Uber created the “surge pricing” system by using an algorithm which ensures that supply and demand criteria is met with a constant balance. In reality ‘surge pricing’ allows Uber to identify zones (of a city) that are in demand and allocate drivers accordingly.
The algorithm tries to keep supply and demand in constant balance by encouraging drivers to pick customers from busy areas, and eventually moderating customer requests by increasing the price of each ride. This is called “surge pricing”.
Uber users, regulators and even drivers criticized surge pricing as it varies quickly without any predictability, points out NPR. But,Uber maintains that without such a model, the whole promise of a ride in minutes falls apart when there’s a crush of demand.
Explained: How The Algorithm Works
Uber never revealed how the algorithm actually works, so a team of researchers from Northeastern University decided to find out by performing something called ‘algorythmic auditing’.
“They have this algorithm and they say it changes prices based on supply and demand, but it’s a black box. You have to trust that it’s working correctly, because you can’t verify. You don’t know how many customers there are, you don’t know how many other drivers there are,” says Christo Wilson, one of those researchers.
Wilson and his fellow researchers, Le Chen and Alan Mislove created 43 Uber accounts with a custom script that could automatically login and ping Uber’s servers every 5 seconds. They set-out to record information about Uber drivers in Manhattan and San Francisco.
The team tested their tracking methodology on New York’s public database of taxis to make sure that they could successfully mine information about the vast majority of cars in the fleet. They then studied Uber’s fleet movements, and ultimately combined that research with Uber’s publicly available tools and information to analyze how they correlated with surge prices.
In their paper, presented at the Internet Measurement Conference in Tokyo, the researchers pointed out that:
- Surge prices do temper demand.
- Sometimes they do entice more drivers to go to busy areas and sometimes they don’t.
- They vary not only by city but also by sections of the city with what appear to be manually created boundaries of each surge area.
- They most commonly last less than 10 minutes and often less than 5 minutes (and prices are updated every 5 minutes).
What Consumers Can Learn From The Study
“Surge pricing is working in a sense that it is responding to supply and demand, but I would argue that it’s not working as intended,” says Christo Wilson, Assistant Professor, College of Computer and Information Science.
“What we see is that demand drops precipitously, cars stop getting booked and drivers are just sitting there. And actually there’s a lot of drivers who drive away from surges …. If the incentive was working the way it should, you would expect there always to be an incentive for [drivers] to always move in. But in this case, the result is mixed,” adds Wilson.
NPR points out to Uber users: “When prices are surging, waiting a few minutes or walking a few blocks to a different area may result in a cheaper ride.”
Wilson says that the short lifespan of a surge price may create mixed response from drivers, and might not give them enough time to respond to the price surges that effectively reflect the demand from five minutes earlier.
Uber, after receiving criticism from it drivers themselves, earlier this month revealed a redesigned app for its drivers. It helps drivers to predict the location of the next wave of customers on an even more granular level than the surge area maps that Wilson’s team had figured out.
What Uber Had To Say About The Study
Uber agrees to the existence of pre-defined surge areas and the constant rise-and-fall of surges, and claims that both allow the app to quickly calibrate supply and demand.
“People love Uber because they can push a button and get a ride quickly and reliably—wherever they are in a city. And dynamic or surge pricing helps make that possible. It encourages drivers to go to the neighborhoods with the highest demand, ensuring there’s always a ride available within minutes. Contrary to the findings in this report—which is based on extremely limited, public data—we’ve seen this work in practice day in day out, in cities all around the world,” says Uber spokesperson Molly Spaeth in a statement to NPR.