A Deep Learning–Powerd Regional Industrial Synery Model: Simulating the Multi-Tiered Catalytic Effects of the “Suchao” Sporting Event on Regional Economy

Amidst the national initiative to integrate sports events into scenic areas, urban blocks, and commercial districts, mass sporting events have emerged as a pivotal driver of regional economic development. Leveraging data from the “Suchao” event series and combining panel regression with graph neural network (GNN) methodologies, this study simulates the multi-tiered economic impacts of mass sporting events on regional GDP growth, cultural-tourism consumption, and specialty industries. Findings demonstrate that event quality indices significantly amplify GDP growth rates, tourism expenditure, and local product sales, catalyzing a synergistic “event-cultural tourism-industry” growth cycle. The GNN model further identifies key communication pathways and nodal influence patterns, highlighting underdeveloped regions’ latent economic spillover potential and the moderating effects of heterogeneous contextual variables such as transportation networks and industrial configurations. To optimize outcomes, we propose establishing a star-rated mass sporting event evaluation system and a closed-loop “event-driven communication-investment attraction” policy mechanism, and enabling precise resource allocation and fostering “event + industry” synergy.