Slashdot Mirror


Uber Plans To Kill Surge Pricing With Machine Learning (npr.org)

An anonymous reader writes: Surge pricing is a familiar term for any regular Uber rider -- or driver. It's when you call an Uber, and the price of a ride is two, three, or four times more as a result of greater demand brought on by a sporting event or weather event nearby. For riders, it's an annoyance, but for drivers, it's a perk as it usually results in more pocket change. Inside Uber, surge pricing is considered a market failure, and a problem to be solved. "That's where machine learning comes in. That's where the next generation comes in," says Jeff Schneider, engineering lead at Uber Advanced Technologies Center. "Because now we can look at all this data, and we can start to make predictions." Everyone knows that when a Beyonce concert ends, for example, there's going to be a lot of demand for Uber drivers. Schneider explains, "[What's harder] is to find those Tuesday nights when it's not even raining and for some reason there's demand -- and to know that's coming. That's machine learning." With enough of the right data inputs, computer algorithms can do the research that Uber drivers already do -- only better, "so the surge pricing never even has to happen," Schneider says.

14 of 95 comments (clear)

  1. Why is it a failure by NotInHere · · Score: 2

    In the perfect market, the price is determined by supply and demand. If the demand raises and the supply stays the same, the price raises. So if you believe the price is too high, just raise the supply as well. Banning price surges just adds imperfections into the market.

    1. Re:Why is it a failure by unrtst · · Score: 2

      More importantly, if Uber is able to predict the surges better, how the hell will that get rid of surge pricing!?!?!

      Everyone knows that when a Beyonce concert ends, for example, there's going to be a lot of demand for Uber drivers. Schneider explains, "[What's harder] is to find those Tuesday nights when it's not even raining and for some reason there's demand -- and to know that's coming.

      That sound a hell of a lot like a great reason to spike prices, not a good reason to get rid of the spikes.

      If they wanted to get rid of surge pricing, they could do that today. Just get rid of it. If it's necessary now, then the imperfection is that they're not surging enough - like the example he provided, when it's not even raining and for some reason there's deman.

    2. Re:Why is it a failure by ottothecow · · Score: 4, Insightful
      I think it is considered a failure because it doesn't really work for uber.

      If surge is low, it isn't worth a driver heading across town without a fare just for a 20 or 40% bonus in fares (especially if surge is gone by the time he gets there). Low surge doesn't do much to increase supply.

      However, if surge is high, customers won't want to pay. At least in my market, taxis are still a perfectly viable option (and can be flagged off any street corner), and last I checked, a surge of 1.7x or more made UberX more expensive than a taxi. I would also be willing to take a bus or ride a bike in some instances (or simply wait for surge to go away). I think I have only paid surge over 2X once, and it was for a short ride where the money just didn't matter much.

      High surge is great at reducing demand. This helps clear the market and is overall a market success. Unfortunately, Uber is in the business of selling you a ride. Reducing demand for their own product is not exactly a success.

      The only times that it is really a success for uber are times where many drivers expect surge in advance. New Years Eve is a great example of this. In my city, there weren't crazy surges on NYE like there were a few years ago. Drivers knew there was money to be made and they went out. They may have been disappointed that they weren't seeing huge surges (averages were less than 2...probably a lot in the 1.2-1.4 range), but they were out there driving, and customers were surprised by the low fares and took more ubers.

      I think the idea is that they could use machine learning to predict the non-obvious times. Get drivers on the road in time to meet the demand...thus increasing supply rather than decreasing demand.

      --
      Bottles.
    3. Re:Why is it a failure by vux984 · · Score: 2

      The issue is that it is not a perfect market. Increasing the supply means giving more money to drivers; that's how you incentivize more drivers to hop into a car. So they need to keep the price the same while paying drivers more money during a surge to get them onto the road.

      And the solution to ubers "problem" is pretty simple.

      Price the service to account for it. Do the analysis on surge frequency and duration and they raise the cost of a regular fare by a nickle or so, and then when a surge hits, they have that 'warchest of extra nickels' built up to absorb the cost of paying drivers extra to get them on the road during a surge.

      Seriously this isn't hard. Uber just sucks.

