A BBC article looks at the ways online dating can utilise big data, the processes companies currently use to match their customers, and the limits of these systems.
- Do you like horror movies?
- Have you ever travelled around another country alone?
- Wouldn’t it be fun to chuck it all and go live on a sailboat?
These are the questions Christian Rudder, co-founder of OKk
Paul Rubens’ article looks at the dating sites, like OkCupid, who collect masses of data and information about their customers, to better tailor matches to them.
Rudder says the problem with such information is that people lie – whether intentionally or not.
And so dating companies are using habits, rather than answers to questions, to amass information about the user, in order to better recommend matches to them – like Netflix’s recommendation systems.
Zoosk’s Behavioural Matchmaking uses this approach – building a picture and recommending based on a user’s activity and behaviour on the site.
It also references the new matchmaking system from Iowa University’s Dr Kang Zhao and his team, who devised an algorithm that recommends partners by assessing the user’s tastes and their own attractiveness to other singles, by the responses they receive.
However, as Christian Rudder says, these systems are, at the end of the day, striving to get as close as possible to an unattainable formula:
“Two people may have exactly the same iTunes history, but if one doesn’t like the other’s clothes or the way they look then there simply won’t be any future in that relationship.”
Read it here.