Predicting Destination Station in Real Time Based on Public Transit Passenger Profiling
The smart card is an universal tool in public transit. It collects large amounts of data on buses, urban railway transit, and ferries, and provides opportunities for passenger profiling. Such advanced data collection, processing, and learning tools provide a foundation for efficiently analyzing and predicting real-time travel behavior and demand. To this end, the contribution this study makes is combining offline analysis of passenger profiling with real-time prediction to propose a method that accurately predicts the destination station in real time when passengers swipe their smart travel cards (“tag on”), First, a static database of transit passenger profiling was constructed, having identified dual passenger travel patterns based on Density-Based Spatial Clustering of Applications with Noise. The transit passenger profiling included origin–destination-time- and destination-time travel characteristics. A rapid real-time prediction algorithm based on transit passenger profiling and Roulette Wheel Selection (RWS) was proposed, to predict the destination of boarding passengers. Rules were set to distinguish between regular and irregular passengers: passenger profiling was applied to regular passengers, and RWS to irregular passengers. This study provides a technical foundation for real-time passenger-flow prediction, monitoring, and simulation, and prediction of short-term passenger behavior and demand. Furthermore, it facilitates efficient, real-time acquisition of passengers’ travel destinations and demand. To validate its practical performance, an actual case simulation was conducted, yielding an accuracy rate of 80.27% during peak hours and maintaining 70.07% overall. These results demonstrate both the technical feasibility and operational efficiency of the proposed solution.
Authors
- Fangsheng Wang (ORCID: https://orcid.org/0000-0002-5309-9361)
- Xuyang Song (ORCID: https://orcid.org/0000-0001-5860-1974)
- Ruihua Xu (ORCID: https://orcid.org/0000-0002-5197-0715)
- Minh Kieu (ORCID: https://orcid.org/0000-0001-7798-6195)
- Jun Yin
- Wenjun Li
Institutions
- Tongji University (CN)
- Shanghai University of Engineering Science (CN)
- University of Auckland (NZ)
Publication Details
- Journal
- Transportation Research Record Journal of the Transportation Research Board
- Published
- 2026-11-20
- DOI
- https://doi.org/10.1177/03611981261491299
- Primary Topic
- Transportation Planning and Optimization
- Type
- article
- Field-Weighted Citation Impact
- 0.00