What are the most influential drivers of tourism destination competitiveness?

Аннотация

This study investigates the complex drivers behind the competitiveness of global tourism destinations, employing a comprehensive machine-learning approach to analyze data from the World Economic Forum and the UNWTO for 2019 and 2021. By utilizing decision trees, random forest algorithms, and Partial Dependence Plots (PDPs), the research identifies key factors—such as ICT Readiness, Human Resources, Non-Leisure Resources, and Price Competitiveness—that significantly influence tourism competitiveness. Key findings indicate that ICT Readiness stands out as a critical determinant across all countries, highlighting the indispensable role of digital infrastructure in the tourism sector. For the 20 leading destinations by international arrivals, non- leisure resources and human resources are pivotal, suggesting that offering a wide array of activities and maintaining a skilled workforce are essential for a competitive edge. This research contributes valuable perspectives for policymakers, industry stakeholders, and academics, enriching the global dialogue on strategies for fostering competitive and sustainable tourism industries. Introduction. Tourism scholarship recognizes the difficulty of defining tourism competitiveness due to the diverse factors that affect a destination's viability (Fernández et al., 2020). According to Lee (2015), tourism competitiveness depends on long-term government policy, effective planning, and capable administration. Countries develop national tourism policies, advertise destinations, and create tourism-focused institutions in various ways (Paskaleva-Shapira, 2007). Enhancing destination competitiveness is crucial, prompting nations to implement various advertising strategies, improve infrastructure, logistics, and transportation, and train staff to interact with international tourists (Kumar et al., 2024). The importance of destination competitiveness is more pronounced than ever (Song et al., 2023; Xu & Au, 2023). It encompasses natural and cultural resources, infrastructure, service quality, digital transformation, and environmental stewardship (Luštickỳ & Štumpf, 2021; Akin et al., 2021; Dwyer, 2022). Destinations seeking international tourists, economic growth, and sustainable development must understand and enhance these factors amid increasing competition and shifting global dynamics (Huang et al., 2023; Yamagishi, 2023). Research on tourism destination competitiveness is extensive, utilizing various theoretical frameworks to understand the complex factors impacting success (Cronjé & du Plessis, 2020; Gomezelj & Mihalič, 2008). Theories such as Porter's Diamond, the Resource-Based View (RBV), the Tourism Area Life Cycle (TALC), and destination management and marketing have shed light on competitiveness (Cronjé & du Plessis, 2020). However, the need for advanced analytical tools like machine learning to synthesize these perspectives and provide nuanced insights into competitiveness drivers is growing, especially given the industry's challenges and opportunities (Huang et al., 2023). This research draws on the Travel & Tourism Competitiveness Index (TTCI), which includes metrics from 117 countries for 2019 and 2021, to examine a variety of competitiveness factors. The TTCI provides a comprehensive assessment of the tourism competitiveness of different countries by evaluating various dimensions, such as the enabling environment, travel and tourism policy and enabling conditions, infrastructure, natural and cultural resources, and price competitiveness. To gain a deeper understanding, this study focuses on both a broad analysis of all 117 countries and a detailed examination of the top 20 countries by international arrivals. By comparing the factors influencing 211 STUDENTLERDI BIRLESTIRIW: XALÍQARALÍQ IZERTLEWLER HÁM PÁNLER BOYINSHA BIRGE ISLESIW 1-XALÍQARALÍQ STUDENTLER KONFERENCIYASÍ. NÓKIS, 2025-JÍL 20-21-MAY tourism competitiveness across these two groups, this study aims to identify the key drivers and how they differ in their impact on general and top destinations. The primary purpose of this study is to deepen our understanding of the competitiveness of tourism destinations by reviewing and integrating key theoretical perspectives related to tourism destination competitiveness. Additionally, it aims to utilize machine learning algorithms to explore the multifaceted drivers of competitiveness in the current global tourism landscape, specifically identifying and analyzing the drivers of competitiveness for the world's top 20 tourism destinations. This focused examination provides valuable insights and actionable strategies for destination managers and policymakers to enhance competitiveness and sustainability. By leveraging advanced machine learning techniques, such as decision trees, random forests, and Partial Dependence Plots (PDPs), the research aims to offer a comprehensive and nuanced analysis of the factors that contribute to tourism destination competitiveness. Follo