Pub Date : 2025-10-16DOI: 10.1016/j.tourman.2025.105326
Jaume Rosselló-Nadal, María Sard
Tourism taxes have become increasingly relevant as destinations seek to balance public revenue generation with the sustainability of local communities and tourism competitiveness. While traditional taxation debates focus on voter impact, tourism taxation shifts the burden to non-residents, raising distinct economic and social considerations. This paper offers a comprehensive review of the current landscape of tourism taxation, analysing its regulatory motivations, the externalities it seeks to address, demand responsiveness, and levels of stakeholder acceptance. Drawing on existing literature, the study explores how tourism taxes are designed and implemented and assesses their potential as instruments for promoting more resilient and sustainable destinations in the face of growing visitor pressure and evolving global challenges.
{"title":"Tourism Taxation: Balancing revenues, competitiveness and sustainability in destination management","authors":"Jaume Rosselló-Nadal, María Sard","doi":"10.1016/j.tourman.2025.105326","DOIUrl":"10.1016/j.tourman.2025.105326","url":null,"abstract":"<div><div>Tourism taxes have become increasingly relevant as destinations seek to balance public revenue generation with the sustainability of local communities and tourism competitiveness. While traditional taxation debates focus on voter impact, tourism taxation shifts the burden to non-residents, raising distinct economic and social considerations. This paper offers a comprehensive review of the current landscape of tourism taxation, analysing its regulatory motivations, the externalities it seeks to address, demand responsiveness, and levels of stakeholder acceptance. Drawing on existing literature, the study explores how tourism taxes are designed and implemented and assesses their potential as instruments for promoting more resilient and sustainable destinations in the face of growing visitor pressure and evolving global challenges.</div></div>","PeriodicalId":48469,"journal":{"name":"Tourism Management","volume":"113 ","pages":"Article 105326"},"PeriodicalIF":12.4,"publicationDate":"2025-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-15DOI: 10.1016/j.tourman.2025.105328
Jiekuan Zhang
This study applies the theory of externality internalization in environmental economics to develop a novel city-level panel dataset combining statistical data and textual evidence. Through empirical analysis of 286 Chinese cities, this study establishes the causal relationship between the carbon generalized system of preferences (CGSP) pilot policy and tourism development while identifying its underlying mechanisms. The results demonstrate that CGSP overcomes the cost-constraining paradigm typical of conventional environmental policies, effectively driving tourism advancement through integrated value endowment, information feedback, and behavioral incentivization mechanisms. Crucially, digitalization and green finance simultaneously reinforce CGSP's positive effects on tourism and enhance the functional efficacy of these mechanisms. Moreover, the tourism-promoting impact exhibits significant heterogeneity. This research pioneers the integration of environmental economics with digital transformation theory and financial intermediation theory. By constructing a comprehensive “policy signals-behavioral responses-ecological capital” mechanistic framework, this study presents China's approach to synergistic environmental-tourism development.
{"title":"Tourism effects of the carbon generalized system of preferences: Value creation and heterogeneous responses","authors":"Jiekuan Zhang","doi":"10.1016/j.tourman.2025.105328","DOIUrl":"10.1016/j.tourman.2025.105328","url":null,"abstract":"<div><div>This study applies the theory of externality internalization in environmental economics to develop a novel city-level panel dataset combining statistical data and textual evidence. Through empirical analysis of 286 Chinese cities, this study establishes the causal relationship between the carbon generalized system of preferences (CGSP) pilot policy and tourism development while identifying its underlying mechanisms. The results demonstrate that CGSP overcomes the cost-constraining paradigm typical of conventional environmental policies, effectively driving tourism advancement through integrated value endowment, information feedback, and behavioral incentivization mechanisms. Crucially, digitalization and green finance simultaneously reinforce CGSP's positive effects on tourism and enhance the functional efficacy of these mechanisms. Moreover, the tourism-promoting impact exhibits significant heterogeneity. This research pioneers the integration of environmental economics with digital transformation theory and financial intermediation theory. By constructing a comprehensive “policy signals-behavioral responses-ecological capital” mechanistic framework, this study presents China's approach to synergistic environmental-tourism development.</div></div>","PeriodicalId":48469,"journal":{"name":"Tourism Management","volume":"113 ","pages":"Article 105328"},"PeriodicalIF":12.4,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145325225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-11DOI: 10.1016/j.tourman.2025.105323
Henri Kuokkanen , Dai-In Danny Han , Ksenia Kirillova , Malu Boerwinkel
While hospitality and tourism industries engage in social and environmental responsibility through various initiatives, these efforts often fail to generate business benefits that offset costs and enhance performance. The concept of ethically meaningful experiences (EME) was introduced earlier to address this gap by immersing customers in corporate social responsibility (CSR) without invoking the notion of sacrifice associated with sustainable behavior. This study is the first to examine which design aspects of an experience can trigger consumers’ evaluations of ethical meaningfulness. We demonstrate that social connection is the primary driver of ethical meaning and positive affect, while information transparency functions as a secondary, reinforcing pathway. Beyond offering the first empirical support for EME, the results extend its initial conceptualization, enrich the literature on ethical and experiential consumption, and carry significant practical implications for how businesses should engage customers in CSR efforts.
