How Races and Religions Match in Online Dating

September 29th, 2009 by Christian Rudder

This week, we’re going to take a step back from examining messages to your matches and take a look at matching itself. We’ll slice OkCupid’s data on compatibility by religion, race, and other factors, and by the end we’ll have some unsettling conclusions on how people match and interact online. But first, I want to explain something important.

What Does It Mean To “Match” Someone?

All OkCupid users create their own matching algorithms, so when we determine who matches who, we’re just crunching the numbers people give us.
A match percentage between two people is an expression of how well they might get along.
A match percentage between two people is a condensed, yet statistically valid, expression of how well they might get along. 75% is very high, 45% is very low, and 60.2% is the site-wide average. If, for example, a couple match each other 71%, it means they are likely to like each other, based on their own individual definitions of what makes a person cool, sexy, and attractive, not ours. I point this out now so that, below, when we claim that Jewish women are easier to get along with than Christians, you don’t blame us, you blame Jesus.

We discuss matching more at the end of this post, if you’re interested or nerdy. Now let’s move on.

The Zodiac and Other Beliefs

Since he’s a Pisces and I’m a Virgo, Chris and I of course think the Zodiac is total bullshit, and it was very gratifying to have the data bear this out. Here are the grouped match percentages for a random pool of 500,000 users. Astrological sign has no effect whatsoever on how compatible two people are.

We’re showing you this table, as dull as it is, because the uniformity neatly illustrates how beefy our data set is. There are 144 pools considered above, and they all match the mean plus or minus 0.5%. Our next table again aggregates the preferences of those 500,000 random users, but it shows stronger feelings. Red indicates mutual dislike and green, mutual like. For brevity, and because that’s where we have by far the most data, all the tables on this page display data for straight men and women only.

The numbers on the perimeter of the table are the weighted average match percentage, a measure of group likability, for each column or row. Here’s what we see:

  • Jews and Agnostics get along better with people. Jewish men, in particular, have an above average match percentage with every religious group. They even match Muslim women better than Muslim men do, which I find both a hilarious irony and a somewhat sad reflection on the fact that Muslim males don’t seem to be doing very well. The data also cast an interesting light on the Jewish people’s history as a persecuted people: the underlying facts indicate an intrinsic mainstream likability, yet Jews have not been, and in some places still aren’t, “liked.” We’ll investigate a similar dichotomy in the second half of this post when we look at matching by race.
  • Muslims of both sexes and Hindu men get along worse. Now is a good time to stress that just because a group has low match percentages, even across the board, that does not mean they are bad people. It just means that they’re harder to please. The converse is also true: the above chart is not evidence that Jews or Agnostics are better than the rest of us. Just better liked. In any event, please keep in mind that each individual has designed his own matching criteria, so the poor-matching groups aren’t failing some outsider’s imposed system. Why, for example, Hindu men would match worst with Hindu women is a mystery.
  • Catholics are more universally liked than Protestants. While neither Christian group has many extremes of like/dislike, Protestant Christians only truly match well with other Christians. Catholics have above average match percentages with Hindus, Jews, and even Agnostics. Looks like Vatican II is working, guys!

Get Serious, Or Don’t

When we change our question from “What do you believe?” to “How strong do you believe it?” we get a much more orderly color pattern, and we also unlock some of the mysteries of the previous table. Below we plot people by their attitude about religion, as selected on their profile page.

As it turns out, people who hold their beliefs lightly are much better liked, even by people who are themselves serious. Weird huh? While it’s true that the most serious women believers slightly prefer their men to not be “laughing about it”, every other slice of this data indicates that the less serious (or more flexible?) you are about your religious beliefs, the better you get along.
The less serious you are about religion, the better liked you are, even by very religious people.
Please note that when I say “religious beliefs,” I’m talking about the full spectrum of beliefs, from Atheism to Orthodoxy, so don’t take this as anti-god; I also realize that “getting along” is hardly the purpose behind most people’s theological attitudes. Nonetheless, I think it’s interesting that even a man who’s “very serious” about his religion and has presumably designed his matching algorithm around this fact is still more compatible with the women who are laughing about it.

This information goes some way in explaining our first religion table: in our data pool, Muslims and Protestants tend to be more intense about their beliefs than the others, and Jews and Agnostics are by far the least serious. Here’s the first chart, replotted to include overall seriousness in blue.

Race

Ah, race. If religion is a minefield, then race is a field that’s just one giant mine. But luckily, our match-by-race table isn’t nearly as, well, colorful as the religion ones.

