A conversation with the co-founder of OKCupid.
Sam Yagan: My name is Sam Yagan. I'm co-founder of OKCupid.com.
Question: What’s new about OKCupid?
Sam Yagan: I think of OkCupid as an online bar; a place where singles can go, have fun with each other and in the process hopefully meet new people, some of whom might turn into a romantic relationship.
Imagine if you had a video camera in every bar in the country and you could watch and log every transaction, every interaction that took place. You could watch what each person was wearing; you could watch what pick-up line they used. You could watch the person of this race and age approach the person of this race and age. And was that a successful interaction? Imagine how amazing that data set would be and how much fun you could have learning about people, dating, society.
We’ve got that essentially on our online bar. We can watch every time someone looks at a profile. Do they choose to send that person a message? We can look at every message that’s sent and we can determine, was that message replied to or not. And we can run a bunch of regressions and a bunch of analyses to determine what were the driving factors of that decision being made to send a message or that decision being made not to reply to a message.
So we have this data. And what’s really interesting about the data is that it is not survey data. It’s not an experiment; it’s not in a laboratory. If you remember back to the 2008 elections, there was this thing called “The Bradley Effect.” And nobody knew if the surveys were able to actually quantify the potential impact of race. If you call someone up and say, are you racist? They say, no. And will race impact your vote? They’re going to say, no. But when you get into that ballot box, you just don’t know what’s going to happen.
And so what we’ve got is we’re actually observing these behaviors and race is the easiest thing to talk about because it’s so salient. But even beyond that, you can look at hair color, you can look at height. You can look at pickup lines.
I think the data-based approach actually appeals much more broadly than a psychology-based approach which might just be dismissed by people. Even if you’re not a math person, you’re unlikely to dismiss something that was brought to you by a scientific process.
Question: What has the reaction been to OKCupid’s approach?
Sam Yagan: We have published some things that have made other dating executives worry about us and wonder why we’re "hurting the industry." For example, we published the average response rate on OKCupid is about 33%. So about one out of every three messages you send get responded to. And we got several inquiries from our competitors saying why would you say that? Why would you tell people that most messages they send don't get replied to?
Our entire brand is about transparency. We want that data out there because you know what? If you are only getting one in three messages replied to, you’re normal. You’re right there in the middle of everything with everyone else. So rather than wondering to yourself, “Wow, am I the only person that’s not getting most of my message responded to?” Quite the opposite. You are, again, in the norm.
So we really believe that transparency is the best approach. We think we have the best product. We think we have the best matching algorithm, we think we have the best members. So why wouldn’t we want to just shine the light onto just how our processes work, what the real data are, and let people come to their own conclusions.
Question: How is OKCupid different from other dating sites?
The biggest difference between a psychology-based approach to matching and a data-based approach to matching—in particular in the way that we do it as opposed to somebody like eHarmony—is, you know, eHarmony employs a centralized model. They have a specific way to match people up. A specific belief on what drives a successful relationship. They may be right, they may be wrong, and that’s the flaw in their model... is that they may be wrong.
Our system is decentralized. We don’t have any preconceived notion of what makes a good match. We don’t have any preconceived notion about whether like wants like, whether opposites attract. We don’t have any preconceived notion that God is more important than pets. What we believe, fundamentally, is that people are single and people therefore turn to online dating, not because they don’t know what they’re looking for, but because they don’t meet enough people in their day-to-day life.
Ask yourself, how many single people of the appropriate gender, the appropriate orientation and the appropriate age do you meet in a given week? If you’re like most people, you have routines. You go to the same job, you go to the same gym, you hang out with the same friends and you don’t meet that many new people. You turn to online dating, not because you say, “Gosh, I have no idea what I’m looking for.” You turn to online dating because you want to meet more people. And in that way, I think the decentralized model of you come and tell us what you’re looking for, we’ll use data, we’ll use algorithms to sort through the millions of profiles and find the best people for you. We think that’s much more powerful and, in particular, not exposed to that risk of our algorithm being wrong. It’s possible the eHarmony algorithm is perfect and right, but it’s also possible that it’s right for some people and wrong for other people. And if you fall into one of those... if you’re one of those people for whom their algorithm is wrong, then their product can’t service you by definition. And our model doesn’t have that fault. We don’t believe that X is looking for Y or that A and B are matches for each other. We simply give you the platform to express your preferences.
