Current State of Practice in Transit Ridership Prediction: Results from a Survey of Canadian Transit Agencies
place - north america, planning - surveys, planning - methods, technology - passenger information, ridership - forecasting, ridership - modelling
ridership prediction, automated data collection
With the emergence of new technologies, new data sources, and software, it is important to understand the current approaches used by transit agencies in ridership prediction. This study reports the results of a recent web-based survey conducted in 2018 among 36 Canadian transit agencies to understand their current state of ridership prediction practice. The study presents a wide range of results, starting from agencies’ used prediction methods to the challenges faced by transit agencies as a result of the observed changes in ridership estimates after the introduction of new automated data collection systems. The study also discusses the transit agencies’ level of satisfaction with the currently used methods and data inputs and factors that are incorporated in their methods. In addition, it develops a better understanding of the requirements of robust ridership prediction models from the transit agencies’ perspective. This paper provides planners and researchers with a comprehensive examination of the different aspects and issues that are related to the current state of transit agencies’ ridership prediction practices.
Permission to publish the abstract has been given by SAGE, copyright remains with them.
Diab, E., Kasraian, D., Miller, E.J., & Shalaby, A. (2019). Current State of Practice in Transit Ridership Prediction: Results from a Survey of Canadian Transit Agencies. Transportation Research Record: Journal of the Transportation Research Board, Vol. 2673, pp. 179-191.