As you can see, there are slight matching biases here, but nothing too dramatic. It’s not going to make many people excited to hear that, for example, white people tend to be better liked, (or, if you want to think reciprocally, do more liking) than the other races, or that black and Indian men are less liked/liking, but, still, those differences are small compared to what we saw with religion. In addition, it’s entirely possible that most of the discrepancies might be just reflect different religious attitudes across the races.

More than anything this table shows the overall compatibility of all races—indicating that in a perfect world, yes, we could all just get along. Yet we don’t. And, in this way, it marks the perfect transition point in our discussion. In the real world people largely choose who to get along with, and even who to get to know.As I said in the beginning of this post, match percentage is an excellent predictor of how well two people might get along; however, in the real world people largely choose who to get along with, and even who to get to know. In online dating, we can measure this choice by looking at how often people reply to actual messages from people of the various races, and then contrast that rate with the underlying compatibilities. And that’s exactly what we’ll do in the second half of this post, which will be up next week. Look once more at the match-by-race chart above and then look at the reply-rate-by-race table below.

It’s a glimpse at the jagged terrain where we’ll be going:


Addendum, If You’re Interested: “Match Percentage”

We all know what it feels like to meet someone you really like, but, unfortunately, feelings are something web servers have trouble with. Therefore, our first goal with OkCupid was to quantify this elusive idea of “compatibility” so we could accurately suggest users to each other.

It’s not as simple as saying, Mary really likes hockey and Bob really likes hockey

It’s not as simple as saying, Mary really likes hockey and Bob really likes hockey, therefore they are a good match—which is how many dating sites work. What if instead Mary really likes being dominated during sex? If Bob also needs to be dominated, and good sex is important to them, Bob and Mary are terrible matches. In bed, at least, they both want their opposites.

This, and other thought experiments, eventually led us to a definition of compatibility that’s user-defined. After all:

  • You’re great in all kinds of ways we don’t understand.
  • You have specific needs we can’t possibly categorize.
  • You don’t want our advice, you want to meet people you’ll like.

In short, our method is this: we host an ever-changing database of user-submitted questions, covering every imaginable topic, from spirituality to dental hygiene. To build their own match algorithms, our users answer as many questions as they please (the average is about 230). When answering a question, a user also picks her how her ideal match would answer and how important the question is to her. It’s very simple, and it removes all subjectivity on our part. We simply crunch the numbers.

OkCupid is no more responsible for people’s match percentages than Microsoft Excel is responsible for their net worth.

So, for example, if two people match each other 69%, what it means is that they are very likely to like each other, based on their own definitions of what makes a person attractive, not ours. OkCupid is no more responsible for people’s match percentages than Microsoft Excel is responsible for their net worth. Again, our users write the match questions, choose which ones to answer, and determine how important each answer is. We just do the math. A very detailed explanation of exactly what math we do is in our FAAAQ.

157 Responses to “How Races and Religions Match in Online Dating”

  1. greg says:

    That last mapping seems to have lost its labels, but assuming they are the same as the previous race chart, black females are the most likely to respond to messages, for everyone except for middle eastern and native american males. Hispanic, asian and white females are the least likely to respond. And white and native american males are the most likely to be responded to, by a pretty large percentage.

  2. greg says:

    Also, how does match percentage relate to message response? I don’t recall that being in the previous entry either.

  3. th3myst says:

    The story of my dating life broken into numbers… oh fuck.

  4. Wilhelm says:

    It’s so awesome being a white, agnostic male who doesn’t take himself too seriously. Hell Yeah! Take that, black muslims!

  5. Barry says:

    Fascinating. I’d love to see the same analysis done for income, body type and height. Obviously most people are going to exaggerate their reporting for that stuff, but it would still be interesting.

  6. Quivirian says:

    I still think there’s a serious flaw in this. Your “Match Percentage” gives a symmetric result – if A matches B 69%, then B will also match A 69%. “Liking” is very much a NON-symmetric phenomenon. So the observation that, for example, agnostics tend to have higher match percentages than average doesn’t necessarily mean people tend to like them better. It might mean that they like other people better, i.e., that they’re more open to relationships with people who differ from them in religious belief.

    It would be interesting to see some analysis based on the uncombined percentages – considering how much B meets A’s preferences separately from how much A meets B’s. (It would also be nice to have individual matches reported separately, but I’m not holding much hope out for that.)

  7. Steve-o says:

    Regarding “Inflated Match Percentages”

    Yo!

