Were you unable to attend Transform 2022? Check out all of the summit sessions in our on-demand library now! Watch here.

It seems like everyone is getting into big data these days.

Cubic Transportation Systems, the company that operates the Clipper card fare-payment system, announced the formation of a new subsidiary called Urban Insights earlier this week. The subsidiary provides transit agencies with subscription-based access to big data tools as well as a big data consulting service.

“The transportation industry is awash with very useful data that’s not currently effectively harnessed,” Matthew Cole, acting general manager at Urban Insights, said in an interview with VentureBeat. “Because transit agencies typically have unique systems for specific things. What they are able to do because their tools that allow them to do it is not enough to bring the data sets together.”

Urban Insights has already been working with the San Diego Metropolitan Transportation system and a few other transit agencies to improve their transportation systems.

More and more industries have been incorporating big data projects into their workflows lately.

Food delivery startup SpoonRocket is working with big data to forecast demand and plan its expansion into more cities. A virtual makeover company is using big data to analyze your face. And a nonprofit is using big data to identify earmarks in congressional texts.

In transportation, you’d better believe lots of data sources come into consideration.

A fare system like the Clipper card has a reporting database. The vehicle location system, like NextBus, also has a database. And there are plenty other databases. What Urban Insights does is provide a tool based on Hadoop open-source software for storing and processing lots of different kinds of data. The tool “ basically solves the problem how you get these disparate pieces of data together,” on a terabyte scale, Cole said.

The insight derived from aggregating and mining all the different data sets can inform the transit agencies to make better decisions.

In San Diego, Urban Insights is helping the transit agency connect trips into journeys. Say you are traveling from one part of the city to the other. During the first part, you take the trolley, and during the second part, you ride the bus. You will use your smart card when you go on the trolley and again when you go on the bus.

The system will record your journey as two unlinked trips. Urban Insights tries to triangulate the data and connect your trips into a single journey.

If there are a sufficient number of people making this trolley-to-bus journey, the transit agency might plan a bus route for the whole duration of the journey.

“The only way we get to associate the trips is by knowing it’s done by the same individual,” Cole said. However, he said, Urban Insights anonymizes the data by “leaving out the personally identifiable information.”

One possible Urban Insights application Cole gave is to help the BART system identify overcrowded trains. The Clipper system knows the stations and times you enter and exit, but it doesn’t know which trains you board, because you could take any number of trains.

By combining the Clipper data with the data from the scheduling system and the vehicle-location system, “we are able to identify to a very high degree of probability which actual trains you board,” Cole said. When the BART compares the data with train load capacity, it can identify which trains are overcrowded and try to solve the problem.

Urban Insight hasn’t worked with the BART system or SFMTA yet. Let’s see what will happen when this big data consultancy comes to the Bay Area.

VentureBeat's mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Discover our Briefings.