Evaluating machine learning techniques for predicting tourist occupancy: an experiment with pre- and post-pandemic COVID-19 data
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/138476
Título: | Evaluating machine learning techniques for predicting tourist occupancy: an experiment with pre- and post-pandemic COVID-19 data |
---|---|
Autor/es: | Moreno-Izquierdo, Luis | Más-Ferrando, Adrián | Perles Ribes, José Francisco | Rubia, Antonio | Torregrosa, Teresa |
Grupo/s de investigación o GITE: | Economía de la Innovación y de la Inteligencia Artificial (ECO-IA) | Finanzas de Mercado y Econometría Financiera | Economía del Turismo, Recursos Naturales y Nuevas Tecnologías (INNATUR) |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Análisis Económico Aplicado | Universidad de Alicante. Departamento de Economía Financiera y Contabilidad | Universidad de Alicante. Instituto Interuniversitario de Economía Internacional |
Palabras clave: | Tourist occupancy | Airbnb | Prediction | Tourist demand | Machine learning |
Fecha de publicación: | 12-nov-2023 |
Editor: | Taylor & Francis |
Cita bibliográfica: | Current Issues in Tourism. 2023. https://doi.org/10.1080/13683500.2023.2282163 |
Resumen: | This paper analyses the prediction capacity of machine learning techniques under severe demand shocks. Specifically, three methods – Naive Bayes, Random Forest and Support Vector Machine – are tested in predicting rental occupancy for tourist accommodation in the city of Madrid. We compare two different scenarios: firstly, the predictive capacity in the years prior to COVID-19 and, secondly, the ability to anticipate demand behaviour once the pandemic started. The results demonstrate first that without market disturbances, the Random Forest model exhibits the best predictive capability. Second, the COVID-19 pandemic caused such major changes that none of the three tested models are entirely reliable, although the Random Forest and Naive Bayes models outperform the SVM model. As a methodological novelty, this paper includes occupancy quantiles to resolve problems with available data and temporal biases. |
Patrocinador/es: | This study has been carried out in the framework of the research project ‘Digital Transition and Innovation in the Labour Market and Mature Sectors. Taking Advantage of AI and Platform Economy (DILATO)’, funded by the Spanish Ministry of Science and Innovation as a 2021Green and Digital Transition Project, with reference [grant number TED2021-129600A-I00]. |
URI: | http://hdl.handle.net/10045/138476 |
ISSN: | 1368-3500 (Print) | 1747-7603 (Online) |
DOI: | 10.1080/13683500.2023.2282163 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/article |
Derechos: | © 2023 Informa UK Limited, trading as Taylor & Francis Group |
Revisión científica: | si |
Versión del editor: | https://doi.org/10.1080/13683500.2023.2282163 |
Aparece en las colecciones: | INV - ECO-IA - Artículos de Revistas INV - INNATUR - Artículos de Revistas INV - Finanzas de Mercado y Econometría Financiera - Artículos de Revistas |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Moreno-Izquierdo_etal_2023_CurrIssTourism_final.pdf | Versión final (acceso restringido) | 1,69 MB | Adobe PDF | Abrir Solicitar una copia |
Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.