More couples are finding love on online dating sites, and it makes sense: coupled with the convenience of finding a mate in the comfort of your own home and schedule, these platforms are getting smarter. Way smarter.
Dating platforms are collecting an enormous amount of data about how people look for a partner and what they say they want, especially compared to who they actually want and pursue.
And it's only going to get more sophisticated from here — in fact, Match.com has its sights set on using facial recognition technology in the future, which could allow users to highlight the features they are most attracted to so the company can provide them with matches most in tune with their preferences.
See also: 10 Creative Social Media Resumes To Learn From
To learn more about how some of the biggest dating sites — and platforms with a niche dating focus — are matching up people worldwide, Mashable spoke with the teams behind some of the sophisticated, high-tech algorithms out there. Here's a look at how your personal data is used to find the one.
With more than 1.9 million paid subscribers, Match.com's data pool has been increasing for the past 18 years. It is the largest dating site in the world and according to the company, has brought more people together than any of the platforms on the web.
"We keep refining our algorithms, which takes so much into account when matching people up," Amarnath Thombre, president of Match.com told Mashable.
See also: 'Data, A Love Story:' How One Woman Found the Secret to Online Dating
In addition to asking each member anywhere from 15 to 100 questions, the company weeds through the essays they fill out about what they want and gives points to each user based on each parameter in the system — from education and the vocabulary they use, to hair color and religion. People with a similar amount of points, which are weighted on certain areas, have a greater chance of being compatible.
"We also take historical data into account, as well as distance — people in Dallas are more inclined to date someone far away than someone in Manhattan, who might not want to date someone who lives in Queens," Thombre said.
The site also looks at what people say they want in a partner and who they are actually pursuing on the site.
"People have a check list of what they want, but if you look at who they are talking to, they break their own rules. They might list 'money' as an important quality in a partner, but then we see them messaging all the artists and guitar players," he said.
Match.com also sends matches based on this behavior: "Similar to Netflix or Amazon, we know that if you liked one person, you might like another that is similar," Thombre said. "But of course it is different here. Carlito's Way may be your favorite movie, but in this case, he has to like you back for it to be a match."
Moving forward, Thombre says Match.com wants to experiment with facial recognition technology via the site.
"We have done a lot of interesting work on facial recognition and think there is a lot of potential for online dating," Thombre said. "People are drawn to certain facial features and how a person looks, so with all the technology out there today, it's something we would really like to get involved with."
HowAboutWe has embraced an algorithm different from other dating sites because its focus is less on online interactions and more on helping people get offline and on actual dates.
"Our deepest insight is that it's difficult to predict chemistry online," said Aaron Schildkrout, HowAboutWe co-founder and co-CEO. "That's why our ultimate focus is on actual dates. Get offline — that's where the chemistry happens."
Behind the scenes, HowAboutWe says it "builds quickly and tests everything" on the site as a part of an effort to pair couples up based on how they like to date, from having picnics in the park to visiting amusement parks.
"We actually launched HowAboutWe with a robust algorithm, which we subsequently got rid of after realizing that we had put the cart far, far before the horse," Schildkrout said. "It’s only after you achieve significant liquidity in a market that you can build a useful algorithm."
As the user interacts with the site, the company gets a better sense for their unique preferences and the recommendation algorithms rely less on an ‘average person weighting’ and more on what is inferred from their behavior.
"Over time, we can pick up on patterns such as, ‘this user only messages people who have children and like to exercise,’ and make recommendations accordingly," he said.
It factors a few key patterns from general user behavior on the site too, such as how the average person is more likely to message someone of a similar or higher education level. But characteristics such as political affiliation are much less important for HowAboutWe users.
Coffee Meets Bagel is one of the younger dating platforms on the market. The free service curates user data — including Facebook profile pictures and preferences — as well as behavior on the site to "like" or "pass" on a person to make match predictions. The site delivers one match (called a "Bagel") to users every day at noon.
Through research, the company discovered that in addition to religious background and education, social context is ranked high for many daters.
"We found that having at least one mutual friend amplified the probability of two people connecting by 37%," said Coffee Meets Bagel CEO Arum Kang. "We also found that women are more sensitive to ethnicity and social context (mutual friends), so our algorithm takes all of that into consideration."
"People talk a lot about big data these days, but the biggest area of opportunity is incorporating social elements into that through user inputs such as friend recommendations," Kang said.
With this in mind, the site has a feature called GIVE where members can recommend Bagels they think are good for their friends.
"The mutual connection rate on the GIVE Bagels are 30% higher than our own algorithm's," she added. "Ultimately, we believe, like Facebook does, that our members do a better job than algorithms at regulating human interactions."
Image: iStockphoto, Djahan