Comment by Melting_Harps | Hacker News Reader

Comment by Melting_Harps | Hacker News Reader

This reminds me of a recent NPR story-telling guest from a PhD student at UCLA who hacked one of the major dating apps (match or eharmony?) matching algorithm and he was going into detail of his exploits; he used the Lab to run tons of simulations of desirable answers to the profile questions to garner the attention of women in his surrounding area and on the site internationally.

In the process revealing how erroneously so many put stock in matching via a system with a very clearly vulnerable system (compatibility rating algorithm) and went out of his way to optimize the system further with less than desirable results: he was the most desired Male profile and was going out on several dates a day and rejecting women he'd have coffee dates with in more and more absurd ways as he got more and more requests.

It was really funny, albeit cautionary, and I only caught like 65% of it, so if anyone finds it can you post it here?

Jack Dorsey's recent interview on the AI podcast hinted at how perilous this could be, too. The 'why' part of Machine learning/data Science/AI has to be just as tightly examined as the optimization development when deployed into Society.

Probably this? https://themoth.org/stories/data-mining-for-dates

And here's an article https://www.wired.com/2014/01/how-to-hack-okcupid/

Not to throw this into standard male internet complaining about dating, but it's funny that the Wired article waits until almost the end to mention that the dude is over six feet tall with blue eyes (and per the photo at the beginning, not bad-looking!). I wonder if this kind of gaming would have worked if he wasn't already in a highly desired male demographic. It's possible that just being noticed is a big marginal benefit when you're already in that demographic.

Of course it wouldn't. Why would women suddenly find a man attractive just because some app brings up a match? The matching algorithms are not there to show you who you find attractive, they are there to filter out the 95% (for women), or 50% (for men) of people you definitely don't find attractive.

If 95% of women reject your profile, would you get more matches if your profile was in front of 10 women or 10,000?

The trouble is it's not "95% of women reject your profile" but rather "women reject 95% of profiles" -- which is something else entirely.

Generally it’s not 95% of women rejecting a given profile, but all women (or near enough to make no difference) rejecting mostly the same 95% of profiles and not rejecting the rest.

I.e. boosting visibility probably brings proportionate benefits to the most desirable men, but little additional benefit to the ugly/short/older guy.

Source? With 51.5% of American men presently married I have a hard time believing 95% of men are consistently rejected by every woman!

It’s 95% of the men on dating apps, not 95% of all men. The men who get married presumably delete their profile. It’s not hard to see that all of the gold had already been panned out and there’s nothing left but mud (in the eyes of the women on those dating apps).

That sounds like how hiring managers describe the tech job market.

Sellers' markets all have this dynamic.

Edit: wtf @ stripping emoji HN

It's probably a misremembering of actual findings:

At least on OKCupid, women rate 80% of men as below-average attractiveness, while men rate women at right about 50% as below-average and 50% as above-average [0].

OKCupid has since deleted the post with their findings [1], but references to it still exist all over, as does an archived copy [2].

[0] https://techcrunch.com/2009/11/18/okcupid-inbox-attractive/

[1] https://theblog.okcupid.com/your-looks-and-your-inbox-8715c0...

[2] http://web.archive.org/web/20100324074028/http://blog.okcupi...

It sucks that they deleted it. It's so hard to know the truth in this area because the truth offends people.

Their blog was a goldmine but decommissioned when they were bought by match.com

Maybe men just answer the question more literal and find the real average (50%). Women understand the question more figuratively. Below average is what they don't like and they don't like 80% of men.

Why even ask for above/below average ratings? What people like/don'tlike is more interesting.

Maybe he most attractive men in the population aren't on dating apps.

If someone had good experiences with people the app recommended previously, then the app recommending someone can be enough to make them willing to date them.

It's basically the same mechanism that works for physical attraction, i.e. if you had good interactions with people of a certain "type" then you'll be attracted to other people of that "type".

Are those percentages based on data you got somewhere, or are they a part of the 84% of statistics that are made up on the spot?

Not sure why folks are downvoting me... perhaps giving the humorous out is rubbing folks the wrong way.

I looked at the links and didn’t see mention of those values, and I don’t know if they are commonly known, so I’m going to ask again.

Where are these numbers (95% of women and 50% of men) coming from?

The OKCupid and Tinder studies, as linked elsewhere. The OKCupid study showed women rate 80% of men as "below average". But if you assume that most women don't want an average or even just slightly above average man, it easily becomes more than 90%.

It is probably based off the OkCupid data that found that women rated 80% of men as below average attractiveness or the Tinder data which has the top 50% of women chasing 5-10% of the men.

https://medium.com/@worstonlinedater/tinder-experiments-ii-g...

https://qz.com/1051462/these-statistics-show-why-its-so-hard...

http://archive.is/BtTP2

I can't find the actual statistic the above people are repeating, but these are similar.

It starts with his photo...

This was fascinating all around - both for the means by which he optimized OKCupid for himself, and for the the insights about women that it yielded. He was able to type women in to 7 clusters, but that 7th cluster ('diverse') could have been optimized into further groups, it seems.

> Probably this? https://themoth.org/stories/data-mining-for-dates

That's it, I was really hoping to hear this in its entirety but could never find it: thanks!

I did this on OkCupid just by answering common questions in the most common way. But more dates isn't really the point, at least not for me. So I weighted the questions in the way they mattered to me and I met my current gf. Cheaters only cheat themselves.

Yup, met my wife this way too (OkCupid as well). I in general was very upfront. I didn't try to sell myself much, which meant my flaws in interaction were present too. I didn't like the idea of wasting time with people I'd slowly push away as I let my crafted guard down.

Yes! The thing was that he only got 3 second dates and 1 third date. In the end, he gave up and found love the way the algos intended; she messaged him. The conclusion I took was that the math worked. His gaming the systems was pointless, he needed patience more than anything.

Reply on news.ycombinator.com