    Very compelling information that you’ve posted regarding the match percentages between races and religions! I figured that the immense volume of data that OKC has at its disposal would allow for very accurate graphical representations of the statistics to be developed. I can’t wait to see more results from the analysis of this data!

    I did want to post a comment about artificially inflated match percentages, though I’m not certain that much could be done about this. By “artificially inflated match percentages”, I refer to individuals who answer questions using the following method:
    Step1: Choosing the answer that their idea match would most likely prefer instead of the one that best represents them.
    Step 2: Indicating that the answer given by their ideal match is irrelevant.
    Step 3: Repeat

    In so doing, this user is likely to have a match percentage that is higher than it should be. Now, most people wouldn’t want to do this because it would skew their match percentages up. However, there are individuals that care less about how well they actually match up with someone and moreso about showing up at the top of search results as having the highest match percentage in hopes of increasing the likelihood for profile views/messages from others.

    I believe this to be a phenomenon that is present here at OKC, though I wouldn’t say that it is prevalent. I discovered this when I had someone who had (intentionally or otherwise) used this method to answer matching questions agree to do a WTF report. I found that they had consistently selected “irrelevant” as the importance of each question, which indicates that they either A) could absolutely care less about the opinions and beliefs of potential suitors (very unlikely) or B) they wanted/needed the attention that a high match percentage and a nice picture brings. Furthermore, this person had select answers to the questions that were “safe” (or likely to be the preferred answer) so as to increase the match percentage by not detracting from the match by having selected more edgy answers. As it ended up, that person was strongly opinionated, not in the way that would have resulted in a high match percentage. I had only been able to find this out through extensive conversation that culminated in the discontinuation of contact with this particular individual.

    I would presume that there isn’t a lot that can be done about this phenomenon or its converse (wherein someone intentionally chooses answers that are likely to lower match percentage because less of their Ideal Matches are likely to indicate that these answers are the preferable ones). I only hope that the members of this site are serious when they answer questions so as to maintain the integrity of the match percentage. I can imagine that the number of members that behave in this manner are but a miniscule fraction of a percentage, but having personally experienced this situation, I remain leary of those people that have inordinately high match percentages ( >90%).

    I am a loyal member of OKC. I’ve answered (or skipped) all of the questions that are active currently. I’ve recently received my MBA in Business Administration w/ a 4.0 GPA and would love to participate in a greater capacity with OKC. If there is anything that I can do to be of assistance, please feel free to contact me!

    Thank you,

    Steve-o

  8. FunnyIntellect says:

    I can honestly say without hyperbole that this blog is the best thing about online dating.

  9. bob mack says:

    Hey, I am loving these stats your pulling. Next time, do you think you could find out sexiness correlation’s between age groups? Like for example being 28, what age group do i really have a shot with statistically? and whats the best age to be?

    Thanks,

    Bob Mack

  10. 27may says:

    What about the fact that match percentages really don’t mean much when the other user has only answered, say, 20 questions, and I’ve answered 600?

  11. Nick says:

    I’d like to see the match and respose catagories diffrentiated by height. Like, do taller men get more responses from women? And parlay this across different height spectrums.

    Also, while the zodiac and your system shows great irrelevance, can you track who actually hooks up and or at least responds to each other?

  12. cee says:

    Is it possible to filter out the religious attitude from the belief? Maybe run one graph of all the religious where they are very serious, and one where they are laughing.

    Disorderly data bothers/fascinates me.

  13. Ara Pacis says:

    This also seems to ignore the issue of answer rate and usage rate. Since people can skip questions, such as those about thorny religious isues, then the match percentage would be based on non-religious compatibility, leaving religious discrimination to rear its head undetected. It might be useful to look at a group of people who all answered at least a set selection of questions on this particular topic. Also, initial contact and response rates might be a better judge. Also, the more someone uses the site, the more likely it will be to judge whether the match percentage is operative and causitive or merely correlative.

  14. ablondecouple says:

    Fascinating stuff. It is extra nice to see info like the average match %, average number of questions answered and the like.

  15. sing_le says:

    Are even those users who say zodiac sign “matters a lot” equally compatible with all others?(I’m an “it doesn’t matter” myself).

    I’ve never filled in the religion section,though of partly Jewish descent I am a simple theist who vigorously rejects both atheism and any religious organization/text/creed and it’s important to me that a match be similarly averse to religious involvement and certain that there must be a largely unknowable God.Not sure how that would be described.

