I think it's unrealistic to say that we can look through millions of people and find the one person who is best for you, but what we can do is of these millions of people, here are the top 100 that might be the best for you to look through and here are the bottom 1,000, or 100,000, that you shouldn't waste your time with.
That level of granularity, sort of picking the most likely and the least likely, that's something that an algorithm can do really well.
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. 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 wants to experiment with facial recognition technology via 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.
"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.
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.We fundamentally believe that the way to predict compatibility is to rely on data and and to allow people to customize an algorithm that would take into account their preferences and their lifestyle to cull through the millions of profiles we had to find the people that were most compatible with them.”"I would say the larger the pool you have to select from, the more likely you are to find the most compatible person for you, if you have the right algorithms working on your behalf.