Researchers at the University of Iowa say they may have found the secret to finding the right mate online: Pair people according to their past interests and who they have contacted in the past, rather than on who they say they’re interested in.
The algorithm developed by Kang Zhao, an assistant professor of management sciences in the Tippie College of Business, and doctoral student Xi Wang, uses a person’s contact history to recommend partners. It’s similar to the model Netflix uses to recommend movies to users by tracking their viewing history, according to the researchers.
Using data provided by a popular online dating site, the researchers looked at 475,000 initial contacts involving 47,000 users in two U.S. cities over 196 days. About 28,000 of the users were men and 19,000 were women, the researchers noted, reporting that men made 80 percent of the initial contacts.
The data shows that only about 25 percent of those initial contacts were reciprocated, according to Zhao.
To improve that rate, the researchers developed a model that combines two factors to recommend contacts: A user’s tastes, determined by the types of people he or she has contacted; and attractiveness/unattractiveness, determined by how many of those contacts are returned and how many are not.
The combination of taste and attractiveness do a better job of predicting successful connections than relying on information that users enter into their profiles, according to Zhao.
That’s because what people put in their profiles may not always be what they’re really interested in, he said. They could be intentionally misleading, or people may not know themselves well enough to know their own tastes in the opposite sex, he theorized.
For example, 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 said.
The algorithm eventually notices that while a client says he likes tall women, he keeps contacting short women, and will change its recommendations to him accordingly, Zhao explained.
“In our model, users with similar taste and attractiveness will have higher similarity scores than those who only share common taste or attractiveness,” Zhao says. “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.”
When the researchers looked at the users’ profile information, Zhao says they found that their model performs best for males with “athletic” body types connecting with females with “athletic” or “fit” body types, and for females who indicate that they “want many kids.”
The model also works best for users who upload more photos of themselves, the researchers said.
While the data suggests the existing model leads to a return rate of about 25 percent, Zhao claims a recommender model could improve returns by 44 percent.
Zhao reports he’s been contacted by two dating services interested in learning more about the model. Since it doesn’t rely on profile information, he notes it can also be used by other online services that match people, such as a job recruiting or college admissions.
Source: University of Iowa