{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T22:34:12Z","timestamp":1769812452631,"version":"3.49.0"},"reference-count":42,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>To address the limitations of traditional tourism demand forecasting models in leveraging multi-source data and their lack of interpretability, this study proposes an integrated multi-data-driven interpretable forecasting framework incorporating historical visitor volumes, social media activities, holiday schedules, weather conditions, and seasonal indicators. This study develops a system-oriented tourism demand forecasting framework that integrates a Variable Selection Network (VSN) and an enhanced long short-term memory (xLSTM) architecture to jointly model and interpret multi-source demand drivers. The VSN module employs a dynamic feature weighting mechanism to automatically discern distribution characteristics and relevance variations across heterogeneous data sources, thereby assigning adaptive weights to input variables. The xLSTM model incorporates innovative exponential gating and matrix memory structures, enabling rapid adaptation to sudden tourist flow fluctuations while effectively capturing long-term cyclical dependencies. By combining VSN-derived feature importance weights with SHAP-based prediction attribution analysis, this framework offers dual-level interpretability\u2014in both input feature selection and output explanation. Experimental results demonstrate that social media data significantly reflect tourist attention and travel intention and reveal distinctive demand-driving mechanisms for various types of tourism destinations. The study provides theoretical insights and empirical support for advancing tourism demand forecasting and management strategies.<\/jats:p>","DOI":"10.3390\/systems14020146","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T11:09:22Z","timestamp":1769771362000},"page":"146","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on Interpretable Tourism Demand Forecasting Based on VSN\u2013xLSTM Model"],"prefix":"10.3390","volume":"14","author":[{"given":"Hanpo","family":"Hou","sequence":"first","affiliation":[{"name":"School of Business, Beijing Technology and Business University, Beijing 102488, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4721-5125","authenticated-orcid":false,"given":"Haiying","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Business, Beijing Technology and Business University, Beijing 102488, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1177\/10963480231223151","article-title":"Tourism and Hospitality Forecasting with Big Data: A Systematic Review of the Literature","volume":"49","author":"Wu","year":"2025","journal-title":"J. Hosp. Tour. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"103675","DOI":"10.1016\/j.annals.2023.103675","article-title":"Forecasting Daily Tourism Demand with Multiple Factors","volume":"103","author":"Xu","year":"2023","journal-title":"Ann. Tour. Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1016\/j.annals.2019.01.014","article-title":"Tourism Demand Forecasting: A Deep Learning Approach","volume":"75","author":"Law","year":"2019","journal-title":"Ann. Tour. Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"104056","DOI":"10.1016\/j.im.2024.104056","article-title":"Daily Forecasting of Tourism Demand: An ST-LSTM Model with Social Network Service Co-Occurrence Similarity","volume":"62","author":"Luo","year":"2025","journal-title":"Inf. Manag."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kim, D.-K., Shyn, S.K., Kim, D., Jang, S., and Kim, K. (2021, January 5\u20137). A Daily Tourism Demand Prediction Framework Based on Multi-Head Attention CNN: The Case of The Foreign Entrant in South Korea. Proceedings of the 2021 IEEE Symposium Series on Computational Intelligence (SSCI), Orlando, FL, USA.","DOI":"10.1109\/SSCI50451.2021.9659950"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1016\/j.ins.2023.01.095","article-title":"A Time Series Attention Mechanism Based Model for Tourism Demand Forecasting","volume":"628","author":"Dong","year":"2023","journal-title":"Inf. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1016\/j.annals.2018.12.001","article-title":"A Review of Research on Tourism Demand Forecasting: Launching the Annals of Tourism Research Curated Collection on Tourism Demand Forecasting","volume":"75","author":"Song","year":"2019","journal-title":"Ann. Tour. Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"103277","DOI":"10.1016\/j.annals.2021.103277","article-title":"Forecasting Tourism Demand: Developing a General Nesting Spatiotemporal Model","volume":"90","author":"Jiao","year":"2021","journal-title":"Ann. Tour. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1177\/0047287518759226","article-title":"Modeling and Forecasting Regional Tourism Demand Using the Bayesian Global Vector Autoregressive (BGVAR) Model","volume":"58","author":"Assaf","year":"2019","journal-title":"J. Travel Res."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.tourman.2007.07.016","article-title":"Tourism Demand Modelling and Forecasting\u2014A Review of Recent Research","volume":"29","author":"Song","year":"2008","journal-title":"Tour. Manag."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1080\/10941665.2019.1709876","article-title":"A Deep Learning Approach for Daily Tourist Flow Forecasting with Consumer Search Data","volume":"25","author":"Zhang","year":"2020","journal-title":"Asia Pac. J. Tour. Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"102925","DOI":"10.1016\/j.annals.2020.102925","article-title":"Bayesian BILSTM Approach for Tourism Demand Forecasting","volume":"83","author":"Kulshrestha","year":"2020","journal-title":"Ann. Tour. Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2021","DOI":"10.1177\/13548166211025160","article-title":"Tourism Demand Forecasting: An Ensemble Deep Learning Approach","volume":"28","author":"Sun","year":"2022","journal-title":"Tour. Econ."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"103255","DOI":"10.1016\/j.annals.2021.103255","article-title":"Tourism Demand Forecasting with Time Series Imaging: A Deep Learning Model","volume":"90","author":"Bi","year":"2021","journal-title":"Ann. Tour. Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"103271","DOI":"10.1016\/j.annals.2021.103271","article-title":"Multi-Attraction, Hourly Tourism Demand Forecasting","volume":"90","author":"Zheng","year":"2021","journal-title":"Ann. Tour. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"110275","DOI":"10.1016\/j.knosys.2023.110275","article-title":"A Graph-Attention Based Spatial-Temporal Learning Framework for Tourism Demand Forecasting","volume":"263","author":"Zhou","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1719","DOI":"10.1177\/00472875211040569","article-title":"Forecasting Daily Tourism Demand for Tourist Attractions with Big Data: An Ensemble Deep Learning Method","volume":"61","author":"Bi","year":"2022","journal-title":"J. Travel Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.tourman.2018.03.009","article-title":"Big Data in Tourism Research: A Literature Review","volume":"68","author":"Li","year":"2018","journal-title":"Tour. Manag."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.1177\/1354816619872592","article-title":"Data Source Combination for Tourism Demand Forecasting","volume":"26","author":"Hu","year":"2020","journal-title":"Tour. Econ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1080\/13683500.2023.2183818","article-title":"A Deep Learning Model Based on Multi-Source Data for Daily Tourist Volume Forecasting","volume":"27","author":"Han","year":"2024","journal-title":"Curr. Issues Tour."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Huang, J., and Zhang, C. (2024). Daily Tourism Demand Forecasting with the iTransformer Model. Sustainability, 16.","DOI":"10.3390\/su162310678"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"109488","DOI":"10.1109\/ACCESS.2021.3102616","article-title":"A Forecast Model of Tourism Demand Driven by Social Network Data","volume":"9","author":"Peng","year":"2021","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1814","DOI":"10.1080\/13683500.2023.2216882","article-title":"Tourism Demand Forecasting Based on User-Generated Images on OTA Platforms","volume":"27","author":"Ma","year":"2024","journal-title":"Curr. Issues Tour."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"103838","DOI":"10.1016\/j.annals.2024.103838","article-title":"Tourism Demand Forecasting Using Short Video Information","volume":"109","author":"Hu","year":"2024","journal-title":"Ann. Tour. Res."