dating app algorithms
It turns out that there’s one algorithm almost all dating apps use. It’s called collaborative filtering. It’s pervasive: It powers your Facebook and Twitter feeds, your Google searches, and your Netflix and Amazon recommendations. It’s not that complicated. You’ve seen this a million times: “You might also like…” How does Amazon know what you might also like, and why does it use the word “also?” Because you’re not the only person on Earth buying tortilla chips.
Amazon looks up what else tortilla chip buyers have bought: salsa. So it knows “you might also like” salsa without really understanding anything about the innate relationship between tortilla chips and salsa. The same exact thing is going on with dating, except the thing that’s for sale is people.
Collaborative filtering in dating means that the earliest and most numerous users of the app have outsize influence on the profiles later users see. Some early user says she likes (by swiping right on) some other active dating app user. Then that same early user says she doesn’t like (by swiping left on) a Jewish user’s profile, for whatever reason.
As soon as some new person also swipes right on that active dating app user, the algorithm assumes the new person “also” dislikes the Jewish user’s profile, by the definition of collaborative filtering. So the new person never sees the Jewish profile. A recent look at this phenomenon is going to change the way you think about online dating.
research and resources
learn more about collaborative filtering and data on dating, offline and online
"Our personal data has been used to spy on us, hire and fire us, and sell us stuff we don’t need. In Dataclysm, Christian Rudder uses it to show us who we truly are." Christian Rudder, 2014
"It’s not that he’s just not that into you—it’s that there aren’t enough of him. And the numbers prove it. Using a combination of demographics, statistics, game theory, and number-crunching, Date-onomicstells what every single, college-educated, heterosexual, looking-for-a-partner woman needs to know: The “man deficit” is real." Jon Birger, 2015
"Blending the informed analysis of The Signal and the Noise with the instructive iconoclasm of Think Like a Freak, a fascinating, illuminating, and witty look at what the vast amounts of information now instantly available to us reveals about ourselves and our world—provided we ask the right questions." Seth Stephens-Davidowitz, 2017
"In this paper, we study Collaborative Filtering for people-to-people recommendation in online dating, comparing this approach to a baseline profile matching method." A. Krzywicki et al. 2014
"Recommender systems have become a very important part of the retail, social networking, and entertainment industries. From providing advice on songs for you to try, suggesting books for you to read, or finding clothes to buy, recommender systems have greatly improved the ability of customers to make choices more easily." Jesse Steinweg-Woods, 2016
A well-documented code package that handles datasets, provides many prediction algorithms out of the box, demonstrates new algorithm building, supports a good test framework, and in used by dozens online. Nicolas Hug and contributors, 2019
A brand new simulation has quantified our gut feelings about dating apps: that a feedback loop in collaborative filtering gives majority users better matches at the expense of minority users. There’s something innate about collaborative filtering that disfavors people who are underrepresented in the data, both in terms of when they started using the dating app and how many of those users there are. In no intentional way, collaborative filtering reproduced the underlying causes of an inequality of opportunities in offline life.
This is all beside the point, because there is no perfect dating algorithm, only compromises. There is an imbalance between what people want and what people give in dating. All preferences cannot be satisfied for everyone. Mathematicians know this as the “marriage problem.” We’re not in the business of proposing better alternatives to collaborative filtering. And people who suggest we try are missing the point.