Economist Peter Backus put forward "The Girlfriend Equation" while working on his PhD - a probabilistic model attempting to estimate the likelihood of him finding a girlfriend. In this mini episode we explore the soundness of his model and also share some stories about how Linhda and Kyle met.
Data Skeptic
[MINI] The Girlfriend Equation
(upbeat music) - The Data Skeptic Podcast is a weekly show featuring conversations about skepticism, critical thinking, and data science. - Welcome to another episode of the Data Skeptic Podcast. I'm here with Linda as always for this mini episode. - Hello, I'm Linda. - Linda, I'm so excited because this episode kicks off a four-week mini series we're going to be doing all on the topic of love and data. - Woo, I love love. - I love data and love, so do you wanna expand yours maybe and include that other thing I threw in? - I'm just a normal, simple folk. (laughs) So I just love love. - All right, so yeah, I'm excited because there's gonna be another episode we're gonna do on a similar theme and I have two great guests lined up. One is the Senior Data Scientist from Plenty of Fish, which is an online dating website, and the other is an author who wrote a great book about her experiences trying to both participate in and manipulate the algorithms that are at work on those shows. So we're gonna do a four-week series here all about love and we're gonna kick it off with actually a user suggestion. Linda, you had a look at this, right? The girlfriend equation? - Kyle sent me an email where there was a link to a PDF that had some guy in England, a London, I believe. - That's right. - Try to do some math and calculate the probability that he could find a girlfriend by going out in London. - That's right, and what did you think of this overall? - So I only looked at it for five minutes or so and I never took a statistics class, but I thought it was not accurate. The odds were too low. I'm gonna ask you why you think they were too low. Before we get into it, let's walk through the process. Now, this is essentially an homage to the Drake equation. Do you know what that is? - Nope. - It's this really cool idea that Frank Drake put forward to try and estimate the number of possible intelligent species that might be out in the rest of the universe trying to communicate with us. So it's actually worthy of its own episode or maybe a long interview at some point. So we'll just skip that for now and say that he tries to follow the same logical process. So for example, he starts with N, which is the total population of the UK. Do you think that's a reasonable place to start? - Yeah, but you probably wanna narrow down population of London 'cause he's just in London. - We'll get there. The first term he multiplies by is the percentage of what are they called, great Britners or UKers? What's the term? - UK. - What's the term for one from that place? - Citizens. - All right, citizen and service to the queen is 51% female. So he cuts that number down. It's about 60 million to half of that. Then he cuts down that about 13% of that live in London. So does that seem reasonable so far? - Yeah, that's fine. - About 20% of that are women living in London between the ages of 24 and 34. 'Cause at the time of writing this, I think he was like 30 or so. So he thought that was the reasonable age range. Do you have a problem with that? - That's suspicious, but let's assume he's correct. - That's the reason. I mean, you know, there are people in happy relationships that aren't necessarily close in age, but generally speaking, he gave a good range. Then he went on to say he presumed he would only end up being matched with someone who has a college degree, of which 26% of people meeting the previous criteria are. How do you feel about that, scaler? - 26% of people from the ages of what age? - A female Londoner's between 24 and 34. Basically, one in four such women have a college degree. - Really? - Yeah. - What seems low? - It seems low, but it might be really-- - And especially UK, their tuition is incredibly cheap. - Oh yeah? - Oh yeah. It's like a little tax or something each year or semester. I've asked them, well, when I study abroad in England, this is a long time ago. That would be surprising. - Yeah, that might be a little low, but I'm gonna trust him on that just for now and say maybe he got that right. Even, let's say you double it, 50% of Londoner females, 24 to 34 have a college degree. That's just a factor of two. So more or less, I'll give him that one. His next parameter is he multiplies then by the percentage of people whom he would be attracted to, which he gives us 5% or 1 in 20. Also, I mean, you and I aren't him. We don't know what he's thinking, but that sounds reasonable, right? - No, I think that's too low. - Too low. - This is of the people in his age range. - A good age range and college degree. So also sort of in his social status. - Not true. He would probably find more than 50% percent of women. - More than 50? Come on. - Yeah. - That has no taste at all. He just likes every other woman. - I don't think it takes that much. - How come I had to chase you for so long? - Wow, that's a separate story. - All right, we maybe get to that one. - But anyway, that's just two, 5%. You're not gonna