Abstract for: AI-Supported Dynamic Modeling of Utah’s Ski Tourism: Forecasting Seasonal Visitation Amid Global and Political Change
Introduction Utah’s winter tourism economy is deeply influenced by ski travel, particularly from international visitors. With rising global uncertainty and evolving traveler sentiment, tourism planners must anticipate how shifts in perception and policy will affect visitation and spending. This study focuses on forecasting and evaluating scenario-based impacts leading into key winter travel seasons and related to the recently announced Winter Olympics. Approach We use AI, particularly large language models (LLMs), to generate Python-based simulations of dynamic scenarios. These models incorporate early signals from both public and private data sources, in partnership with the Utah Governor’s Office of Tourism. We emphasize identifying contributing factors such as geopolitical shifts, media sentiment, and macroeconomic trends, and how they influence international travel behavior. Results Preliminary findings indicate that traveler sentiment from Canada and long-haul markets is increasingly divided. Some cohorts appear to be impacted by the announcement of the Winter Olympics, potentially delaying visits in anticipation of future travel. This may lead to seasonal demand imbalances and shifting spending patterns across winter quarters. Discussion This work demonstrates how AI-assisted dynamic modeling can rapidly test scenario outcomes and surface key influence factors. The approach supports more agile and informed decision-making in tourism planning under uncertainty.