Abstract—Large stadium events, such as sports games and concerts, have a significant impact on pedestrian flow, poten-tially resulting in missed business opportunities and threats to public safety. This study addresses the issue of sudden crowd surges caused by large-venue events by developing a predictive Big Data framework that integrates Wi-Fi sensing data, event schedules, and meteorological variables to forecast foot traffic. The study focuses on Sendagaya, Tokyo, an area that hosts multiple large-capacity venues. Using Random Forest regression, we evaluated our model that incorporates event and weather data and compared it with our baseline model, which uses only temporal features. Our results indicate that while temporal data alone yield stable predictions, incorporating event-specific and weather-related factors enhances the prediction accuracy of foot traffic peaks during large events. This research offers a scalable approach to urban crowd management, combining practical data collection using web scraping and multivariate modeling. These findings contribute both to Big Data modeling techniques and applications in local government, societal infrastructure planning, and marketing.
 
Keywords—urban computing, foot traffic, Wi-Fi sensing, crowd prediction, cross-domain data


Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).