According to the wikipedia article on continents, different models are taught in different countries, so you probably end up selecting for a different attribute than you thought.
That questions seems to be a pretty good filter, just not for the reasons he thinks it is.
(As I child – not in school but before – I learned that there are five continents: Africa, Australia, America, Asia, Europe. I don’t think I was ever told in school how many continents there are. All we were told were names of certain landmasses to make sure we are all talking about the same thing when saying America, Antarctica, South America or Eurasia. Why bother counting them? That doesn’t even make sense.)
OTOH, I think I marked this question as irrelevant.
But, I expect when they start teaching people which plates things are on plenty of people are going to find it strange.
If you know every property of something it’s not necessary to ask whether it really is a continent or not.
There isn’t even a communication problem when it comes to this question so it isn’t really necessary to find some sort of great definition.
No matter how many continents you told there were, if you payed some attention you know what people are talking about when they say America, North America, Europe, Asia or Eurasia.
There are lots of otherwise smart people who believe in "stupid" things. For example, in Japan many people believe that your blood type is an indicator of your personality. I'm talking about educated people.
So, there are many women who are interested in astrology. Some don't really believe that astrology is scientific, but they read the horoscope column anyway. Unless she takes it seriously and makes life/relationship decisions based on it, I wouldn't consider it a deal-breaker.
I still have the astrology chart she drew for me.
I didn't know I didn't care about the nutty side until I met her.
I wouldn't have met her via this algorithm.
It's about the general principle that (a) OKC should make Mandatory questions only count as negatives, and (b) unless they do that, users shouldn't make "factual" questions including (1, 2, 3) mandatory.
Maybe they shouldn't have been mandatory in the first place because you can love someone who believes wrong facts, that's a valid point as well but doesn't relate to the algorithm design issues.
The question is "which is bigger: the Earth or the Sun?". It doesn't specify how to measure big, so when answering the question I decided to consider angular size and answered that the Earth is the larger of the two.
I could also say that I am bigger than the Sun because whenever I see the Sun it is only around 3 inches in diameter while I am 5 feet 11 inches. But that is a completely dumb statement, and so is yours.
I can't address all the particulars raised in this analysis, but the biggest is essentially correct:
> The worst side effect of the current scoring system, is that a spammer could easily answer only the questions with obvious answers (basic facts and display of non-bigotry) and get a decently high match percentage with a lot of people. At which point, the spammer uploads a picture of an attractive guy/girl, writes some generic profile text, and scams away.
The algorithm as described in the FAQ does suffer from this problem. However, we have enhancements that address the issue very effectively. The FAQ is slightly out of date, and shouldn't be taken as a complete, exhaustive description of how we make matches.
If you're one of the aforementioned spammers, I assume you just set it up once in pywinauto and then go nuts.
That is exactly what I did which led to my meeting my (now long-term) girlfriend. I was receiving about 5 profile views/week with 500 questions answered. I scrapped them all, answered 20 or 30 questions with non-offensive answers, and skyrocketed to 60-100 profile views/week.
The art of online dating, IMO, is not in the questions answered but the messages sent and secondly how non-offensive your profile description is. Include keywords "Hiking, Laughing, Friends/Family, Good Beer" and you're in like gin.
My 2cents :)
Side note: your view count seems to depend a lot on how active you are. I check back perhaps once every couple weeks, which means most of the time I never show up in the all-important "Online now" or "Online in the last day" search results. Hence girls who find my profile tend to be really looking, and more likely to message. If I'm online regularly for a couple days in a row, my view count goes up, my message count stays constant, and the view/message ratio goes way down.
I guess I can't argue with success, but it seems like the best use of the site is to select for the kind of people you would actually enjoy meeting. And the best way to get people to look at your profile is to write them a message which you spent ~5 minutes thinking about.
100 views = 10 messages = 1 date seems like a ballpark, but there are so many variables that it must be different for everyone.
The current approach is entirely oriented to give people what they think is important and what people think they want. It would probably be better to derive that from existing relationships (successes).
I would be a little surprised if people at OKCupid hadn't already thought about this. Whether there is actually any momentum to change the core matching mechanic or not remains to be seen.
That's not to say they're meaningless though; e.g., if someone puts "mandatory" for all his questions, that definitely says something about his personality, and should be used as a feature in the ML algorithm used for matching.
Another problem is that a lot of users are probably more casual about the weights, such as selecting mandatory. (It's common for people to select an answer and then mark that same answer as unacceptable in a match, for questions in which it makes no sense for them to do that.)
Users can tweak their answers or importance levels and are even encouraged to do so.
They keep you on the site with incentives (answer more questions, you'll get to see better profiles!).
If the algorithm was better, they'd be out of business.
They are doing pretty well, considering their competitors have ads on TV.
I got some profile views and a couple of conversations, but never met anyone through it; with the exception of seeing my co-workers on it, in Shanghai.
In each city, within a few weeks of creating a profile, I've been in a relationship, but not through the site.
I'd suspected for a while TBH that there were odd effects from the balance of what questions were answered; some topics have more data coverage than others in the question pool and that (for me) seems to put a noticeable damper on its precision in other areas.
