–144.
14.
DonaldRJ (1998) Efficient global optimization of expensive black-box function. Journal of Global Optimization13(4): 455–492.
15.
DuMLiuNHuX (2019) Techniques for interpretable machine learning. Communications of the ACM63(1): 68–77.
16.
ErkipN (2022) Can accessing much data reshape the theory? Inventory theory under the challenge of data-driven systems. European Journal of Operational Research308(3): 949–959.
17.
GouthierMHJNennstielCKernN, et al. (2022) The more the better? Data disclosure between the conflicting priorities of privacy concerns, information sensitivity and personalization in e-commerce. Journal of Business Research148: 174–189.
18.
HartmannJHeitmannMSiebertC, et al. (2022) More than a feeling: accuracy and application of sentiment analysis. International Journal of Research in Marketing40(1): 75–87.
HolodinskyJYuAKapralM, et al. (2021) Using random forests to model 90-day hometime in people with stroke. BMC Medical Research Methodology21(102): 1–12.
21.
HuMSongH (2020) Data source combination for tourism demand forecasting. Tourism Economics26(7): 1248–1265.
22.
HuangLZDengZ (2024) Tourism demand forecasting: an interpretable deep learning model. Tourism Analysis29(4): 465-479.
23.
HuangLZWeimin (2021) Novel deep learning approach for forecasting daily hotel demand with agglomeration effect. International Journal of Hospitality Management98: 103038.
24.
HuangLZhengW (2023) Hotel demand forecasting: a comprehensive literature review. Tourism Review78(1): 218–244.
25.
HuangLLiCZhengW (2022) Daily hotel demand forecasting with spatiotemporal features. International Journal of Contemporary Hospitality Management35(1): 26–45.
26.
JoyTTRanaSGuptaS, et al. (2020) Fast hyperparameter tuning using Bayesian optimization with directional derivatives. Knowledge-Based Systems205: 1–8.
27.
KimSLeeS (2023) Nonlinear relationships and interaction effects of an urban environment on crime incidence: application of urban big data and an interpretable machine learning method. Sustainable Cities and Society91: 104419.
28.
KimHSohnS (2010) Support vector machines for default prediction of SMEs based on technology credit. European Journal of Operational Research201: 838–846.
29.
KohaviR (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. International Joint Conference on Artificial Intelligence14(2): 1137–1145.
30.
LawRLiGFongDKC, et al. (2019) Tourism demand forecasting: a deep learning approach. Annals of Tourism Research75: 410–423.
31.
LeeHWangJFLeblonB (2020) Using linear regression, random forests, and support vector machine with unmanned aerial vehicle multispectral images to predict canopy nitrogen weight in corn. Remote Sensing12(13): 1–20.
32.
LiZ (2022) Extracting spatial effects from machine learning model using local interpretation method: an example of SHAP and XGBoost. Computers, Environment and Urban Systems96: 101845.
33.
LundbergSLeeS-I (2017) A unified approach to interpreting model predictions. In: 31st Conference on Neural Information Processing Systems. Long Beach, CA, USA, December 4 - 9, 2017, 4768–4777.
34.
LundbergSErionGChenH, et al. (2020) From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence2(1): 56–67.
35.
MahmoudiMPingleM (2018) Bounded rationality, ambiguity, and choice. Journal of Behavioral and Experimental Economics75: 141–153.
36.
MazzaranoMGalluccioGBorghesiS (2025) Italian urban tourism predictions using the holiday Climate Index. Tourism Economics31(4): 631–650.
37.
NguyenTZhouLChongA, et al. (2020) Predicting customer demand for remanufactured products: a data-mining approach. European Journal of Operational Research281: 543–558.
38.
OhHLeeS (2021) Evaluation and interpretation of tourist satisfaction for local Korean festivals using explainable AI. Sustainability13: 10901.
39.
OkESavochkinA (2021) Believing in forecasts, uncertainty, and rational expectations. Economic Theory74: 1–25.
40.
OztekinA (2016) A hybrid data analytic approach to predict college graduation status and its determinative factors. Industrial Management & Data Systems116: 1678–1699.
41.
PajalaTKorhonenPWalleniusJ (2016) Road to robust prediction of choices in deterministic MCDM. European Journal of Operational Research259: 229–235.
42.
PanBYangY (2017) Forecasting destination weekly hotel occupancy with big data. Journal of Travel Research56(7): 957–970.
43.
PelikanMGoldbergDECantu-PazE (1999) BOA: the bayesian optimization algorithm. In: Proceedings of the Genetic and Evolutionary Computation Conference, Melbourne VIC Australia, July 14 - 18, 2024, 525–532.
44.
RaiA (2019) Explainable AI: from black box to glass box. Journal of the Academy of Marketing Science48(1): 137–141.
45.
SchwartzZUysalMWebbT, et al. (2016) Hotel daily occupancy forecasting with competitive sets: a recursive algorithm. International Journal of Contemporary Hospitality Management28: 267–285.
46.
SenonerJNetlandTFeuerriegelS (2021) Using explainable artificial intelligence to improve process quality: evidence from semiconductor manufacturing. Management Science68(8): 5704–5723.
47.
SongHQiuRTRParkJ (2019) A review of research on tourism demand forecasting. Annals of Tourism Research75: 338–362.
48.
TangMFKingBPrattS (2017) Predicting hotel occupancies with public data: an application of oecd indices as leading indicators. Tourism Economics23(5): 1096–1113.
49.
WangCFengLQiY (2021) Explainable deep learning predictions for illness risk of mental disorders in Nanjing, China. Environmental Research202: 111740.
50.
WangLGopalRShankarR, et al. (2022a) Forecasting venue popularity on location‐based services using interpretable machine learning. Production and Operations Management31: 2773–2788.
51.
WangXWuYZhangA, et al. (2022b) Reinforced causal explainer for graph neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence45(2): 1–13.
52.
WuDSongHShenS (2017) New developments in tourism and hotel demand modeling and forecasting. International Journal of Contemporary Hospitality Management29(1): 507–529.
53.
YangYPanBSongH (2014) Predicting hotel demand using destination marketing organization’s web traffic data. Journal of Travel Research53(4): 433–447.
54.
YangYFanYJiangL, et al. (2022) Search query and tourism forecasting during the pandemic: when and where can digital footprints be helpful as predictors?Annals of Tourism Research93: 103365.
55.
YıldızMAydinMGökçayG, et al. (2023) The effect of intercultural sensitivity and ethnocentrism on health tourism awareness level in nurses: analysis with machine learning approach. Archives of Psychiatric Nursing46: 40–50.
56.
ZhangJYDuZJSunSL, et al. (2024) Perception of customer satisfaction and complaints based on BERTopic and interpretable machine learning: evidence from hotels in Xi’an. Current Issues in Tourism2024: 1–23.
57.
ZhengWJiHLinC, et al. (2019) Using a heuristic approach to design personalized urban tourism itineraries with hotel selection. Tourism Management76: 103956.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
