Thread

Singapore govt dating app uses Gale-Shapley stable marriage algorithm

466 points · 499 comments · rzk

abeppu · 1790807528 · focus · HN ↗
So on the one hand it's nice to see when a cool algorithm or framework is used IRL.
On the other hand, actually applying a 'stable marriage algorithm' to people makes a bunch of assumptions which are worth interrogating:
- Do people actually know what they want even in the short term?
- Do people's preference change meaningfully over longer periods of time?
- Does your preference _upon reading people's profiles_ have any strong relationship to your preference after spending any amount of time with them?
The property that right after being matched, no one could have matched with someone whose profile they preferred more does not mean that this will create stable relationships.
1. justonceokay · 1790810616 · focus · HN ↗
  Least they are using an algorithm that has the intended purpose of matching people. For profit dating apps are more interested in keeping you coming back then they are in creating successful relationships
  1. missedthecue · 1790812597 · focus · HN ↗
    This is an extremely common sentiment I see online - that there is some conspiracy to keep people single to reduce subscription churn. I have run two dating apps (my own apps, not working for a company), and what I found through trial and error was that no matter how many levers you pull and tweaks you make, a lot of it is simply user-behavior problems, not a tech or product design problem. There is no reliable way for a dating app to only serve users non-committal matches for example. The reason someone's matches aren't committal is because they don't want to commit.
    The thought experiment I usually pose is to ask what you think a free, open source, and community supported dating app would change. The answer is "not much".
    autumnstwilight · 1790820881 · focus · HN ↗
    Yeah, this seems to be a truism along the lines of "scammers intentionally use poor English to filter for stupid people". It gets repeated a lot because it resonates with people, but there's no evidence it's actually done deliberately. Sure, they're making UI and other decisions to maximize for time on the app, but in order to avoid serving you the best matches for a long-term relationship, they'd have to know what those are, and still serve you only plausible, appealing matches that are somehow bad (if they were too bad, you'd quit using the app). I don't think they have this much insight.
    *I came very close to falling for a scam that was written in perfect English, formatted convincingly, and appeared to come from an organization I was expecting to receive a message from at the time. Believing that scams will always be obviously stupid increases your chances of falling for one that isn't.
    derangedHorse · 1790823422 · focus · HN ↗
    > but in order to avoid serving you the best matches for a long-term relationship, they'd have to know what those are
    No? With modern dating apps they can just serve you people who have already swiped left on you. Even if they made it a random presentation of candidates, they will never be incentivized to matchmake for free. If you're not paying then you'll get shown people in the area and that's it. That's all they need for their ad-revenue.
    missedthecue · 1790827064 · focus · HN ↗
    I think we're talking about different populations. You are talking about someone who gets zero matches at all but we are talking about people that get matches, but those matches never turn into relationships. To be fair, both populations of people have the same complaint that "dating apps don't work", but for extremely different reasons.
    I don't think that dating apps are showing users profiles that have already swiped left, and if they do, it's not an attempt to get users to convert to a paid subscription. Consumer psychology doesn't work that way. People are far more willing to pay to upgrade a good experience than they are to pay to try to improve a bad one. Further, an unappealing profile that gets zero likes will continue to get zero likes after they upgrade to a paid subscription. This means that user will churn almost immediately after 1-2 months of paying for something that doesn't work. They typically don't stick around paying for years while getting zero matches all the while.
    Dating apps DO derank unappealing profiles, but rather than doing it to try to get them to convert, it's instead done to try to prevent high bounce rates. Imagine a user downloads a dating app and is shown profiles in completely randomized order. This user is far more likely to get frustrated and uninstall after a few minutes than if they were to download the app and be shown profiles that are appealing. This rigged ranking may sound like its reducing relationship formation, but they never would have swiped on the unappealing profiles anyway; the counterfactual is they simply uninstall the app in frustration.
    derangedHorse · 1790858044 · focus · HN ↗
    > You are talking about someone who gets zero matches at all
    No, I'm not.
    > People are far more willing to pay to upgrade a good experience than they are to pay to try to improve a bad one
    This is an assumption and one I believe is false. My belief is that people are more risk-averse rather than they are risk-taking [1]. People don't care to upgrade when they're winning.
    > Further, an unappealing profile that gets zero likes will continue to get zero likes after they upgrade to a paid subscription.
    Not matching with someone does not mean they have 0 likes. The platform just isn't incentivized to show you who likes you for free. Concretely we can take Tinder as an example. They will show you that someone likes you even when they won't show you who. Swiping enough to find the person who likes you usually takes countless hours.
    > This user is far more likely to get frustrated and uninstall after a few minutes than if they were to download the app and be shown profiles that are appealing
    If you're extending this to anything past the first profiles shown, this is simply untrue. You just need to dangle a carrot in the form of "someone likes you," even when the person liking you is a bot account.
    [1] <a href="https://en.wikipedia.org/wiki/Prospect_theory" rel="nofollow">https://en.wikipedia.org/wiki/Prospect_theory

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.