You might just be a step away from getting your perfect dating partner. Researchers have developed an algorithm for dating sites that recommends the right match on the basis of your contact history and online mating success.
Kang Zhao, assistant professor of management sciences in the Tippie College of Business, and University of Iowa doctoral student Xi Wang worked together to develop the algorithm similar to the model Netflix. The model recommends movies that users might like by tracking their viewing history.
In order to develop the program, the researchers collected the data given by an online dating website. They studied 475,000 initial contacts that involved 47,000 users in two U.S. cities over a 196-day span. Around 28,000 were men and 19,000 were women. Nearly 80 percent of the contacts were accounted to men.
Just 25 percent of the initial contacts reverted to the researchers. To gather more people, Zhao developed a model that combined two factors to recommend contacts: client's tastes, determined by the type of people the client has contacted; and attractiveness/unattractiveness, determined by how many of those contacts are returned and how many are not, the researchers stated in the press release.
Zhao explained that this particular combination would predict better partners for the users based on the information they put in their profile. "Your actions reflect your taste and attractiveness in a way that could be more accurate than what you include in your profile," Zhao said. "The model also considers the match of both taste and attractiveness when recommending dating partners. Those who match both a service user's taste and attractiveness are more likely to be recommended than those who may only ignite unilateral interests."