We have this term in the office called “three ways,” which isn’t probably what you’re thinking about. A three way in OkCupid’s parlance is a message, a reply and a reply back. We believe that if you’re in a "three way," that is, you are having a conversation with someone that is a metric of success. We’ve done a good job of matching you up. So we do feedback whether or not a message led to a "three way" into our matching algorithms.
There is a risk of people gaming the system. And that’s a question we get a lot because these are expressed preferences rather than observed behaviors. There is a chance for someone to answer questions in a particular way that they might think is more attractive to someone that they’re trying to impress. We have a few different ways of countering that. The most powerful of which is, our system inherently penalizes inconsistency. What do I mean by that? There might be 10 questions, imagine that we have learned, that are highly correlated. Right? We know that people who tend to answer question A, a certain way also answer question B a certain way and answer question C a certain way.
So if you go through, you’re trying to game the system and you don’t actually have these preferences, you’re just trying to guess what answers are going to be the most attractive to a given person, you’re unlikely to know and to expose all those same correlations that we’ve seen in the data.
Sort of a more visceral way of thinking about that is: if you try to game the system, you’re unlikely to... you’re going to have a set of preferences that is likely to piss everyone off in some way or another. Right? Because you’re not a sort of coordinated set of answers that’s likely to make one person very happy and one person very unhappy, you’re likely just to make every person relatively unhappy because you haven’t answered the questions in a consistent way that people are looking for.
And so the system inherently penalizes someone who tries to game it. It inherently penalizes inconsistency. Now you could sort of put yourself in some sort of Zen mode where you just say, "I am going to become this person. I’m going to become a 45-year old devout Catholic who is looking for marriage." And you could sort of live out this whole lifestyle and answer every question exactly that way, and sure, in that case you’ll game the system. But for most cases, you’re going to have missteps along the way and the system is going to penalize you.
A lot of times what people think they want and what people actually want turn out to be different. So you may say that I want someone in this age range, or you may be searching for someone of a certain ethnicity, of a certain race, but it may turn out that you may be sending messages to people outside of that range, or outside of those constraints. And so we will sometimes loosen constraints for you if we know that you’re actually more receptive to people outside of those boundaries.
Question: When you give away your product, how do you make money?
Sam Yagan: OKCupid’s model is almost entirely based on advertising, which is the way most online media is monetized these days, whether it’s the news or whether it’s sports and we think online dating is going to evolve in the exact same way. In fact, we think that the paid subscription model is somewhat antiquated and doesn’t really flow with what the people on the Web, especially young people on the Web, are expecting from a media property.
I think for marketplace businesses, and when you think about online dating, it’s not a social network. It’s not a place where you go to talk to people you already know, it’s a place you go to interact with someone you’ve never met before. And so when you think about the marketplace businesses and what makes an efficient marketplace, you want to make entry and exit into that marketplace as efficient as possible.
So putting up a pay wall and keeping people out of your marketplace is the exact opposite of what you should be doing. The sort of the most efficient way for online dating marketplace to evolve, and in fact, any marketplace to evolve is to have one really big market where people can enter and exit as they please, where people have really advanced search, sort, and filtering technology. Look at classifieds, look at auctions in each of those industries you’ve got eBay, you’ve got Craig’s List that have dominated the entire vertical and they’ve done so by making their marketplace as efficient as possible.
In an ideal world, we would charge people a $10,000 success fee when they get married, or a $5,000 success fee if they enter into a relationship with someone. Unfortunately, that’s a little bit hard to track although someday maybe we’ll get around to that. So yeah, we do have that challenge, but there is no financial transaction that we’re in the middle of. So in the monetization sense, we’re like any other media property.
However, we can collect a disproportionate amount of data. We can ask our users questions in the name of getting them a better date that practically no other property could ask. We can as about people’s smoking preferences, we could ask about how many hours of video games you play. We can ask whether you want to have kids. We can ask all kinds of questions about your personal life and your consumption habits and your preferences that you would not tell to any other site on the Web, but that you’ll gladly tell us in exchange for better dates.
What we have found is that users understand the kind of quid pro quo at OkCupid, which is that if you give us data, we give you dates—and, oh by the way, we’re going to show you some more relevant ads at the same time. We’re very careful about personally identifiable information and not using anything that is inappropriate for targeting an ad. But if we know that you like to play video games, we’re going to show you a video game ads. And what we have found is that users actually prefer ads that are well targeted. You know, especially in this political season, the thing that upsets people the most is seeing an ad for a candidate they don’t like. That’s what gets people the most angry.