  16. Shalmanese says:

    One possible explanation for the low Hindu-Hindu match is that there are many websites dedicated to specifically Hindu dating which means that the Hindus using OkCupid are those who are specifically not looking for a Hindu date.

    For other religions, such sites aren’t nearly as prevalent.

  17. nycjunglist says:

    Being a black male who is largely not attracted to black women, the last grid doesn’t provide my already-lingering faith much more hope in OKC. Personally, it has become much more of a time-sink than anything else, unfortunately.

    On the flipside, these statistics posts are badass. Keep it up!

  18. Thane says:

    Beautiful. Absolutely beautiful. I love being awash in numbers, letting them flow over my mind like so much orange tang.

    Would be very interesting, as this is going to be a multi-parter, to see these same data-fields, but with enemy percentage, rather than match.

  19. Nicole says:

    Sing_le, I’d group that roughly under agnosticism, myself.

  20. Cappysay says:

    And Steve-o, many people (myself included) who mark questions “irrelevant” that they actually feel passionately about have not done this to inflate their match possibilities. There’s simply no option for “I care about this question a lot, but I could still see dating someone who provided any of these answers provided they had thought it through and had a legitimate reason for thinking so.” I started clicking the painful word “irrelevant” on these questions after several WTF reports turned up massive penalties with exactly the sort of people I was looking for: people who are colorful and articulate and don’t agree with me about everything.

  21. TenderCrucifier says:

    Thank you for an interesting post.

    I agree with 27May: the matching procedure is not strict enough when the number of questions is small. According to the FAAAQ, the procedure subtracts 1/(#S) from the initial score. Perhaps it would be better to use 1/sqrt(#S).

    If using 1/sqrt(#S) caused people who have answered too few questions to not show up in match results, then message those people, explain the situation to them, and suggest that they answer more questions. The questions and answers are what most distinguishes OkCupid!

    Using 1/sqrt(#S) would slightly decrease most match percentages. Would that be a good thing? Consider an example: the five best-matching people for me in the world have a match percentage of at least 90%. So, according to OkCupid, at least one of those people is a real true-life match for me with probability 1-0.1^5 = 0.99999. In reality, after studying the five profiles, it is clear that none of them is a true-life match. So yes, lowering match percentages slightly would make them more realistic.

    (Also, taking a sqrt seems natural, sort of like with std deviations and how far off you can be with (linear) Gaussian diffusion.)

  22. ABF says:

    One thing about the race stats is that white males is the overwhelming majority on this site, so that will definitely affect the findings.

  23. christian says:

    Quivirian, match percentage is a predictor of how much two people will like each other; we use it to set up matches between two people who might otherwise never meet, and it takes into account both people’s preferences. When I say “Agnostics are better liked” I mean it in the speculative sense, since only a tiny portion of the 500,000 people we’re talking about in these charts have ever met and had a chance to decide for themselves.

    It is a fact that the population at large is statistically more likely to get along with an Agnostic person, and it actually is symmetric in the way you describe. Agnostics’ high match percentage tells us that if we pair a random Agnostic with a random OkCupid member, the chances are higher that the pair could have a successful relationship (from both people’s perspective). Of course, that’s a likelihood. They might well end up hating each other. Such is the real world. Basically, match percentage is a guide to how well people might get along—given that they’ve never had the chance to annoy each other in all the ways we can’t measure with a cwebsite.

  24. mboutching martin says:

    every thing is good

  25. Kalbo1d says:

    I agree with FunnyIntellect, you guys with your blog are the awesomesauce. I don’t know that it has helped me to find more dates, but it has helped me to understand the game itself. All the number crunching is so scientific…way to be objective!

    Keep up the excellent work!

  26. chillwith says:

    this is a follow up to my earlier comment which i was unable to complete, (and i can see you have decided not to post it :-). so no hope in posting this either, still :-) i beleive you can not match people based on relegion mathematically . considering the latest stigmas attached to certain religions, alot of people are willing to admit to a certain beleife and not the other and some religions and races are willing to join such sites as okc. more than others… mathematically if you have a group A containing a mixture of (1000 positives, neutrals and negatives) and a group B containing a mixture of ( 100 positives neutrals and negatives), choosing 20 randoms from each A or B to match 20 randoms in a third group ( C ) you will most often ( not absolutely always) find most matches from group A…still the whole matching system is useless and you will not post this :-) :-)

  27. Cynical_nerd says:

    I personally have chosen irrelevant on almost every question. Rarely is something so important that it will make/break a relationship.

    Is it not okay that my match have differences in opinion?