{"title":"Crafting ethically meaningful experiences: Towards experiential corporate social responsibility","authors":"Henri Kuokkanen , Dai-In Danny Han , Ksenia Kirillova , Malu Boerwinkel","doi":"10.1016/j.tourman.2025.105323","DOIUrl":"10.1016/j.tourman.2025.105323","url":null,"abstract":"<div><div>While hospitality and tourism industries engage in social and environmental responsibility through various initiatives, these efforts often fail to generate business benefits that offset costs and enhance performance. The concept of ethically meaningful experiences (EME) was introduced earlier to address this gap by immersing customers in corporate social responsibility (CSR) without invoking the notion of sacrifice associated with sustainable behavior. This study is the first to examine which design aspects of an experience can trigger consumers’ evaluations of ethical meaningfulness. We demonstrate that social connection is the primary driver of ethical meaning and positive affect, while information transparency functions as a secondary, reinforcing pathway. Beyond offering the first empirical support for EME, the results extend its initial conceptualization, enrich the literature on ethical and experiential consumption, and carry significant practical implications for how businesses should engage customers in CSR efforts.</div></div>","PeriodicalId":48469,"journal":{"name":"Tourism Management","volume":"113 ","pages":"Article 105323"},"PeriodicalIF":12.4,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145261686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-11DOI: 10.1016/j.tourman.2025.105322
Peng A. Yang, Juho Pesonen
The concept of conative image, originating from psychology, has been widely applied in tourism research. Within the cognitive–affective–conative (CAC) model, it is traditionally regarded as the consequential component of destination image. However, it suffers from conceptual vagueness, theoretical tautology, limited consideration of volitional processes and inadequate adaptation to today's data-rich environments. These issues also undermine its explanatory capacity to analyse the factors driving tourist behaviour. To overcome these challenges, we propose an extended conative framework for tourism destination research (eCFTD). This approach separates behavioural intentions from actual actions, removes conative elements from destination image to avoid circular reasoning and integrates volitional factors, such as self-efficacy, action planning and intention stability. Applicable to physical, virtual and synthetic destinations, eCFTD employs technology-driven nudging to enhance destination management. By addressing key limitations, it offers a rigorous and data-informed approach that advances both tourism research and practical management.
{"title":"Rethinking conative image","authors":"Peng A. Yang, Juho Pesonen","doi":"10.1016/j.tourman.2025.105322","DOIUrl":"10.1016/j.tourman.2025.105322","url":null,"abstract":"<div><div>The concept of conative image, originating from psychology, has been widely applied in tourism research. Within the cognitive–affective–conative (CAC) model, it is traditionally regarded as the consequential component of destination image. However, it suffers from conceptual vagueness, theoretical tautology, limited consideration of volitional processes and inadequate adaptation to today's data-rich environments. These issues also undermine its explanatory capacity to analyse the factors driving tourist behaviour. To overcome these challenges, we propose an extended conative framework for tourism destination research (eCFTD). This approach separates behavioural intentions from actual actions, removes conative elements from destination image to avoid circular reasoning and integrates volitional factors, such as self-efficacy, action planning and intention stability. Applicable to physical, virtual and synthetic destinations, eCFTD employs technology-driven nudging to enhance destination management. By addressing key limitations, it offers a rigorous and data-informed approach that advances both tourism research and practical management.</div></div>","PeriodicalId":48469,"journal":{"name":"Tourism Management","volume":"113 ","pages":"Article 105322"},"PeriodicalIF":12.4,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145261678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-10DOI: 10.1016/j.tourman.2025.105324
David Boto-García , María Santana-Gallego
The economic benefits of hosting mega-sport events have been widely debated. However, empirical evidence on their overall impact on economic activity remains inconclusive, largely due to methodological challenges. This study analyses the economic impact of the two largest mega-sport events, the Summer Olympic Games (SOGs) and FIFA World Cup (WC), on international tourist arrivals, GDP per capita, and the share of employment and value added in the tertiary sector. Using a panel dataset from 1991 to 2023, we provide causal estimates through dynamic difference-in-differences estimators. Considering suitable control groups, we distinguish between anticipation and legacy effects, account for staggered treatment timing, and accommodate heterogeneous treatment effects. Results indicate moderate anticipatory effects on tourism and notable impacts on employment and GDP per capita, with the SOGs exhibiting a stronger impact. These findings provide a nuanced understanding of the economic consequences of hosting mega-sport events and highlight the limitations of standard approaches.
