While it is true that some people successfully find good, lasting relationships on online dating sites, it is also true that many end up frustrated and disappointed.
Rochelle, a Match.com user from Irvine, Calif., says she has found a troubling pattern with the men she has met online: they aren't telling the truth, she says.
“I've noticed that a lot of men are lying about their age,” Rochelle writes in a ConsumerAffairs post. “I set my age limit at 45 and about a quarter of the men contacting me are no way even close to 45. Try 55-65! Also, a lot of men use very old pics. Sorry, but any picture older than 2-3 years is irrelevant.”
Disconnect
Researchers at the University of Iowa (UI) think Rochelle might unknowingly be onto something. Not that people are dishonest when they use an online dating site but there's a disconnect -- what they say doesn't really match what they truly want.
Kang Zhao, assistant professor of management sciences in UI's College of Business, and UI doctoral student Xi Wang are part of a team that has developed an algorithm for dating sites that uses a person's contact history to recommend partners with whom they may be more romantically compatible.
Netflix model
It's similar to the model Netflix uses to recommend movies users might like by tracking their viewing history. For example, you might not pick a particular movie to watch but Nexflix, analyzing the movies you've watched in the past, says “hey, you might like this one.” In a way, it's putting the computer in computer dating.
Dating sites are taking notice. Zhao says he's had preliminary discussions with two dating services who have expressed interest in learning more about the model. Since it doesn't rely on profile information, Zhao says it can also be used by other online services that match people, such as a job recruiting or college admissions.
The system was developed with the help of a popular commercial online dating company whose identity is being kept confidential. The research team looked at 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 showed that just 25% of those initial contacts were actually reciprocated. To improve that results, Zhao's team developed a model combining two factors to recommend contacts: a client's tastes, determined by the types of people the client has contacted; and attractiveness/unattractiveness, determined by how many of those contacts are returned and how many are not.
Better predictor
Zhao believes those two factors, 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're really interested in. And from Rochelle's observation, they could also be intentionally misleading.
Zhao goes a step further, suggesting the average user of an online dating site might not really know themselves well enough to know their own tastes in the opposite sex. A man who says on his profile that he likes tall women may in fact be approaching mostly short women, even though the dating website will continue to recommend tall women.
"Your actions reflect your taste and attractiveness in a way that could be more accurate than what you include in your profile," Zhao says.
Another way of saying, actions speak louder than words. Zhao says that eventually, the algorithm will notice that while a client says he likes tall women, he keeps asking out short women, and will change its recommendations to start suggesting that he contact short women.
If it works for movies, it should work for dates, Zhao says.