Why Data Science Says Most People Get Dating Completely Wrong

Data science, with help from machine learning models, reveals that identifying desirable romantic partners is easy. But predicting good romantic partners who will provide happiness is hard. 

Which is to say that height, wealth, beauty and a few other variables are utterly predictable. But neither AI nor any other aspect of relationship science can accurately determine what will actually make people happy with each other over time. 

Seth Stephens-Davidowitz reports in Wired:

Can 85 of the world’s most renowned scientists, combining data from 43 studies, mining hundreds of variables collected from more than 10,000, and utilizing state-of-the-art machine learning models—help people pick better romantic partners? No. The most important finding in the field of relationship science, thanks to Big Data, is this: Desired romantic partners are easy to predict with data. Good romantic partners are difficult to predict with data. And that suggests that many are dating wrong. In the dating market, people compete ferociously for mates with qualities that do not increase one’s chances of romantic happiness.WHOM SHOULD YOU Marry ? 

This may be the most consequential decision of a person’s life. The billionaire investor Warren Buffett certainly thinks so. He calls whom you marry “the most important decision that you make.” 

And yet people have rarely turned to science for help with this all-important decision. Truth be told, science has had little help to offer. Scholars of relationship science have been trying to find answers. But it has proven difficult and expensive to recruit large samples of couples. The studies in this field tended to rely on tiny samples, and different studies often showed conflicting results. In 2007, the distinguished scholar Harry Reis of the University of Rochester compared the field of relationship science to an adolescent: “sprawling, at times unruly, and perhaps more mysterious than we might wish.” 

But a few years ago, a young, energetic, uber-curious, and brilliant scientist, Samantha Joel, aimed to change that. Joel, like so many in her field, was interested in what predicts successful relationships. But she had a noticeably different approach from others. Joel did not merely recruit a new, tiny sample of couples. Instead, she joined together data from other, already-existing studies. Joel reasoned that, if she could merge data from the existing small studies, she could have a large dataset—and have enough data to reliably find what predicts relationship success and what does not. 

Joel’s plan worked. She recruited a large number of scientists who had collected data on relationships—her team ended up including 85 other scientists—and was able to build a dataset of 11,196 heterosexual couples. 

The size of the dataset was impressive. So was the information contained in it. For each couple, Joel and her team of researchers had measures of how happy each partner reported being in their relationship. And they had data on just about anything you could think to measure about the two people in that relationship.

The researchers had data on:

• demographics (e.g., age, education, income, and race)
• physical appearance (e.g., How attractive did other people rate each partner?)
• sexual tastes (e.g., How frequently did each partner want sex? How freaky did they want that sex to be?)
• interests and hobbies
• mental and physical health
• values (e.g., their views on politics, relationships, and child-rearing)
• and much, much more

Further, Joel and her team didn’t just have more data than everybody else in the field. They had better statistical methods. Joel and some of the other researchers had mastered machine learning, a subset of artificial intelligence that allows contemporary scholars to detect subtle patterns in large mounds of data. One might call Joel’s project the AI Marriage, as it was among the first studies to utilize these advanced techniques to try to predict relationship happiness.

After building her team and collecting and analyzing the data, Joel was ready to present the results—results of perhaps the most exciting project in the history of relationship science.

 

Joel scheduled a talk in October 2019 at the University of Waterloo in Canada with the straightforward title: “Can we help people pick better romantic partners?”

So, can Samantha Joel—teaming up with 85 of the world’s most renowned scientists, combining data from 43 studies, mining hundreds of variables collected from more than 10,000, and utilizing state-of-the-art machine learning models—help people pick better romantic partners?

No.

The number one—and most surprising—lesson in the data, Samantha Joel told me in a Zoom interview, is “how unpredictable relationships seem to be.” Joel and her coauthors found that the demographics, preferences, and values of two people had surprisingly little power in predicting whether those two people were happy in a romantic relationship.