So if it’s based on someone’s preferences then I would love for someone to show me a BMW ad; that would make me very happy.
Question: What have you learned about human behavior by looking at online dating patterns?
Sam Yagan: There are a ton of interesting things that we’ve learned. One thing that we learned that we published on our blog post is that uniformly, men lie about their height by almost exactly two inches. So if you look at a plot of census bureau data on the distribution of men’s heights in the U.S. and you plot men’s heights on OKCupid, it is exactly shifted two inches to the left. And so it’s just interesting to see how uniformly men lie about their height when given a chance to. Until they get to about six feet. And then they don’t lie quite so much. But if you’re under six feet, you’re going to add about two inches to your height. That’s one example.
We talked about some of the race... some of the interactions based on race. We also looked at what words people use in their profiles. And we categorized those by race and gender. And we said, what words are the biggest outliers in each race/gender pair. And so for white men, the word they use most disproportionately is the phrase, "Tom Clancy." For white women, it’s "The Boston Red Sox," if you look at Hispanic male profiles, they reference violent sports like mixed martial arts, but at the same time reference humor more than any other race and gender pair. If you look at black women, they reference spirituality. They have over 10 of the 25 most common words in a black woman’s profile involve God, Jesus or religion.
So if you just look at what I call these ethnic autobiographies, you can see what is important to each ethnic group in their own words, and that’s been pretty powerful.
There is this longstanding belief among some portion of the population that gay people try to convert straight people to being homosexual. So we just did an analysis and we tried to find out what percentage of people, what percentage of gay men search for straight men. And it turns out that it’s well under 1% of men, of gay men, search for straight men.
So by simply putting that data out there, we can influence people’s perceptions and hopefully they’ll believe, that people who hold that belief that it’s the mission of homosexuals to on mass go and convert people, maybe this will be just one more argument against that position and they will be a little bit more open-minded and say, oh it turns out that when you actually observe people’s behavior, that’s not what they are trying to do.
Question: What role does age play in determining how a user approaches the site?
Sam Yagan: OkCupid has users from 18 to 80 on the site. And we get to observe all of their actions. We get to watch how they use the site, how they interact with other people. And what we’ve found is there’s a tremendous difference across the ages, in particular those who grew up with the Web versus those who didn’t.
People who are older have very different usage patterns on the site. They are less likely to use it to kind of hang out on the site. Less likely to interact with people that aren’t explicitly in dating context. Younger people will, again, have that bar-like experience. So they’re come, they’ll message people, they might even message people that are the same gender as them even if they’re heterosexual. The might message someone who is really far away just to strike up a conversation.
We’ve also done a bunch of research on... one topic we’ve done a lot of research on is race and ethnicity and what is the impact on race and ethnicity on dating. And we have found some tremendous differences according to age. In particular, we looked at for each age bucket, do people that age tend to send messages to only to people of one race or to people of multiple races? And what we found is that as you age, the more likely you are to just send messages of your ethnicity.
So if you are in your 50s and 60s and you’re white, you’re almost only sending to other white people. If you’re in your 50s and your 60s and you’re hispanic, you’re almost only sending messages to other Hispanics. If you look at people in their 20s and early 30s, it’s the exact opposite. It the minority of people who are sending messages just to their own race. And in fact, most people, if you’re white, you’re sending messages to whites and blacks. If you’re black, you’re sending messages to hispanics and Asians. And you’re seeing a much broader context and a much broader approach to dating as you get younger.
So I think, I think in general, the usage habits are reflective of people’s idiosyncrasies and people’s stereotypes. I think it’s no surprise that the younger people are more progressive, more open-minded, more... sort of more color blind, if you will. And people who are older are more set in their ways. They grew up in the '60s and '70s and are you know, still remember some of the, whether it’s Jim Crow or other sort of racial issues that we’ve had in this country.
So when it comes to actual usage of the site, yeah, it’s definitely the case that the older you get the more focused you are on marriage and in most cases. And the younger you are, you just want to meet people. And so that may also impact how people use the site.
Question: What statistics and trends should online daters be aware of?
Sam Yagan: We did some research that showed that the very first word of your message that you send a girl—when we looked at men sending messages to women—the very first word can have a tremendous... can have a very accurate prediction of whether you’re going to get a reply.