I've noticed that too. There seem to be a lot of repetitious questions all aiming at or around faith vs atheism. "Do you believe in fate", "Do you believe in miracles", etc are talking about the same kind of thing.
passionfruit, that does exist on OKC. Some of the tabs to the right portray personality aspects like messy, experienced, old-fashioned, indie, geeky, thrifty.
Hmmm, I'm a bit disappointed or maybe I'm just missing something.
Of course, it doesn't really matter for me, anyway. I don't use OkCupid as a dating site. I use it as a way to find things like local libertarians, programmers, and other essentially platonic things. In fact, for a few years, I haven't even used it for that -- but that's how I did use it, so dating criteria are kinda irrelevant, which means answering questions is kinda irrelevant too. (I've answered quite a few just for shits and giggles, though.)
It could be that OKC has developed a very good system for meeting new friends, but not necessarily for dating.
A) Dudes that have an opinion about the OKC algorithm
B) The amount of times they get laid each week
Jokes aside, I'm fascinated with this topic. For most of history, the likelihood of finding a mate was left to chance. Then OKC comes along and says it can leap past obstacles such as chance and geography to help you find your soul mate. That's an incredibly powerful idea.
I like OKC, but they don't do even basic filtering of profiles. If they just verified, say, a mobile phone, it would get rid of the vast majority of fake accounts.
So anyway, some tweaking done. Let's see if it has any visible effect...
* If you're going to do it properly and give them meaningful data, a 'quick' skim is the exact opposite of what you want to do. Yet it's what the function is set up for; you can't even see a person's questions and answers, which have frequently (to me) proved far more revealing than the profile.
* Again, if you're doing it properly, rating someone highly sends them a mail saying 'someone's interested in you'. Which always looks to me like saying 'Someone's interested in you but doesn't have the guts / energy / enthusiasm to write you a proper message so has gone for the easy way'. Not a great intro.
With a bit of tweaking I agree it could give some useful seed data, but not much more; fundamentally I think the question-based approach is very good, but I think their scoring algorithm could benefit from refinement.
In both cases, the key observation is to realize that the meaning of the numbers is more important than the numbers (or how they're calculated, per se). This point is kind of abstract--especially compared to the salient examples in both pieces--but if you're looking to understand why this error is so common, look first to the fact that it's not an error of stupidity or insufficient maths.
You can sometimes avoid a big practical problem (e.g., an avenue to attack your system via diluting meaning ("spam")) by abstractly considering the meaning behind the structures available to you.
Spearfish, SD versus Brooklyn, NY for instance -- the Brooklynites could benefit more from algorithmic improvements.
So, I think that the right way to go is to just increase the speed and accuracy with which a human can look for matches. Some ideas here: http://ideashower.posterous.com/idea-dating-site-slideshow-a...
at this point, I dont really even look at scores anymore. I can tell based on profile text alone whether I'm likely to get along with a person.
but this is age and experience, not math.
I'd rather okcupid had a feature that tells me what things are going to cause fights between a person and myself after we date for a while :)
but this is age and experience, not math. //
Arguably your brain is running an algorithm that can be expressed mathematically, we simply don't know the exact nature of the algo.
Age is largely irrelevant, it's mainly a first pass indicator for experience. Your experience is probably largely a statistics based algorithm with some unsound choices caused by your psych make-up thrown in to keep things interesting.
This seems like a weakness to me. I'd love to be able to choose between different algorithm for matching features and set some relevant coefficients. It'd be fun to see the profiles that have a minimum hamming distance from mine, or whatever.
Most everyone who would join it would be a giant nerd, even moreso than OkC, but that'd significantly increase average compatibility!
I expect that to change though - one (of the many) differences between men and women is womens dating worth as a date falls in her twenties while the typical male sees his dataing value go up.
I am still not interested in an older woman (or a fat one, or a fundie or a single mom). If I wanted to date my mothers friends I would give them a call.
It's essentially good enough for them, since the mainstream audience wouldn't realize that, and if a few geeks figure out a way to cheat the system, then that's fine too, since they need all the help that they can get
Is there a way to contact them? They don't reply when I sent via Feedback form is not answered. I seriously thought they have gone out of business (however improbable it might be, being acquired just this year for $50 million)
What is the stigma of online dating?
Obviously the implied answer is that if you are using online dating then you cannot find a date IRL. Or perhaps a kinder answer would be that you have too much going on to find a date IRL. This is the same principle as a meat-market nightclub/singles bar where the bouncer lets the guy with the two attractive women in, but the pack of forever-alones get locked out. Then the slightly wealthier gentleman pays $ to the nightclub to get in, for the opportunity to pay $ to one of the attractive women (in the form of a drink) for the chance to talk to her and (hopefully) get sex/affection/phone #.
Of course this is all crazy, but it is a way in which many bars/nightclubs/online dating works. If OKC can attract attractive women with quizzes/validation/'looking for friends' and associated kitsch, they have it made.
OKCupid was interesting, but not a magic bullet. It was then bought by Match, which consists primarily of marketing and poor website construction.
Online 'dating' is a social problem more than a computing problem and, as such, no good solution will ever exist. Anyone male thinking of sinking time into one would be better served by simply getting out more, taking classes, adopt a dog and walk it, etc.
Several months later, when I was reading The Game, he got around to describing exactly this 'test'. I laughed for quite some time.
Apparently, PUA cheesiness works online, as well.