Transit service performance analysis and bunching detection using automatic passenger counters (APC) and automatic vehicle location (AVL) data
The essential idea is to fully utilize the big data in public transit to provide travelers fine-grained customizable information regarding transit service performance (efficiency, reliability and quality). By monitoring day-to-day transit service and how users respond to information provision, we can develop a better understanding of travelers’ preferences on efficiency, reliability and quality of transit service, as well as their modal choices. Big data and data-driven behavioral models facilitate agencies’ decision making (such as scheduling). Effective information provision, along with data-driven scheduling, holds great potential to improve the service performance and travelers’ riding experience.