And there you have it, folks. Ask AI to figure out whether a set of two human beings can build a happy life together and it is just as clueless as the rest of us.

WELL … THAT sure seems like a letdown. Does data science really have nothing to offer us in picking a romantic partner, perhaps the most important decision that we will face in life?

Not quite. In truth, there are important lessons in Joel and her coauthors’ machine learning project, even if computers’ ability to predict romantic success is worse than many of us might have guessed.

For one, while Joel and her team found that the power of all the variables that they had collected to predict a couple’s happiness was surprisingly small, they did find a few variables in a mate that at least slightly increase the odds you will be happy with them. More important, the surprising difficulty in predicting romantic success has counterintuitive implications for how we should pick romantic partners.

Think about it. Many people certainly believe that many of the variables that Joel and her team studied are important in picking a romantic partner. They compete ferociously for partners with certain traits, assuming that these traits will make them happy. If, on average, as Joel and her coauthors found, many of the traits that are most competed for in the dating market do not correlate with romantic happiness, this suggests that many people are dating wrong.

This brings us to another age-old question that has also recently been attacked with revolutionary new data: How do people pick a romantic partner?

In the past few years, other teams of researchers have mined online dating sites, combing through large, new datasets on the traits and swipes of tens of thousands of single people to determine what predicts romantic desirability. The findings from the research on romantic desirability, unlike the research on romantic happiness, has been definitive. While data scientists have found that it is surprisingly difficult to detect the qualities in romantic partners that lead to happiness, data scientists have found it strikingly easy to detect the qualities that are catnip in the dating scene.

A recent study, in fact, found that not only is it possible to predict with great accuracy whether someone will swipe left or right on a particular person on an online dating site, it is even possible to predict, with remarkable accuracy, the time it will take for someone to swipe. (People tend to take longer to swipe for someone close to their threshold of dating acceptability.)

Another way to say all this: Good romantic partners are difficult to predict with data. Desired romantic partners are easy to predict with data. And that suggests that many of us are dating all wrong.

So, what traits make people desirable to others?

Well, the first truth about what people look for in romantic partners, like so many important truths about life, was expressed by a rock star before the scientists figured it out. As Adam Duritz of the Counting Crows told us in his 1993 masterpiece “Mr. Jones”: We are all looking for “something beautiful.” The conventional attractiveness of a mate is the number one predictor of how many messages someone gets, for both men and women. We are also looking for:

• someone tall (if a man)
• someone of a desired race (even though most never admit it)
• someone rich
• someone in an enforcement profession (like lawyer or firefighter) if a man
• someone with a sexy name (such as Jacob or Emma)
• and someone just like ourselves (people are 11.3 percent more likely to match with someone who shares their initials)

THE FASCINATING, IF sometimes disturbing, data from online dating sites tells us that single people predictably are drawn to certain qualities. But should they be drawn to these qualities? If you are like the average single dater—predictably clicking on people with the traits the scientists found are most desired—are you going about dating correctly? Or are you dating all wrong?

Recall, earlier I discussed the research of Samantha Joel and coauthors. Recall that they found that it was surprisingly difficult to predict whether a person was happy with a romantic partner based on a large list of traits. There is not a set of traits that guarantee romantic happiness or preclude romantic happiness. And no algorithm in the world can predict, with enormous accuracy, whether two people will end up happy together.

That said, there was some predictive power in some traits, some factors that do increase the odds at least somewhat that a person will be happy in their romantic relationship. I will now discuss what does predict romantic happiness—and how little it has to do with the qualities that people look for in a romantic partner.

Say there is a person, John, and he is partnered with Sally. You want to predict whether John is happy in the relationship. You are allowed to ask John and/or Sally any three questions about themselves and use this information to predict John’s relationship happiness.

What questions would you want to ask? What would you want to know about the two members of this couple?

