Analytics remedy bus bunching, curb operational costs

Analytics remedy bus bunching, curb operational costs

For city transportation officials, getting citizens who rely on public transportation from point A to point B dependably is critical. Bus bunching – when two or more buses traveling the same route arrive at the same stop at or very close to the same time – hinders efficiency, which leads to increased operational costs. 

Bus bunching, among other transportation concerns, has been a key focus for the city of Miami, which serves the seventh largest urban population in the nation. The city worked with IBM on an eight-week pilot program aimed at reducing delays and improving services.

Using IBM’s Intelligent Transit Analytics the city analyzed more than 1.4 million bus positions, representing 19,974 bus runs, characterizing the busses’ variability and pinpointing bottlenecks within the system.

The pilot focused on four key routes near South Beach. IBM’s predictive analytic system provided alerts when bunching was likely to occur nearly 60 minutes in advance, giving city  transportation planners ways to better schedule and assess performance.  In contrast to other analytical models that store information in memory prior to processing, the Intelligent Transit Analytics checks streaming data as it comes in. 

After analyzing the busses’ paths, speed and stops, IBM gave the city indicators of bus bunching and assessed the accuracy of bus arrival predictions and bunching event alerts.

IBM has additional tools for urban mapping. The Public Transport Awareness tool features scalable real time analytics, automated generation of infrastructure data points to track vehicle trajectory, inferred road speed, bus bunching analysis and time-of-arrivaltechnology to predict the arrivals of various moving parts within transportation infrastructure.   

About the Author

Mark Pomerleau is a former editorial fellow with GCN and Defense Systems.

inside gcn

  • artificial intelligence (ktsdesign/Shutterstock.com)

    Machine learning with limited data

Reader Comments

Please post your comments here. Comments are moderated, so they may not appear immediately after submitting. We will not post comments that we consider abusive or off-topic.

Please type the letters/numbers you see above

More from 1105 Public Sector Media Group