Show HN: BandMatch – “Tinder” but for finding musicians to create bands/collab

Dating app monetization creates a principal-agent problem: both subscriptions (for paid apps) and advertising/data-brokering (for free apps) are revenue streams that depend on people engaging with the app as much as possible — which people who actually manage to find solid romantic relationships won't do.

The only good dating app monetization model, would be a one-time-fee model. This would induce the correct incentives: as long as people are on the app, they continue to be a cost burden on the service with no further revenue — so, like people hogging a table at a restaurant, the service would be motivated to satisfy them and get them out the door!

But AFAIK, nobody has ever done this yet. (I think it's just because such a site would make so much less money than the traditional "milk your user base eternally" type of dating site. And people who build dating sites are usually in it for the money.)

yes anyone can use a throwaway email, maybe it's all irrational, but i know from user interviews i'm not the only one who feels that way

same thing for app vs web. there's at least a feeling that scammers/hackers/creeps on the other side of the world have less access to my personal info. again maybe it's fake, but the perception is there. (otherwise generally i would prefer web > app 100 times out of 100)

Treating recommendation as a classification problem has all sorts of flaws, mostly down to normalizing the user's indications into a larger model. People will be more passive sometimes and more engaged at other times. Sometimes they'll blindly accept and watch everything that comes along (or blindly swipe right on every match, etc); other times they'll be very choosey.

It's kind of the same problems that asking users for star ratings has — people interpret the meaning of "one star" or "three stars" or "five stars" differently; and there are selection biases on when people will bother to vote at all. (The Netflix Prize was a challenge for a reason!)

You can avoid all these temporal and selection biases, though, because content recommendation is actually ultimately a ranking problem: any recommendation algorithm ultimately wants to generate a subjective ranking of its universe of items, such that everything gets put in a sequence, with the thing the user would most like to see next, first.

And conveniently, we already have a mathematically-perfect way to do ranking: ELO. Or, in app UX terms: the classical HotOrNot design, where you're presented with exactly two options, and you have to pick one as being better than the other. And you get to see the each option several times, paired against different other options each time.

In user-engagement terms, a HotOrNot interface would be just as much of a "dark pattern" as a Tinder interface. But in recommendation-tuning terms, the backend of a HotOrNot-UX app could build you a subjective scoring function that's much more accurate, much sooner.

> you can't conclude anything at all because a user didn't click on an item

The real negative signal that sites like YouTube (and to a degree, TikTok) use, is landing on something though a more passive engagement action (e.g. auto-play next) and this inducing engagement in a previously-passively-consuming user to "get away" from this content.

A probability score for “will he like it?” works as a ranking score in my experience with some caveats which aren’t so much about the score as a score but that recommendation is really a sequential problem. That is, if I get different versions of the same news article that all score 0.9, it might be OK to show me one or two articles from that list. I believe people’s satisfaction with an article is greatly influenced by being spammed with too much of the same thing and that is not so influenced by ranking scores.

I’ll go so far as to say full text search should also be treated as a classification problem, in particularly you need a probability score if you want to make a service like “Google Alerts” where you tell people about new marching documents. Also if you are trying to combine several radically different searchers (like IBM Watson did back in the day) the probability score is essential.