According to my read of the research of Joel and her coauthors, as well as some other research in relationship science, the best three questions to figure out whether John is happy with Sally would have nothing to do with Sally; in fact, all would be related to John. The best questions to predict John’s happiness with Sally might look something like these:

• “John, were you satisfied with your life before you met Sally?”
• “John, were you free from depression before you met Sally?”
• “John, did you have a positive affect before you met Sally?”

Researchers have found that people who answered “yes” to questions such as these are significantly more likely to report being happy in their romantic relationship. In other words, a person who is happy outside their relationship is far more likely to be happy inside their relationship, as well.

Further—and this was quite striking—how a person answered questions about themselves was roughly four times more predictive of their relationship happiness than all the traits of their romantic partner combined.

Of course, the finding that one’s happiness outside of a relationship can have an enormous impact on one’s happiness inside that relationship is hardly a revolutionary idea. Consider this saying that was featured on Daily Inspirational Quotes: “Nobody can make you happy until you’re happy with yourself first.”

This is the type of quote that often makes cynical data geeks like myself roll our eyes. However, now, after reading the work of Joel and her coauthors, I have become convinced that this quote is largely true.

This relates to an important point about living a data-driven life. We data geeks may be most excited when we learn of a finding that goes against conventional wisdom or clichéd advice. This plays to our natural need to know something that the rest of the world doesn’t. But we data geeks must also accept when the data confirms conventional wisdom or clichéd advice. We must be willing to go wherever the data takes us, even if that is to findings like those featured on Daily Inspirational Quotes.

So, as discovered by both a team of 86 scientists and whoever writes Daily Inspirational Quotes, one’s own happiness outside a relationship is by far the biggest predictor of one’s happiness in a romantic relationship. But what else predicts romantic happiness beyond one’s own preexisting mental state? What qualities of a mate are predictive of romantic happiness? Let’s start with the qualities of one’s mate that are least predictive of romantic happiness.

Among more than 11,000 long-term couples, machine learning models found that the traits listed below, in a mate, were among the least predictive of happiness with that mate. Let’s call these traits the Irrelevant Eight, as partners appear about as likely to end up happy in their relationship when they pair off with people with any combo of these traits:

• Race/ethnicity
• Religious affiliation
• Height
• Occupation
• Physical attractiveness
• Previous marital status
• Sexual tastes
• Similarity to oneself

What should we make of this list, the Irrelevant Eight? I was immediately struck by an overlap between the list of irrelevant traits and another data-driven list discussed in this chapter.

Recall that I had previously discussed the qualities that make people most desirable as romantic partners, according to Big Data from online dating sites. It turns out that that list—the qualities that are most valued in the dating market, according to Big Data from online dating sites—almost perfectly overlaps with the list of traits in a partner that don’t correlate with long-term relationship happiness, according to the large dataset Joel and her coauthors analyzed.

Consider, say, conventional attractiveness. Beauty, you will recall, is the single most valued trait in the dating market; Hitsch, Hortaçsu, and Ariely found in their study of tens of thousands of single people on an online dating site that who receives messages and who has their messages responded to can, to a large degree, be explained by how conventionally attractive they are. But Joel and her coauthors found, in their study of more than 11,000 long-term couples, that the conventional attractiveness of one’s partner does not predict romantic happiness. Similarly, tall men, men with sexy occupations, and people of certain races are valued tremendously in the dating market. But ask thousands of long-term couples and there is no evidence that people who succeeded in pairing off with mates with these desired traits are any happier in their relationship.

If I had to sum up, in one sentence, the most important finding in the field of relationship science, thanks to these Big Data studies, it would be something like this (call it the First Law of Love): In the dating market, people compete ferociously for mates with qualities that do not increase one’s chances of romantic happiness.

Moreover, if I had to define the qualities that are highly desired even though they don’t lead to long-term romantic happiness, I would call many of them shiny qualities. Such qualities immediately grab our attention. Just about all of us are quickly drawn to the conventionally beautiful, for example. But these attention-grabbing, shiny qualities, the data suggests, make no difference to our long-term romantic happiness. The data suggests that single people are predictably tricked by shininess.