You’ve reached the end of the line.
You want it. We have it. Starting today, our real-time predictions in Los Angeles get a little better thanks to our partnership with Swiftly.
October 30, 2017
The sun in Los Angeles is so hot, it cooks the sweat right off your forehead. The asphalt is searing with heat. You cower in the shade of the bus shelter, crossing your fingers that you won’t have to wait much longer. You pull your phone out of your pocket —when is the bus gonna get here, exactly? The last time you checked, on your walk over, the app said three minutes. You check it again… the app says the bus has already come?!?
You shake your fists at the (admittedly, beautiful) sky.
You’ve been duped. Again.
Because while LA Metro does have real-time information for its buses and subways, the data isn’t always great. It’s outdated. It can take up to three minutes for a vehicle to update its real-time position, which means — if you’re like most people (who don’t show up ten minutes early) — you’ll eventually get burned by your transit app’s “real-time” predictions.
We wanted to stop the burning.
LA Metro data (left) vs. Transit crowdsourced data (right). LA Metro takes up to 3 minutes to update its own vehicle locations. With our crowdsourced data, it takes a few seconds.
This month, after successful pilots in New York, San Francisco, and Montreal, our app Transit started publishing crowdsourced transit data in Los Angeles. Instead of updating every 3ish minutes, we update vehicle locations in actual real-time. How is that possible? We have thousands of Los Angelenos proudly sharing their vehicle locations with other users, all thanks to GO, a keystone feature of Transit.
GO gives you real-time transit instructions (like when to leave for your stop, when to disembark, and where to transfer) but it also broadcasts your real-time vehicle position while you ride. We use those GPS coordinates to make real-time ETA predictions for everyone down the line — so fewer people miss that bus (or subway)!
Today, our predictions are getting even better, with a little help from our friends at Swiftly.
Swiftly is a transit data company that improves the accuracy of real-time information. Their “big data engine” can combine legacy datasets (like old CAD/AVL real-time systems) with modern ones (like crowdsourced GPS). Swiftly’s software makes it possible to overlay our high-frequency transit data on top of the low-frequency agency feed (if the line isn’t crowdsourced).
It’s exactly what we needed.
Today, we’re announcing our first joint project: LA Metro. Here’s what you should expect:
With Transit’s crowdsourced data + Swiftly’s data sorting skills, we can make faster (and smoother) updates on vehicle positions. Which means more reliable data and a better rider experience.
Whenever you ride LA Metro, take advantage of GO. Not only will you get real-time notifications on when to leave for your bus (more time for breakfast), when to disembark (more time for naps) and where to transfer, but you’ll be helping thousands of fellow riders get better data about your line.
With just one person running GO on each vehicle, we can produce accurate real-time predictions for the entire transit network.
We’re already generating significant amounts of crowdsourced data in Los Angeles. With your help, we can crowdsource the whole dang city.
Los Angeles is just the latest city to get better real-time data. But it won’t be the last. Thanks to Transit + Swiftly, it’s now easier than ever to generate accurate real-time predictions — our pilot project for LA Metro is just the start.
By working together, startups and agencies can massively improve the rider experience. Fewer missed rides. More trustworthy service. Cities where people are proud of their public transit.
Which is why we’re excited to pursue deeper relationships with LA Metro. Together with Transit + Swiftly, we could put this data in the hands of millions more riders. Let’s make it happen.
See your ride approaching in real-time thanks to our new crowdsourced data feature
Transit riders want to know how crowded their vehicles are. One problem: that data didn’t exist in most cities. Now it has arrived.
How we’re using machine learning at Transit to improve real-time predictions for Montreal’s STM buses 🙂🚍👉🤩🚍