Men who drive for Uber earn roughly 7 percent more per hour than women, according to a new study that examined over a million Uber drivers. Women were found to earn $1.24 per hour less than men, and also $130 less per week on average, in part because they tend to drive fewer hours.

The study, which was released today, was a collaboration between the University of Chicago, Stanford University, and Uber’s own economic team. Researchers examined earnings data from over 1.8 million drivers, of which roughly 27 percent were women.

The results are surprising, given that Uber has long argued that its algorithms that determine how much drivers earn are supposed to be blind to things like race, gender, and sexuality. The technology, however, did not take into account differences in driver behavior, which can vary between men and women.

“Overall, our results suggest that, even in the gender-blind, transactional, flexible environment of the gig economy, gender-based preferences (especially the value of time not spent at paid work and, for drivers, preferences for driving speed) can open gender earnings gaps,” the study concludes. 

In a blog post, Uber says the study produced “no evidence that outright discrimination, either by the app or by riders, is driving the gender earnings gap.”

Researchers attributed the earnings gap to a number of factors, including that male drivers were more likely to drive in higher paying locations, were more likely to drive faster, were more likely to accept trips with shorter distances to the rider, and were more likely to chose to drive longer trips.

All of these are variables in the formula Uber uses to calculate driver wages, and the study showed they all tilted in men’s favor (the study claims men earn $21.28 an hour, on average). Women also have higher turnover on the platform, and more experienced drivers tend to get higher pay.

As a company, Uber has been scrutinized for a toxic workplace culture that allowed male engineers to get away with sexually harassing their female colleagues. But the disparity in pay among male and female drivers isn’t related to Uber’s corporate reputation, as much as its a result of driver behavior.

“So, I think when you look at our data, I think it’s actually a mixture of preferences,” John List, professor of economics at the University of Chicago, chief economist at Uber, and a lead author on the study, told Freakonomics. “Driving fast. But I also think it’s a mixture of constraints, and what I mean by that is men work more hours and take more trips than the average woman. So, why is that? Part of it is because women have more constraints — i.e, take the kid to school in the morning. Be responsible for taking Johnny to the soccer game. And I think those constraints then lead women to actually receive less experience and less learning-by-doing. So I think it’s actually a mixture of preferences and constraints. Now as policy makers, what we want to do is make sure that we can alleviate those constraints as much as possible.”

Stanford’s Rebecca Diamond said, “I think this is showing that the gender pay gap is not likely to go away completely anytime soon. Unless somehow, things in our broader society really change, about how men and women are making choices about their broader lives, than just the labor market.”

In the interview, Uber’s executives dismissed the notion of increasing the baseline pay of women drivers by 7 percent as “discriminatory.”