    4. Re:Why is it a failure by ottothecow · · Score: 3, Insightful
      You're forgetting the other half of the supply & demand equation:

      When prices go up, it pushes consumers to consume less. You still get a market-clearing result--everyone who needs a ride is able to get one quickly, because those people who can wait or go by some other means (or can't afford the new price) will remove themselves from the market.

      Turns out that the effect on demand is much stronger than the effect on supply. Customers drop their requests faster than drivers can get to the area. Uber probably sees it as a failure internally because they make less money when prices go up (even though it is still a success at ensuring availability and short wait times).

      --
      Bottles.
  2. Re:Perk? by khallow · · Score: 4, Insightful

    when the whole point of Uber is to be flexible for drivers.

    It's not. And no matter how flexible you might want to be for drivers, passengers are not out there at the convenience of the driver.

  3. Oh yeah... that'll be great... by the_skywise · · Score: 4, Funny

    Honey... There's an Uber driver out here who says you're delivering a baby?
    That can't be true, my water hasn't even broooooOMG!!!!

  4. Obligatory "that's not how this works!" by H3lldr0p · · Score: 3

    Schneider explains, "[What's harder] is to find those Tuesday nights when it's not even raining and for some reason there's demand -- and to know that's coming. That's machine learning

    That's not how it works. That's not how any of that works!

    Deus! Stop your bullshit marketing and get back into whatever festering hole you crawled out of you twit!

  5. Re:Perk? by ShanghaiBill · · Score: 4, Insightful

    Also, surge pricing is a perk for the passenger, because it means a ride is actually available.

    Surge pricing is just supply and demand. If you don't like it, you are free to go wait at the taxi stand for an hour in the rain.

  6. There's something missing... by quantaman · · Score: 2

    Schneider: And so the idea is if you can predict that demand, you get that information out there – and you get that supply there ready for the demand so the surge pricing never even has to happen. And I think that's one of the really cool things that machine learning's doing for Uber right now.

    Supposedly surge pricing is supposed to get more drivers go out on the road because they earn a premium.

    Just predicting that you'll need more drivers doesn't actually put those drivers on the road, you'll still need some kind of extra incentive.

    You might get away with a smaller surge, but predictions alone doesn't solve the problem that surge pricing was made to solve.

    --
    I stole this Sig
  7. Re:Perk? by xevioso · · Score: 5, Interesting

    Thing is, here in San Francisco, Taxis are doing rather well, despite all the publicity to the contrary.

    It's actually quite easy to catch cabs in many parts of the city now and they are often better, because cabs have gotten their act together and are now much more responsive to folks looking for them, and they accept cash. Also, many of the companies now have an app (Flywheel) that can be used just like Uber and Lyft's app. To be honest, I actually prefer Taxis.

  8. Re:Why should uber exist at all? by Shompol · · Score: 2

    Uber circumvents laws to protect passenger safety.

    ... that create artificial scarcity and barrier to entry to protect the industry owners. Does squat for safety.

    They pay lousy wages while slacking on insurance.

    Seems to work for drivers so far.

    They don't do appropriate background checks as evidenced by the Kalamazoo shootings.

    And regular taxi/car service drivers have never been involved in shootings? At least with Uber the ride is tracked. If a flagged down taxi driver wants to do me in, no one will ever know.

    Why should Uber exist at all? They have no interest in protecting either consumers or employees.

    Same reason why all for-profit businesses exist: for profit. They have no other interest.

    Can anyone justify Uber's existence? I expect the answer is no.

    Their customers, drivers and employess depend on Uber's existence, and that is a lot of people.

  9. Re:Why should uber exist at all? by khallow · · Score: 3, Insightful

    Can anyone justify Uber's existence?

    Can you justify your own existence? What I find remarkable about babble like yours is how little understanding there is of consequences. No one has the understanding of society or reality to decide who "should" exist. It'll just create destruction obstructions to human progress by people too stupid and short sighted to create the sort of things, like Uber, which they are judging.

    My view is that Uber's existence is sufficient justification for their existence.

  10. Re:Perk? by ConfusedVorlon · · Score: 2

    it looks like the yellow cab bankruptcy may have been triggered by an $8m compensation claim.
    They're still trading - just using bankruptcy to restructure (abandon?) their debts.