date anyone. - So all that gets him down to 10,510 suitable matches for him. He then says, and this is where I think his work is most dubious, he says, "Well, 5% of those will be attracted back to me. 50% will be single and 10% will probably get along with me and me with them," which gets him down to like 26 possible candidates. - Yeah, now that's definitely too low. He thinks only 5% of those women would be attracted to him. - Right. - Okay, I don't know what this person looks like. So I can't judge. He's either the average, below average or above average. So 5% to me sounds below average. - You think so? - Because I mean, most of attraction is personality. So is he saying he doesn't have a good personality to attract someone? What is he saying? It's so odd. So my main objection to that is not necessarily his value, but that he earlier multiplied by 5% of women he would be attracted to. And then also tacked on 5% who would be attracted back to him, which I don't think is totally independent. - So why do you not think they're independent or you do think they're independent? - I do not. I think that given that person A is attracted to person B, that it's more likely that person B will also be attracted to person A. - I don't know. This is a great question for the makers of that app where you swipe left and right. - Tinder? - Tinder. How many people, what's the percentage of people who swipe left and right on each other? - Well, they're here in LA. Maybe I can get an engineer from Tinder to come on as well. - I would like to hear what they have to say. - But he also said, I objected to this, that only 10% of all those potential matches are those he'd get along with. And that's again on top of only 5%, he'll be attracted to and 5% will be attracted back to him. So that's kind of like saying out of 100 people, there's only 2.5 that would be mutually attracted. - So quick editors note here, that's actually not right. It's 0.25%, so a quarter of a person or one in 400. - And that doesn't seem right to me. I think that it's not independent. And then given that we already say we have two people mutually attracted, why would they only have a 1% and 10% chance of getting along with each other? What do you think? - I mean, I don't know where these numbers are coming from because whether or not you get along, some people, it's, I mean, you just have to be able to change and you have to be adaptable. That's, I mean, that's part of being in a relationship. And so it just seems odd that he goes, well, I'll just date 10 women and one of 10 will stick. As if it's, he's just, it's almost like he's saying it's not random. - True, yeah, yeah. - 'Cause I think if you went on a date and they liked each other, they're more likely to try even if it didn't work. - Ah, good point. Maybe he's figured that into his 10% that even given effort, only 1 in 10 would work out. - I mean, if only 1 in 10 works out, I think there's something wrong with you. Like, I don't think this guy, he doesn't sound very likable. - So in fairness, I don't know personally the author of all this is a economist named Peter Bacchus. And also overall, even though we're criticizing his work, I don't think he put this out there like it was the most rigorous proof. I think this was mostly for fun and to get some journalists to write about his other projects and stuff, which is fine. But I think my primary criticism is around how he doesn't consider the conditional probabilities and variables. He treats everything as independent. But it sounds like you take most issue with the scalar values he chose. - I don't know what you mean by scalar, the numbers? - Yeah, the numbers. - Yeah, I just don't know where they're coming from. - In some cases, I assume he went to the census where he knew 51%. - Yeah, but the like someone, like someone back, the chances he'll work out. I mean, what's his history of, you know, what's his statistic? - Well, see if we can get him on the show, but I agree. I think that given a Londoner, given the age group, given they have a college degree, given that he's attracted to them, all those things put together, it's unlikely that it's only 5% would be attracted back and 10% of those would get along with him. So I think he's being a bit pessimistic in all this. What do you think his odds probably really are? - Of meeting someone? - Yeah. - Well, first of all, he has to go out of his apartment, probably. - Assume he does. - I guess we'll assume the condition is meeting someone is, he asks someone on a date and they say yes. Is that what we're saying? - Well, I don't know, I asked you on a date and you said no, and now we're married, so. - Yeah, well, that's separate. - Okay. - So we're saying what are the odds that he will ask someone out and they will say yes. First of all, he's gonna ask someone out based, he's not just gonna ask anyone. So he's already self-filtering. - That's true. Maybe even filtering strategically. Like he's, even if he met like, you know, some, I don't know, top-ranked, certain, you know, senior scientist, he might not approach her 'cause he's intimidated. He knows she can land a better fish or something like that. - Yeah, I mean, he's not, if he sees someone married or has a partner, he's probably gonna be like, oh, I guess I won't ask him out. So, I mean, he's already setting up his chances of success by filtering that. And then, you know, some people are open-minded and will not and will say yes, even if they don't like you. - Oh, yeah? - As in, they just don't know you. So they're like, well, I'll go on one date. - Well, I am hungry and broke. So I guess this is the way you get me. - No, they'll just agree to like have a conversation with them. Hey, let's go out and have a conversation. 