ONLINE dating would be more successful if sites used software similar to that helping users choose books and movies, instead of software designed to find the secret formula to love, University of Iowa researchers have found.
The university said the research team – led by Tippie College of Business management sciences assistant professor Kang Zhao – had recently developed an algorithm for dating sites that used one’s contact history to recommend more compatible partners. Websites like Netflix and Amazon recommend movies users might like by tracking their viewing history.
Zhao’s team analysed 475000 initial contacts on a popular dating site involving 47000 users in two US cities over 196 days.
“The team then developed a model that combined two factors to recommend contacts: a client’s tastes, determined by the types of people the client had contacted; and attractiveness, determined by how many of those contacts were returned and how many were not,” the university said.
“Your actions reflect your taste and attractiveness in a way that could be more accurate than what you include in your profile,” Zhao said. “Since it doesn’t rely on profile information it can also be used by other online services.”