Development of a Data-Driven Platform for Transit Performance Measures Using Smart Card and GPS Data

Abstract

To improve customer satisfaction and reduce operation costs, transit authorities have been striving to monitor transit service quality and identify the key factors to enhance it. The recent advent of passive data collection technologies, e.g., automated fare collection (AFC) and automated vehicle location (AVL), has shifted a data-poor environment to a data-rich environment and offered opportunities for transit agencies to conduct comprehensive transit system performance measures. However, most AFC and AVL systems are not designed for transit performance measures, implying that additional data processing and visualization procedures are needed to improve both data usability and accessibility. This study attempts to develop a data-driven platform for online transit performance monitoring. The primary data sources come from the AFC and AVL systems in Beijing, where a passenger’s boarding stop (origin) and alighting stop (destination) on a flat-rate bus are not recorded. The individual transit rider’s origin and destination can be estimated by utilizing a series of data-mining techniques, which are then incorporated into a regional-map platform for transit performance measures. A multilevel framework is proposed to calculate the network-level speed, route-level travel time reliability, stop-level ridership, and headway variance. These statistics are interactively displayed on a map through a simplified transit GIS data model. This platform not only serves as a data-rich visualization platform to monitor transit network performance for planning and operations, it also intends to take advantage of e-science initiative for data-driven transportation research and applications.