Detecting shifts in urban rail passenger behavior during emergencies: A data-driven comparative approach

Abstract

During urban rail transit (URT) emergencies, passengers often modify their travel behavior in response to perceived risks and disruptions. Detecting and understanding these behavioral shifts is essential for evaluating the impacts of such events and designing effective contingency strategies. This paper proposes a data-driven approach to detect individual behavior changes by comparing observed behavior during emergencies with predicted normal behavior. To establish reliable references, we design a continuous rolling prediction pipeline that dynamically forecasts routine travel patterns, serving as counterfactual baselines for comparison. We validate our approach through a case study using data from Beijing’s URT system. Results demonstrate that the predictive module improves the accuracy of normal individual travel behavior predictions, and our data-driven approach effectively detects behavioral changes during emergencies. These findings offer valuable insights for understanding individual behavior variability, improving emergency planning, and forecasting passenger flow under crisis conditions.