If you just say, “Hi.” You’re gonna do... you’re much less likely to get a reply than if you say, “Howdy,” for example. That one simple word choice can drive how that person perceives your entire message and is going to impact the success you have in online dating.
There are all kinds of gems that we’ve managed to dig up. Some of them are somewhat obvious, but when you put a number to them, it makes them more interesting. So for example, for – any woman who has ever gone out to a bar knows that what you wear impacts whether guys will come and talk to you. and in particular, how low-cut your shirt is, is a very important driver of interest. So that’s not a surprise. But what we were able to do is to actually quantify the impact of showing some cleavage in an online dating photo.
So it turns out that you do get more messages if you have a more revealing photo. But we found that was actually more insightful was that the cleavage advantage, as I call it, actually increases with age. So when you’re 18 years old, if you have a photo that’s more revealing, you’re going to get about 24% more interest than a non-revealing photo. By the time you turn 32 that advantage increases to 79%. So that impact that everybody knows exists, you might not have realized actually changes with time and increases with age.
It turns out there are a bunch of things you can do to make your profile pictures better. Don’t use flash; we learned that if you use flash, it adds seven years of age. So a 28-year old using flash has the same attractiveness as a 35-year-old who doesn’t use flash. Right? So we have some insights that are a little bit more trivial, if you will, and don’t have the social impact, but some do.
There are similar effects for men. One thing... we did some research hoping—I don’t have very good abs—we did some research hoping that we would finally convince men that showing your abs in a picture was not the right thing to do. Well unfortunately for me, the data turned out to show that if you show your abs in a photo and you’re male, you get a much higher response rate.
Now as we did some digging and we did some thinking about this, it turns out that only men with nice abs show their abs, and them men with flabby abs, like me, don’t show their abs. So we generalize that conclusion to say: definitely show your best assets and put your best foot forward. So there are all kinds of gems that we found. Some of the more simple to explain, you know, like that, some of them are more complicated.
So what do you do if you don’t have great abs and maybe you don’t have cleavage and you’re just a guy sitting there trying to get a girl to write you back? One think that we’ve found is, to not compliment the woman’s physical features when writing a message. So if you use the words, "sexy" or "cute" or "beautiful" in a message, you’re going to get about a 30% worse response rate than if you talk about interests that she has in her profile. So if you use words like, "Oh it’s fascinating that you have this interest" or if you talk about a band that she likes or something that’s actually written about in her profile. You’re going to do twice as well as if you’re someone who is focusing on her physical looks.
Question: Given your familiarity with the data, what should people keep in mind when building their profile?
Sam Yagan: ‘When you’re thinking about building your own online dating profile, especially on OkCupid, you should go through the same steps you’re thinking about when you’re going out to meet someone new. You want to put your best foot forward. So there are a couple of things that we really recommend. And I think about it in two categories. One is your photos and one is the text on your actual profile.
So on the photos we’ve learned a bunch of things. We’ve learned that you should be doing something interesting. We’ve learned that if you are a man, you shouldn’t look straight into the camera because that’s intimidating to women. If you are a woman, you should be looking into the camera because men don’t want to imagine you looking at some other guy. They want you looking straight at them. So we’ve learned that if you take a photo in your bathroom or a photo taken with your cell phone, those have a more authentic, more intimate appeal and those actually do very, very well. So we’ve learned a bunch of things on the photo side. I already told you about the flash example.
And then on the text side, what we’ve learned is, grammar matters. If you use poor grammar that is the same thing as having bad breath or body odor when you go to a bar. Right? It puts a very unorganized and it puts forth the impression that you don’t care. You need to be funny. People value humor a lot. You need to be not... don’t share all your problems with people. So don’t talk about all your previous breakups and why you’re going broke and how you still live at home with your mom. Those aren’t thing that are, again, put your best foot forward.
So we’ve learned a bunch of things when you send a message to people, keep those message short. Imagine walking up to a girl in a bar and going into a four-minute speech about how great you are. No one wants to hear that. Your goal in an online dating profile and in your first message to somebody is to strike up a conversation. Ask a question. Put forth a challenge. Ask someone, “What are your favorite restaurants in New York?” Let people... give people a little hook that they can grab onto and make it easy for someone to send you a message back.
Question: What would you say to someone who’s having trouble succeeding at dating online?