    Switching topics, how is friend percentage calculated? I understand the match and enemy but friend percentage is given no face time, even in the FAAAQ.

  28. Codexon says:

    Forgive me but I decided to give the “Message reply rate by race” diagram a proper axis since I couldn’t wait until next week here:

    http://www.codexon.com/posts/okcupid-dating-statistics-shows-racism-very-much-alive

  29. Lea says:

    I guess I’m too french because religion like it’s so important even when dating sounds so retarded to me. Why people should define themselves as being something? I wish people were first and foremost free citizens.

  30. thoughtcrimes6 says:

    Brilliant, Brilliant job guys, this is fascinating stuff. I can’t wait for a much larger demographic from different locations in the world, join in and reveal some facts. The religion/race tables were very enlightening and something that I had predicted, intuitively, nice to find statistical evidenc of the same. I feel almost stupid saying that I am more excited by the work this website is doing in psychology/sociology than actually finding a match here! I wish I could join you guys in this venture in anyway possible other than spreading the word about the site itself.

  31. Steve says:

    “I’d love to see the same analysis done for income, body type and height. Obviously most people are going to exaggerate their reporting for that stuff, but it would still be interesting.”

    Odd, I don’t feel any need to exaggerate any of these.

    “Next time, do you think you could find out sexiness correlation’s between age groups? Like for example being 28, what age group do i really have a shot with statistically? and whats the best age to be?”

    Analyzing age discrepancy between matches is a great idea.

    Have you ever considered changing the way the match questions are scored? Like others commenting here, I have also found the “Irrelevant”/”Mandatory” ranking to be nonintuitive, and it has marked as incompatibilities things that actually aren’t, or it has not taken “mandatory” seriously enough. Maybe there’s a fundamentally better way to word the match questions and importance?

  32. Thomas says:

    The male jews/female muslims was really a truly sad irony :(

  33. Matt says:

    Poor Gays. Always left to the side. :)
    I’m curious if the trends between male and female continue when looking at male-male and female-female pairings. I realize that there is a smaller data set and also some definition wrangling that may be necessary, but I would be interested in the results.

    Yours, Matt
    (TheoTiger)

  34. reagan Gibbs says:

    this is chewy goodness… maybe it says more about how people think,em/> about themselves than the reality of their interaction–but it IS provocative. Mark Twain said it best. There are lies, damn lies and statistics.

    reagan Gibbs

  35. reagan Gibbs says:

    this is chewy goodness… maybe it says more about how people think about themselves than the reality of their interaction–but it IS provocative. Mark Twain said it best. There are lies, damn lies and statistics.

    reagan Gibbs

  36. SeanLouis says:

    Interesting stuff!

    I found it interesting that the highest rate of message response is by black females. I’ve personally known many to complain that they have a hard time getting dates. The funnier thing is the last one turned me down due to both my height and my Atheism. Oh well! Short white boy Athiests get no love!

    An interesting chart would be height vs response percentage.

  37. DiscoJer says:

    You should really put that quote about the matching system, “OkCupid is no more responsible for people’s match percentages than Microsoft Excel is responsible for their net worth”, someplace on the proper site.

    So people people post on the forums about the matching system being bad, when they are simply lazy about using it.

    Anyway, one nitpick, unless I’m missing something, the options for religion on OKC are Catholic and Christianity, the latter should not = Protestant. I am a Christian, I am neither one of those. There are also things such as Mormons and several varieties of Orthodox that are Christian, but not Catholic or Protestant.

  38. Oscar says:

    Interesting analysis, and thanks so much for sharing – it makes for great discussions.

    I wonder how well this data correlates to what we might find if we did the same kind of analysis on a wider scale and outside the bounds of OkCupid members. In other words, does this data tell us that Muslims are generally much more picky and “more difficult to like”, or just that Muslims on OkCupid are this way?

  39. Rusty says:

    I would love to see hair color vs. response rates. More specifically, with what type we ginger-kids would get the best response.

  40. Chris Charabaruk says:

    How are you guys normalizing the data so to avoid sample bias? Are you even bothering to minimize its effects at all? For any of this to be valid, it’s important to know that you’re actually doing something about it.

  41. noone of consequence says:

    Very interesting post, thanks. I have a couple of comments

    1) your charts do not look good to a colorblind person. Can we get colors that contrast with each other even when converted to greyscale?

    2) your blog would be easier to read if posts by the blog owners were marked somehow. I mostly like to read replies by blog owners.

  42. Jumanji83 says:

    “As it turns out, people who hold their beliefs lightly are much better liked, even by people who are themselves serious. Weird huh?”

