Iowa Researchers Come Up With a New Formula to Improve Online Dating Success

University of Iowa researchers have created a formula to facilitate the search for potential dating partners in the online world.

Researchers have created an algorithm for online dating sites that recommends potential dating partners based on their past interests and online mating success rates rather than their personal choices.

Kang Zhao, assistant professor of management sciences in the Tippie College of Business, and UI doctoral student Xi Wang, said that this model is similar to Netflix that recommends choices to users based on their viewing history.

Zhao said that since the model doesn't depend on profile information, it can be used on other sites focusing on job recruitments and college admissions.

For the study, Zhao examined 475,000 initial contacts of 47,000 users in two U.S. cities over a 196-day span. Out of the users, 28,000 were men and 19,000 were women. He found that 80 percent of the initial contacts were made by men and only 25 percent of all the initial contacts received a response.

In an attempt to improve that rate, Zhao's team developed a model that combines two factors: tastes (type of people previously contacted) and attractiveness (how many of the contacts were returned and how many were not). The renewed model improved the call back rate from 25 percent to 44 percent.

This model differs from existing models that rely on information that clients enter into their profile as the information does not reflect what they're actually interested in.

"Your actions reflect your taste and attractiveness in a way that could be more accurate than what you include in your profile," Zhao said in a statement. Zhao's algorithm will notice that while a client says he likes tall women, he keeps contacting shorter women and the model will change its recommendations to suit this pattern.

"In our model, users with similar taste and (un)attractiveness will have higher similarity scores than those who only share common taste or attractiveness. 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."