Tinder: You’re doing it wrong

Tinder has a new algorithm, thinks you’re doing it wrong

Tinder says it’s new algorithm will increase your matches by 30% or more. Sound good? There’s a catch, though. If you’re a serial “don’t ask questions, just swipe right” kind of user, this update isn’t for you. In fact, your “Tinder Profile Ranking” could already be in the toilet. Your Tinder Profile Ranking takes into account a lot of data, including how often you swipe right, how often you match with another user, how often you spark a conversation with matches, how often you “un-match” with matches, the number of swipe sessions you have per day, the consistency of your profile preferences, the number of “deep conversations” you have with matches (probably measured by the character count of your messages), and so on. Without consistent swipe behavior, your ranking slips. Without consistent app activity, your ranking slips. Without deep conversations, your ranking slips. Tinder uses your ranking to determine how often you should show up in another user’s profile results. It also dictates the type of profiles you’re shown. The algorithm that Tinder employs to feed this ranking is an important one because Tinder’s value is predicated on the swipe being “worth” something. If people aren’t matching often enough, intuitively enough, or successfully enough, users will go elsewhere. And with multi-homing a foregone conclusion in this business, users that have jumped ship may not miss much.

All of those aforementioned metrics and observations tell a clear story about a user. Tinder can use the same type of regression analyses that we have in class to identify which user behaviors impact their success in the app most. They can also predict which types of users will be welcome additions to the Tinder community. Data is driving Tinder’s business, especially important now that it’s parent company has filed for IPO.

Previous:

Gmail: ensuring a spam-free inbox with Machine Learning

Next:

Hudson’s Bay: Big Data for the Perfect Fit

Student comments on Tinder: You’re doing it wrong

  1. This seems like a big departure from how I figured they saw themselves. The whole “Tinder is a game” thing relied on the use-case of people swiping interminably. I guess, though, that if users have to focus on each potential match before swiping, they’ll pay more attention to those stupid ad cards (well, not that stupid: i have a date with an ad for Fallout 4 next week).

  2. I’m honestly not surprised to see this – several of their competitors have been doing this already (The League, for example) and giving users a secret “flakiness” score that impacts your future matches. Also, I’m not sure if they are doing it anyway, but there is a massive opportunity for mining the text data on the Tinder platform. There is a ton of information on user habits (including what activities they like to do, where they like to go for drinks, etc.) that Tinder should capitalize on before they start to lose their users to other platforms. However, the silver lining about multi-homing is that it’s actually an asset to each platform. Tinder, Hinge, Bumble, etc. only have value when users are single (or cheaters) – the paradox of choice implies that the more perceived options someone has, the less likely they are to commit – thus, it’s better for Tinder if their users are simultaneously on every other platform because it increases their likelihood of staying single and continuing to be a Tinder user.

Leave a comment