    Not really. The more you take your spiritual views seriously, the more likely you are going to disagree with someone about some religious Truth. Even people who share a religion won’t agree on all its principles and interpretations.

  43. Zingiberis says:

    I would like to see how age has an effect on dating on this site. Been here quite awhile and have not received any interest from anyone that is physically close enough to actually meet and that has been sparse.

  44. MysteriousPringerP says:

    Heeey–they left Christians out of the equation. >:\

  45. Yan says:

    Beautiful analysis and insightful data mining as usual; keep it coming! As a web entrepreneur myself I have to give you massive props on getting so many things in your service right. It’s very engaging and you’ve clearly created a very powerful data collection system that keeps people coming back for more.

  46. George says:

    I am very impressed, even if I don’t entirely understand all the algorithms yet. As more data gets crunched, a lot of the other comparisons mentioned above will surely be added. Also, Codexon, cudos for taking it to the next level on your own! Hopefully you’re analysis will be close to what OKC finds (otherwise, we’re all gonna be mad at you!).

    As a professional black guy here in DC, I must say that I don’t feel quite as ‘unloved’ as the numbers suggest I am. Granted, it could always be better, and it’s clear white guys in general (with the exception of SeanLous) are considered to be highly sought after! But I’m guessing a few things are true here. For a free site, OKC seems to be a relatively well heeled female clientele, at least here in DC? Lots of grad degrees, good employment, etc. Rarely do I receive an unsolicited email from a female (and when I do, it’s almost invariably someone I don’t want to talk to!), so I can only judge by who responds to my emails, and it looks like this:

    I’m not particularly dedicated to dating a certain race, so I kind of take things as they come. On OKC, there are undoubtedly more whites than members of other ethnic groups, so most girls I email are white and, within that group, largely not-religious or ‘laughing about it”. Of this group, I’d estimate that I hear back from …..perhaps 1/3? Not outstanding, but more than enough for me to have several in person dates a week. Although it’s harder for me to track down black girls that I have a lot in common with (other than race), I actually very rarely hear back from them when I do email them. I think this might be because the one’s that catch my attention is relatively highly sought after by everyone, meaning the short godless dorky black guy is not first in line there. I’ve also started to get good responses from very nice latin girls (gracias!). As for Jews, I was very open in the beginning, but am starting to feel like few return my emails and the ones I end up meeting seem very incompatible/unhappy with me (perhaps because I know too much about jeudaism and thus remind them of the jewish guy they were trying to avoid when they decided to go out with me in the first place!)

    Anyway, for more important than any of these statistics are the ‘intangibles’ like writing style, humor, etc. If you write a witty, well written email that shows you read her profile, that’s 2-3 short paragraphs long, and you have decent pictures of yourself up, and you do this more than 10 times per week, you’ll be just fine: luckily for guys, girls are a lot more forgiving in terms of appearance than guys are……but just barely!

  47. jakefunc says:

    Wow, I’m really impressed. Each week I find myself more and more intrigued by this statistical analysis. Funny how TheSpark was rooted in science, even if in such a ridiculous manner.

    You are indeed treading upon rough ground…
    Persons perceptions of ethnicity, yikes.
    Here’s the breakdown of American(right?) culture folks, in neatly ordered, shiny color squares.

  48. chillwith says:

    i’m starting to get my head round this, still feel it sad for some one to get less matches based on their beleif and ethnicity, and i still beleive the statistics are wrong since you are more likely to get a positive match result if you have a nice pic. (sad) . and other mathematical factors like the over all amount of a certain religion, or a certain ethnicity users, aswell as factors like overall amount of users in a certain location compared to another and many other factors…example ( my guess is there is more positive match results between users from the USA and other users from tthe USA, compared to results between users from the USA and users from Holland regardless of beleif and ethnicity. Very interesting though and really thought provoking work.

  49. Rob Gordon says:

    Note that the site “eHarmony” screens out agnostics and atheists. It was proven recently on a blog – if you take their test and answer all the questions the same, but in one say that you are an atheist, you will be rejected by them. The people who built this site are right wing Christians, and small minded bigots. Regardless of your religious or spiritual background, please do not support them.

  50. MnemonAgain says:

    Awesome job, really – I love those statistics.

    I have one add-on: Is it possible to quantify the amount of messages sent out by scammers, spammers and webcam-babes? I do not know how big the volume of mail sent by those is on okc, but they might distort the response rate blonde goodlooking women get on OKC :D

    Anway, great work!