Case Study
A Large Metro Transportation Service Provider Introduces A Predictive Solution to Improve Traffic Throughput
The digital transformation solution provides passengers real-time scheduling information through multiple information system channels
Overview
The client is a Crown agency of the Government of Ontario, with a transit system that improves the coordination and integration of all modes of transportation in the Greater Toronto and Hamilton areas.
Challenge
Before partnering with Ness, the client predicted the Estimated Time of Arrival (ETA) of their trains using static rules built using statistics and physics methodologies. To modernize this approach and leverage digital engineering solutions, the client wanted to use predictive analytics and data from diverse sources to increase the accuracy of the ETA in dynamic conditions and in real time.
Solution
Ness’s solution improved ETA accuracy significantly, with 92% of predictions now achieved within 3-minutes of actual arrival time. It helped the client optimize available resources for a given trip or the broader operational network. In addition, the client can now push out more precise information to customers to provide a more accurate ETA, with visibility beyond a single station. Overall, predictive analytics made it possible to optimize train operations and capacity planning for the client.
Result
The predictive analytics designed by Ness predicted the actual time spent at each stop during a trip, the impact of external factors (such as weather), and passenger flow. ETA predictions are updated every 5 to 10 seconds by leveraging historical and real-time data. With the added benefits of CCTV cameras, signal data, and track failure data, the client and their passengers benefit from a modern, streamlined transportation system and more accurate departure and arrival times.