'Cause I mean, even if you're like, meet them in a bar on the sidewalk, you're like, I don't really know what I think about you. I think people will be open-minded and say yes. - So, yeah, I think-- - For the first date. - His odds are a little better than he lets on in his paper, especially living in a densely-populated area like London. - Oh, yeah. I mean, imagine a subway during rush hour. - So if we wanted to kind of follow his odds, what do you think the likelihood was, you know, in hindsight, that you and I got married? - At what point? Are you assessing the odds? - The vowel, I guess? I don't know. - I mean, if we're on the wedding day, the odds are pretty high that we will say yes and get married as we plan the wedding. - Right. Well, maybe we should back up and add some color and just talk about our meeting story. - Meeting? - Yeah. - How we met? - Yeah. - Okay. - What's your perspective on it? - Well, for viewers, you don't know, Kyle and I met at work. - Right. - Oh, yeah, we met at the company Christmas party, and Kyle was not dancing. (laughs) So, and I did not recognize them, so I thought I would ask him a question. - I would never met before. - We had never met. And I was like, "Oh, do you work here?" Because there are people who worked there at the party and people who did not work at our place of business. So, he was like, "Oh, yeah, I work there." I was like, "Are you lying?" (laughs) It's what I thought. I was like, "Huh?" 'Cause our workplace was about 120 people at the time. So, I wasn't sure. 'Cause you see, you could memorize 100 faces. And I had not memorized his face. So, I was like, "I don't know if you work there." So, that's how I met. - Yep. And then seven days later, wedding bills. - Nope. Would you like to tell the rest? - We didn't really start dating at first. We got to be very good friends, best friends even. - Yeah, we were good friends for about eight months. Or eventually through eight months, we became very good friends. - Yeah. And then what happened? - Well, I think this is your part to tell. (laughs) I think it sounds better coming from you. - Well, I asked you if you wanted to go out and you said no. - That's exactly what happened. - So, down to probability zero for me. - So, just to backtrack, Kyle decides one day we were walking away from a bar, which a lot of co-workers, we went to like happy hour or something after work. And Kyle was like really excited and he seemed like full of energy and he looks at me and he goes, I can't remember exact words, but I think he said something like, "Well, you go out with me like on a date." Or, "I think it would be a good idea if we went out on a date." Or something like that. And I was so caught up guard. And I was like, "What?" No. (laughs) And then Kyle had to pick up his face. And I was like, "Oh, okay." And then you said something about how you didn't want to be weird. And so we continued, we were able to continue being friends. And then several months later, I developed a crush on him. And I think when I had declined him at first, I said something like, "Well, if my feelings change, I'll let you know." And so I had to work with the nerve to tell him one day at work. I was like, "Well, you know, maybe we can go on a date or something." I can't remember my words. Maybe you remember better. - I just remember the unprofessional nature of it because what I did was not on company time. (laughs) - Yeah, so then I was like, "Yeah, maybe we should go on a date." And we did, after that, Kyle was still willing to go on a date with me after that. - So thank goodness for that love potion number nine. I slipped you the one day. - Well, I always tell people it's not love at first sight. (laughs) Or even second, third, fourth, fifth, or however we have to hang out with them. You do not know who you're gonna marry sometimes. - So maybe our associate through discussion, Peter Bakas, who wrote the original girlfriend equation, will or perhaps has 'cause this is an older paper, but experienced similar fortunate circumstances for himself. - Yeah, you know what? Maybe he already knew the person that he was gonna marry later. - Oh, so he strategically turned down all of these Londonite females. - Yeah, I mean, when you wanna talk to him, to get a feel for what his personality was or be like, "Who did you end up marrying? Are you married now? And do you think your statistics are accurate?" Like, "Yeah, maybe I can get him on the show. We'll see what happens." 'Cause if he's married now, I don't think his odds were right. (laughs) - Well, that's an interesting discussion that's essentially the confirmation bias, but that will be a topic for another day. - I would like to hear this guy. - Well, thanks for joining me, Linda. - Thank you for joining me. (upbeat music) (upbeat music) You