Does location affect the mechanism of tourism competitiveness? Evidence from machine learning analysis

Evaluation of tourism competitiveness is crucial for the development of destinations. However, a research gap exists in comprehending the spatial variances in the factors that influence tourism competitiveness. This study aims to fill this gap by empirically investigating the spatially heterogeneous effects of determinants related to tourism competitiveness. To achieve this, we utilized multi-source data, geographically neural network weighted regression, and Shapley additive explanations. The results revealed that market demand, physiography, and attractions are the most significant factors contributing to tourism competitiveness. Furthermore, the relative importance of these influencing factors varies across locations, based on different destination types, market contexts, and resource characteristics. These findings provide valuable implications for policymakers to enhance destination competitiveness through adopting localized strategies.