Communications of the ACM
Love Connection
A new algorithm for dating sites uses a person's contact history to make better recommendations of compatible partners.
Credit: luna47/istockphoto.com
University of Iowa researchers have developed an algorithm for dating sites that uses a person's contact history to recommend more compatible partners.
The researchers examined data from 475,000 initial contacts involving 47,000 users in two U.S. cities over a 196-day span. Of the users, 28,000 were men and 19,000 were women, and men made 80 percent of the initial contacts.
The data suggests only about 25 percent of those initial contacts were actually reciprocated, according to University of Iowa professor Kang Zhao. To improve that rate, the researchers developed a model that combines a client's tastes, determined by the types of people the client has contacted, with the user's attractiveness determined by how many of those contacts are returned and how many are not.
Zhao says the combinations of taste and attractiveness do a better job of predicting successful connections than relying on information that clients enter into their profile, because what people put in their profile may not always be what they are really interested in.
Although the data the researchers studied suggests the existing model leads to a return rate of about 25 percent, a recommender model could improve such returns by 44 percent, Zhao notes.
From Iowa Now
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found