Modeling the Duration of the Impact of Unplanned Disruptions on Passenger Trips Using Smartcard Data in Urban Rail Systems

Abstract Many urban rail systems operate near capacity given the rapid increase in passenger demand, and unplanned disruptions are unavoidable. From a perspective, duration of trip delays is major concern, may be longer than train delays. Several studies have focused on predicting delays, but research disruption impacts trips limited that not observed directly. This paper proposes probabilistic method to estimate impact using smartcard data, explores statistical machine learning models predict passengers, identifies influencing factors including incident characteristics, operating conditions, infrastructure, external factors, demand. The results highlight prediction accuracies acceptable for multiple linear regression, accelerated failure time, random forest models. Disruptions caused by power failures durations other causes, followed platform screen doors. fixed block signaling system leads larger moving system. study provides, first data-driven approach understanding data which can facilitate timely informed decision-making under disruptions.