{"title":"Old questions, new methods: Revisiting the economic effects of hosting mega-sport events","authors":"David Boto-García , María Santana-Gallego","doi":"10.1016/j.tourman.2025.105324","DOIUrl":"10.1016/j.tourman.2025.105324","url":null,"abstract":"<div><div>The economic benefits of hosting mega-sport events have been widely debated. However, empirical evidence on their overall impact on economic activity remains inconclusive, largely due to methodological challenges. This study analyses the economic impact of the two largest mega-sport events, the Summer Olympic Games (SOGs) and FIFA World Cup (WC), on international tourist arrivals, GDP per capita, and the share of employment and value added in the tertiary sector. Using a panel dataset from 1991 to 2023, we provide causal estimates through dynamic difference-in-differences estimators. Considering suitable control groups, we distinguish between anticipation and legacy effects, account for staggered treatment timing, and accommodate heterogeneous treatment effects. Results indicate moderate anticipatory effects on tourism and notable impacts on employment and GDP per capita, with the SOGs exhibiting a stronger impact. These findings provide a nuanced understanding of the economic consequences of hosting mega-sport events and highlight the limitations of standard approaches.</div></div>","PeriodicalId":48469,"journal":{"name":"Tourism Management","volume":"113 ","pages":"Article 105324"},"PeriodicalIF":12.4,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145261685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-10DOI: 10.1016/j.tourman.2025.105315
GuoQiong Ivanka Huang , Chen Jason Zhang , Wanyi Christina Zhou Torres , Xiling Xiong , Huahang Li
Artificial Intelligence has evolved from mimicking to enhancing or even surpassing human capabilities in specialized domains. Building on Turing's test and the theory of moral responsibility, this research delves into the ethical and perceptual dimensions of AI-generated content in tourism management through three studies. Study 1 (N=1400) assesses tourists' ability to distinguish AI-generated from human managerial responses and examines their perceptions of responsibility. Study 2 (N=700) develops and validates a multidimensional scale to measure Responsible AI within the tourism industry. Study 3 (N=600) uses a scenario-based experiment to evaluate how collaborative AI-human responses, compared to AI-only or human-only responses, influence tourists' attributions of responsibility and satisfaction, especially when the origin of the response is transparently disclosed. This research advances frameworks for responsible AI in tourism management and emphasizes ethical openness to align technological advances with societal well-being.
{"title":"Responsible AI and human collaboration in tourism management: Ethical considerations and identity disclosure","authors":"GuoQiong Ivanka Huang , Chen Jason Zhang , Wanyi Christina Zhou Torres , Xiling Xiong , Huahang Li","doi":"10.1016/j.tourman.2025.105315","DOIUrl":"10.1016/j.tourman.2025.105315","url":null,"abstract":"<div><div>Artificial Intelligence has evolved from mimicking to enhancing or even surpassing human capabilities in specialized domains. Building on Turing's test and the theory of moral responsibility, this research delves into the ethical and perceptual dimensions of AI-generated content in tourism management through three studies. Study 1 (<em>N=1400</em>) assesses tourists' ability to distinguish AI-generated from human managerial responses and examines their perceptions of responsibility. Study 2 (<em>N=700</em>) develops and validates a multidimensional scale to measure Responsible AI within the tourism industry. Study 3 (<em>N=600</em>) uses a scenario-based experiment to evaluate how collaborative AI-human responses, compared to AI-only or human-only responses, influence tourists' attributions of responsibility and satisfaction, especially when the origin of the response is transparently disclosed. This research advances frameworks for responsible AI in tourism management and emphasizes ethical openness to align technological advances with societal well-being.</div></div>","PeriodicalId":48469,"journal":{"name":"Tourism Management","volume":"113 ","pages":"Article 105315"},"PeriodicalIF":12.4,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145261680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
AI-powered robots can meet both functional and emotional consumer service needs through proactive engagement. Yet, excessive attentiveness may produce unintended negative outcomes. Drawing on conservation of resources theory, this research employs four studies and a single-paper meta-analysis to investigate how highly (vs. moderately) attentive robotic service influences tourists' intentions to discontinue use. Results show that highly attentive robotic service increases discontinuous usage intentions, and this effect unfolds sequentially through perceived threat to freedom and emotional exhaustion. Furthermore, information sensitivity and technology anxiety moderate the relationship between robotic attentiveness and discontinuous usage intentions. These findings offer strategic insights for tourism practitioners on deploying robotic services effectively to foster consumer acceptance of technology.
