The public transport provider of San Diego, the Metropolitan Transit System (MTS), is now using big data
analysis in order to effectively use the massive influx of information it garners. The data comes from diverse sources including GPS-based automatic location devices on buses, automatic passenger counters on trolleys, a
smart-card electronic payment system and a general transit feed specification developed by Google in
2006 to supply route and schedule information.

In an interview with InformationWeek, MTS chief of staff Sharon Cooney explained the aim of this
new data optimization project. “We look at all these data sources independently, and they help us
improve performance, but we haven’t been able to make correlations among the various data sources,”
she says.

The big-data service provider Urban Insights, who is already responsible for the agency’s smart-card
and revenue management software, has developed a cloud-based analytics platform built on Hadoop to
help optimize the use of the disparately-sourced data.

Urban Insights’ director of analytics Wade Rosado explains which tasks the company was confronted
with in this endeavor: “MTS wanted not just a one-off study of transit usage but a reusable process of
integrating data sources and producing insights so planners can determine when travelers are not using
the network as anticipated.” The company aims to “to align and make sense of the data to unravel
the mystery of how people are using the system.”

The fact that one part of San Diego’s public transportation system, the trolleys, relies on an honor system
that is depending on passengers swiping their smart-cards on fare validators makes this data supply quite complicated to analyze. Buses offer both vehicle locators and fare control through the driver, but the
two systems are not connected, which makes it hard to track passengers’ journeys and transfers. In
order to get detailed information on the ratio of ridership to fare validation on the trolley system,
MTS and Urban Insights combined the data gathered from fare validators and the GTFS scheduling
data with time stamped automatic passenger counters.

“Now we can see how many boarded versus how many tapped,” Cooney explains. “The only other way we could
do that previously was through handheld units that officers use to spot-check who tapped and
who didn’t, but that’s only a small sampling of overall system usage.” But the MTS is not
necessarily planning to use these insights in order to crack down on fare dodgers.

One main outcome so far is the redesign of the cities trolley routes according to the observed ridership
patterns. Through this, Urban Insights and MTS are trying to improve the experience of its customers,
analyzing the impact of route changes on data such as the number of passengers, travel duration and
customer surveys. Rosado explains the technological challenges: “It takes a lot of computing power,
memory, and storage, and we’re doing it over a three-month period looking at half a million
transactions per day”.

The collected data is turned into blended datasets and visualizations, which help the MTS to determine
whether its services are consistent with passenger needs. “Understanding the behaviors and needs of
customers is our first job,” Conney states the agency’s objective for this project. “We try to use as many
tools as we can to provide a sustainable system, and we’re hopeful this is one more tool we’ll be able to
use.”

Read more here.
(Image credit: Flickr)



Interested in more content like this? Sign up to our newsletter, and you wont miss a thing!

Previous post

US Senator Writes Letter of Complaint to FTC Regarding Facebook Mood Experiment

Next post

The New Microsoft Vision: Cloud & Mobile