Forecasting Visitor Activity in a Historic Urban District: A Machine-Learning Framework for Destination Management

Historic urban districts face growing challenges in balancing visitor activity with the needs of residents, local businesses, accessibility, and mobility. This study investigates whether short-term visitor forecasts can support destination management and planning in these complex environments. Unlike most visitor-forecasting studies, which focus on large cities and major tourist destinations, this study examines forecasting in a small historic urban district where visitor activity is more variable and management resources are limited. Using hourly pedestrian counts, weather data, and temporal data from the historic urban district of Fredrikstad, Norway, this research forecasts pedestrian activity up to 24 h in advance. The sensors record all pedestrians and do not distinguish tourists from residents or other users. Consequently, pedestrian counts are treated as an operational proxy for overall visitor activity at this heritage destination. Forecasting performance was evaluated using statistical, machine-learning, deep-learning, and benchmark forecasting models. Random Forest achieved the strongest overall forecasting performance (MAE = 209.52; RMSE = 357.18), outperforming the seasonal naïve benchmark (MAE = 247.44; RMSE = 421.70). Random Forest and GRU both outperformed the seasonal naïve benchmark on MAE, demonstrating the value of incorporating weather, temporal, and sensor variables into short-term forecasting. The findings suggest that short-term visitor forecasts may support operational planning, mobility management, service coordination, and other day-to-day destination management decisions. By anticipating periods of increased visitor activity, destination managers, local authorities, and government officials will be better able to allocate resources and coordinate services. This study demonstrates the potential of predictive analytics and sensor technology to support visitor management and operational planning in historic urban districts.