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wu, G., and Ding, X. (2023). Which Type of Tourism Short Video Content Inspires Potential Tourists to Travel. Front. Psychol., 14.","DOI":"10.3389\/fpsyg.2023.1086516"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"5437","DOI":"10.1007\/s00521-022-07967-y","article-title":"Interpretable Tourism Volume Forecasting with Multivariate Time Series under the Impact of COVID-19","volume":"35","author":"Wu","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"14493","DOI":"10.1007\/s10489-022-04254-0","article-title":"Interpretable Tourism Demand Forecasting with Temporal Fusion Transformers amid COVID-19","volume":"53","author":"Wu","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1007\/s10489-025-06715-8","article-title":"End-to-End Multidimensional Interpretable Tourism Demand Combined Forecasting Model Based on Feature Fusion","volume":"55","author":"Wu","year":"2025","journal-title":"Appl. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"102899","DOI":"10.1016\/j.annals.2020.102899","article-title":"Group Pooling for Deep Tourism Demand Forecasting","volume":"82","author":"Zhang","year":"2020","journal-title":"Ann. Tour. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1175\/MWR-D-13-00271.1","article-title":"Heteroscedastic Extended Logistic Regression for Postprocessing of Ensemble Guidance","volume":"142","author":"Messner","year":"2014","journal-title":"Mon. Weather. Rev."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Kopyt, M., Piotrowski, P., and Baczy\u0144ski, D. (2024). Short-Term Energy Generation Forecasts at a Wind Farm\u2014A Multi-Variant Comparison of the Effectiveness and Performance of Various Gradient-Boosted Decision Tree Models. Energies, 17.","DOI":"10.3390\/en17236194"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, Y., Xie, G., Wang, S., and Law, R. (2025). Tourism Demand Forecasting with an Enhanced Interpretability Framework. Curr. Issues Tour., 1\u201324.","DOI":"10.1080\/13683500.2025.2466801"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1111\/rssb.12377","article-title":"Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models","volume":"82","author":"Apley","year":"2020","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2064","DOI":"10.1002\/for.3097","article-title":"Explainable Machine Learning Techniques Based on Attention Gate Recurrent Unit and Local Interpretable Model-agnostic Explanations for Multivariate Wind Speed Forecasting","volume":"43","author":"Peng","year":"2024","journal-title":"J. Forecast."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3194","DOI":"10.1002\/for.3178","article-title":"Shapley-value-based Forecast Combination","volume":"43","author":"Franses","year":"2024","journal-title":"J. Forecast."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"107021","DOI":"10.1016\/j.engappai.2023.107021","article-title":"Transformer for Object Detection: Review and Benchmark","volume":"126","author":"Li","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1177\/1096348020934046","article-title":"Forecasting Tourist Daily Arrivals with A Hybrid Sarima\u2013Lstm Approach","volume":"45","author":"Wu","year":"2021","journal-title":"J. Hosp. Tour. Res."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"103887","DOI":"10.1016\/j.annals.2024.103887","article-title":"Forecast by Mixed-Frequency Dynamic Panel Model","volume":"110","author":"Liu","year":"2025","journal-title":"Ann. Tour. Res."},{"key":"ref_39","first-page":"100782","article-title":"The (Negative) Impact of Violent and Gore TV Crime Series on Destination Image and Travel Motivation","volume":"28","author":"Azevedo","year":"2023","journal-title":"J. Destin. Mark. Manag."},{"key":"ref_40","unstructured":"Beck, M., P\u00f6ppel, K., Spanring, M., Auer, A., Prudnikova, O., Kopp, M., Klambauer, G., Brandstetter, J., and Hochreiter, S. (2024). xLSTM: Extended Long Short-Term Memory. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"20200209","DOI":"10.1098\/rsta.2020.0209","article-title":"Time-Series Forecasting with Deep Learning: A Survey","volume":"379","author":"Lim","year":"2021","journal-title":"Phil. Trans. R. Soc. A"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"103699","DOI":"10.1016\/j.ipm.2024.103699","article-title":"Forecasting Tourism Demand with Search Engine Data: A Hybrid CNN-BiLSTM Model Based on Boruta Feature Selection","volume":"61","author":"Chen","year":"2024","journal-title":"Inf. Process. Manag."}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/2\/146\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T11:35:35Z","timestamp":1769772935000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/2\/146"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,30]]},"references-count":42,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["systems14020146"],"URL":"https:\/\/doi.org\/10.3390\/systems14020146","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,30]]}}}