{"title":"Overservice backfires: The impact of high robot attentiveness on tourists' discontinuous usage intentions","authors":"Jinwei Wang , Yingzong Tang , Xin Chen , Songshan (Sam) Huang","doi":"10.1016/j.tourman.2025.105318","DOIUrl":"10.1016/j.tourman.2025.105318","url":null,"abstract":"<div><div>AI-powered robots can meet both functional and emotional consumer service needs through proactive engagement. Yet, excessive attentiveness may produce unintended negative outcomes. Drawing on conservation of resources theory, this research employs four studies and a single-paper meta-analysis to investigate how highly (vs. moderately) attentive robotic service influences tourists' intentions to discontinue use. Results show that highly attentive robotic service increases discontinuous usage intentions, and this effect unfolds sequentially through perceived threat to freedom and emotional exhaustion. Furthermore, information sensitivity and technology anxiety moderate the relationship between robotic attentiveness and discontinuous usage intentions. These findings offer strategic insights for tourism practitioners on deploying robotic services effectively to foster consumer acceptance of technology.</div></div>","PeriodicalId":48469,"journal":{"name":"Tourism Management","volume":"113 ","pages":"Article 105318"},"PeriodicalIF":12.4,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145261692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-08DOI: 10.1016/j.tourman.2025.105321
Dorine von Briel, Anna K. Zinn, Sara Dolnicar
Are people a different version of themselves when they leave home to go on vacation? If so, what are the differences, and do they offer an opportunity to make tourists behave in more environmentally sustainable ways? We test whether home and vacation place identity activate different environmental self-perceptions. Across three studies, we show that home and vacation place identity differ significantly in self-descriptive attributes and reported environmental responsibility. Results suggest that tourists do not abandon environmental values but temporarily perceive themselves differently. Leveraging home place identity for altering pre-vacation booking decisions or activating home place identity during the vacation, therefore, offers promising new approaches supporting environmental responsibility. With tourism generating 8.8 % of all carbon emissions, the positive environmental impact of any behaviour change would be substantial.
{"title":"Does activating home place identity on vacation have the potential to alter environmentally significant tourist behaviour?","authors":"Dorine von Briel, Anna K. Zinn, Sara Dolnicar","doi":"10.1016/j.tourman.2025.105321","DOIUrl":"10.1016/j.tourman.2025.105321","url":null,"abstract":"<div><div>Are people a different version of themselves when they leave home to go on vacation? If so, what are the differences, and do they offer an opportunity to make tourists behave in more environmentally sustainable ways? We test whether home and vacation place identity activate different environmental self-perceptions. Across three studies, we show that home and vacation place identity differ significantly in self-descriptive attributes and reported environmental responsibility. Results suggest that tourists do not abandon environmental values but temporarily perceive themselves differently. Leveraging home place identity for altering pre-vacation booking decisions or activating home place identity during the vacation, therefore, offers promising new approaches supporting environmental responsibility. With tourism generating 8.8 % of all carbon emissions, the positive environmental impact of any behaviour change would be substantial.</div></div>","PeriodicalId":48469,"journal":{"name":"Tourism Management","volume":"113 ","pages":"Article 105321"},"PeriodicalIF":12.4,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145261679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study proposes a hybrid predictive framework designed to forecast border tourism flows among the United States, Canada, and Mexico. Combining Fuzzy Markov Chains, Hidden Markov Models, and attention-based deep learning architectures (RNNs, GRUs, and CNNs), the model captures the complex and dynamic interplay between exchange rate volatility and broader macroeconomic conditions over forty years. Results show that tourist behavior is shaped by both current economic indicators and long-term economic memory, with attention mechanisms offering interpretable insights into spending and arrival trends. The SUOS model outperforms traditional forecasting approaches, demonstrating superior accuracy and scalability. Its interpretability also enables stakeholders to understand which economic factors drive tourism demand, supporting practical applications such as seasonal planning, marketing timing, and policy formulation. By bridging macroeconomic modeling with advanced AI, this research offers a robust and adaptive tool for anticipating tourism shifts in an increasingly uncertain global economy.