Sam Yagan: The first thing we’d suggest is, read the blog, look at the tips that we’ve got. We’ve covered what the best profile photos are; we’ve covered how to send a message; we’ve covered a lot... it’s sort of our best way of giving a dating advice blog. It’s not really our brand to tell you how to date, it’s not really what we’re here to do, but we think that using the quantitative research that we have can help you.
I think the second thing to do it to really invest in your profile. So what we’ve found is that if you actually, you know, take the time to write a very careful profile, think about who am I really and how do I get my best foot across? How do I put my best foot forward. What are my hobbies? Do I write about them? Do I write about them in an engaging way? Put as much effort into your online dating profile, into your OKCupid profile, as you would a conversation with somebody that you’re having in a bar that you’re trying to impress.
So it is a little bit of a marketing game, but it’s also a numbers game. So you should be reaching out to more people. Don’t be afraid about sending a message to somebody, even if you think you might be, you know, out of your league or not necessarily the best match for you. You have to go out there and you have to put those messages out there. You have to try. Don’t just cut and paste the same messages you sent to the last girl. Customize it. Think about "How do I actually get this specific person, guy or girl to write me back?" And if you put the effort in, you spend the time on the site, you answer a bunch of match questions, you find the people who are the best matches for you, I can almost guarantee you that if you have someone who is a 90% match or better on OKCupid, they’re gonna write you back because there are so few of those people out there that it’s just, you know you’re going to have a lot in common with them. You know, that even if you don’t find them attractive, even if they’re not going to be our soul mate, you know that you’re going to go and have an interesting time because you have so much in common. We have vetted them for you.
So invest in the matching algorithm, invest in your profile, and invest the time in reaching out to people and giving people a chance even if they don’t seem perfect for you at first glance.
Question: Is online dating changing us?
Sam Yagan: I think online dating will have an impact on the way people match up and ultimately marry and ultimately reproduce. I think... if you think about the pre-online dating world... in offline dating you’re limited in a bunch of ways. You’re limited, most importantly, by geography. Right? You’re only gonna interact with people that you’re close to. You’re also impacted by the sort of social effects. For example, you’re probably only hanging out with people of similar socioeconomic class, you’re probably hanging out with people of... or maybe of similar religion if it’s at your church or your synagogue, you’re hanging out with people who would look like you and who are very much are like you.
You might be at a bar with someone and you might... there might be someone... you might be at a bar with your friends and you might see someone that’s very different from the kind of person that you typically date, and you might not go an approach that person because you’re worried about what your friends are going to think. You’re worried that that’s not the kind of person that you’re expected to date.
At OKCupid, or in any online environment, that goes away. A) Nobody knows who you’re messaging; B) You can easily message someone who is five miles away, who is 10 miles away; C) You can send a message to someone who doesn’t look like you, who doesn’t think like you, who is in different socioeconomic class because you’re not really... it’s a very safe environment. You’re just sending a message out there. Maybe you exchange messages. You’re still such a... you’re still not meeting in person and you still have that distance, that safety that you could feel okay experimenting with new types of people.
Question: What role will technology play in the future of dating?
Sam Yagan: First and foremost I think online dating is going to continue to become mainstream. And much like online shopping, just kind of drop the adjective, online, Amazon is now just shopping just like an offline retailer is. I think dating is going to have that same... is going to go that same way. So you’re not an online dater or an offline dater, you just use the web. You use technology to date just like you use technology to shop. So I think that distinction of online versus offline dating is going to go away.
I think inevitably, dating is going to become more mobile. The fact of the matter is that people are out and about when they want to date. If you’re out with friends, that’s a great time to meet new people. So we think that mobile is going to have a big impact, location-aware products and services are going to be out there helping people match up in more real time. But I also think that along with the mainstream... the mainstreamification of dating and the more mobility is going to make it an integral part of everyone’s life.
I’m not as bullish on video mostly because, at least in our current state, women tend not to like videos of themselves nearly as much as men do. Women tend to be much more self-conscious about themselves on video. So if you look at some of the sites that do offer video profiles and other video features, they tend to be much more used by men than by women. So that maybe something that evolves over time as technology changes. But right now, I don’t think video is nearly as important to the future of dating as mobile is.
Recorded on November 4, 2010
Interviewed by Teddy Sherrill
Directed & Produced by Jonathan Fowler
