When Google ETAs Fail…


Hello Uberites! We’re back again with another #UberData post. We recently launched in NYC, and for us that means ‘mo money, ‘mo problems. Take estimated arrival times (ETAs), for example. When we launch a new city, we simply don’t have historical data to draw estimates from. That’s a problem because not only are ETAs woven into virtually every corner of our supply chain and dispatch systems, but we also show them to riders to make decisions based on wait times.

We don’t have estimates at city launch, but Google does. Google has services that predict travel times and that’s what we used to start in NYC. Unfortunately, we found that Google’s ETA predictions were, on average, off by 3.6x the actual pickup time in NYC during our first week. (Thanks, New York crosstown traffic and congestion!) So we’re working on using our own algorithms instead of Google API for ETAs.  And as our data shows, we’re better at it:

Uber vs. Google

We measure our predictor’s accuracy using the mean square error; the lower the error, the better. And as the next graph shows, as we accumulate rides we’re also getting even better by the day:

Over time, the gap between our predictor’s accuracy and Google’s widens in our favor. Math!

To be completely fair, we’re not claiming we’re better than Google. Our domain is more restricted – with reliable and experienced drivers from which we can pull real-time data from. Besides, Google APIs never gave claims of accuracy (“it’s for planning purposes, etc.”) and they’re great for almost everything else, such as geocoding street addresses into latitude/longitudes and then back again. In other words, we love them for everything except for accurate ETAs.

ETAs are just one, albeit important, part of our pool of #UberData projects. As we improve on other areas, such as demand prediction or supply positioning, ETA accuracy can lag behind. In fact, some methods to improve actual wait times may negatively impact our predictor. So we’re in a give and take here, and we iterate on each of the core projects to make the system truly Uber in the long run.

Regardless, expect all things Uber to become better, if not more accurate, as our ridership rises.

#UberData is series of posts by the Uber Engineering Team. We’re highlighting cool and amazing things that data and math can show us to make a better Uber product. (And occasionally make us chuckle.)

Featured articles

5 Times You’ll Need To Order UberEATS This Semester

Whether you’re a freshman or a senior headed back to campus this fall, one thing is certain—you’ll need to eat. And there is nothing worse than being limited to questionable cafeteria food or taking a chance on expired leftovers in the back of the fridge. The best news? UberEATS is expanding to 30+ major college campuses by the end of the year, from Penn State to LSU to Boise State. Since we want you to focus on what you love about college and not worry about your next meal, we’re predicting the 5 times you’ll need to order UberEATS this semester.

Get a Taste of the World: UberEATS is in 100+ Cities

We are excited to surpass the 100th city mark by welcoming two Brazilian cities, Rio de Janeiro and Belo Horizonte, to the UberEATS family. From Atlanta to Warsaw, people have truly embraced this easy and reliable way to discover the food they love at the push of a button. Whether that’s an Indian inspired samosa, a good old-fashioned American burger or Vietnamese pho, people in 27 countries are using UberEATS to get a taste of the world’s flavors at the push of a button.

Uber for Business now makes it easy to give your customers a ride

We’re excited to expand the Uber for Business platform beyond business travel, to include a world-class customer transportation solution, Uber Central. With Uber Central, organizations of all shapes and sizes can now easily provide on-demand, door-to-door transportation for their customers, clients, and guests.