"I brought over a bunch of people who I thought could help solve one of the most difficult problems out there, which is how to model human attraction," she says.
A key recruit was Amarnath Thombre, a soft-spoken engineer from Pune, India.
"When you give it stimuli, it forms neural pathways," he says. It's learning as you go." The same principles are powering the recommendation engines at popular sites around the web.
Amazon uses similar technology to recommend new products for people to buy, Pandora learns from likes and dislikes to customise its internet radio stations, and Netflix famously offered $1m to anyone who could improve the effectiveness of its algorithm by 10 per cent.
On a hazy Monday in June, I came to meet Mandy Ginsberg, the president of US, the world's largest online dating site.