{"title":"Cross-border tourism in North America: A hybrid deep learning framework with macroeconomic indicators","authors":"Debojyoti Seth, Atul Sheel, Irem Onder, Muzaffer Uysal","doi":"10.1016/j.tourman.2025.105320","DOIUrl":"10.1016/j.tourman.2025.105320","url":null,"abstract":"<div><div>This study proposes a hybrid predictive framework designed to forecast border tourism flows among the United States, Canada, and Mexico. Combining Fuzzy Markov Chains, Hidden Markov Models, and attention-based deep learning architectures (RNNs, GRUs, and CNNs), the model captures the complex and dynamic interplay between exchange rate volatility and broader macroeconomic conditions over forty years. Results show that tourist behavior is shaped by both current economic indicators and long-term economic memory, with attention mechanisms offering interpretable insights into spending and arrival trends. The SUOS model outperforms traditional forecasting approaches, demonstrating superior accuracy and scalability. Its interpretability also enables stakeholders to understand which economic factors drive tourism demand, supporting practical applications such as seasonal planning, marketing timing, and policy formulation. By bridging macroeconomic modeling with advanced AI, this research offers a robust and adaptive tool for anticipating tourism shifts in an increasingly uncertain global economy.</div></div>","PeriodicalId":48469,"journal":{"name":"Tourism Management","volume":"113 ","pages":"Article 105320"},"PeriodicalIF":12.4,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145242018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-03DOI: 10.1016/j.tourman.2025.105314
Apostolos Ampountolas, Yunmei (Mabel) Bai
This study introduces Modern Portfolio Theory (MPT) as a unified framework for combining tourism-demand forecasts. By leveraging the complementarity of time-series models, machine-learning regressions, and deep-learning sequence models, we recast ensemble design as a mean–variance optimization problem. Each forecasting model is treated as an asset with an expected return (mean forecast accuracy) and risk (error variance and covariance). Using daily hotel data from a major U.S. East Coast city (2015–2019), we demonstrate that MPT-weighted ensembles outperform both individual models and traditional variance–covariance (VACO) blends, achieving MAPE values below 5.1% and reducing AvgRelMAE by up to 81.4% relative to a naïve benchmark. These findings advance tourism and hospitality forecasting by introducing a transferable efficiency frontier toolkit, enabling managers to explicitly balance forecast accuracy and volatility while making more informed pricing, staffing, and inventory decisions in volatile market environments.
{"title":"Optimizing hotel demand forecasting through ensemble models: A Modern Portfolio Theory approach","authors":"Apostolos Ampountolas, Yunmei (Mabel) Bai","doi":"10.1016/j.tourman.2025.105314","DOIUrl":"10.1016/j.tourman.2025.105314","url":null,"abstract":"<div><div>This study introduces Modern Portfolio Theory (MPT) as a unified framework for combining tourism-demand forecasts. By leveraging the complementarity of time-series models, machine-learning regressions, and deep-learning sequence models, we recast ensemble design as a mean–variance optimization problem. Each forecasting model is treated as an asset with an expected return (mean forecast accuracy) and risk (error variance and covariance). Using daily hotel data from a major U.S. East Coast city (2015–2019), we demonstrate that MPT-weighted ensembles outperform both individual models and traditional variance–covariance (VACO) blends, achieving MAPE values below 5.1% and reducing AvgRelMAE by up to 81.4% relative to a naïve benchmark. These findings advance tourism and hospitality forecasting by introducing a transferable efficiency frontier toolkit, enabling managers to explicitly balance forecast accuracy and volatility while making more informed pricing, staffing, and inventory decisions in volatile market environments.</div></div>","PeriodicalId":48469,"journal":{"name":"Tourism Management","volume":"113 ","pages":"Article 105314"},"PeriodicalIF":12.4,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号