| To implement strategies to reduce environmental impact while optimizing infrastructure and enhancing the overall visitor experience, there is a need to analyze and comprehend the patterns of tourist flow. In addition, weather variability can significantly impact the number of tourists visiting a destination. Thus, when analyzing tourist flows, it is essential to take account of weather variations. In this paper, a thorough analysis of the dynamics of monthly tourist flows per day and year is investigated, by using advanced machine learning techniques, specifically BIRCH. This approach allows the discerning of distinctive patterns and clusters within the tourist data. Furthermore, LightGBM is used with the above tourist data, to project the expected tourist flow based on date-time and weather fluctuations. The findings reveal how weather fluctuations influence tourist flow, providing insights for sustainable tourism practices and resilient management strategies, in response to weather variability, while showcasing an accuracy of 98%. |
*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.