New Online Dating Formula Could Lead to More Successful Matches

Traditional dating websites match people based on things like mutual preferences, interests, and goals. Attraction obviously factors in whether you'll reach out or respond to those matches, but the algorithms used don't really take attraction into account (beyond basic, vague specifications like body type preference). But mutual physical attraction is at the center of a new potential matchmaking formula. Created by computer scientists at the University of Iowa, the algorithm will only match you with partners likely to find you attractive.

The formula works by analyzing your message history to make new recommendations based on both shared tastes and the kinds of people you've found attractive. Evoking a fictional online dater named Mike, the researchers note that "It is Mike’s taste that affects whom he approaches through initial contacts, and his attractiveness that determines whether he can get responses." In other words: Poor Mike can approach all the women who share his affinity for Dexter and Frisbee golf in the world, but it won't matter if Mike keeps messaging ladies likely to find him unattractive.

"Considering the match of both taste and attractiveness, our model tries to improve dating partner recommendations by boosting a user’s chance of getting responses," the researchers write. They tested the algorithm using anonymised data on 47,000 users from a real dating website, for a period of nearly 200 days. When compared with other methods of matchmaking — such as using shared interests, likes or other variables — the results showed significant superiority in their beauty-based method.

“If a user approaches a partner recommended by [our engine], he/she will have a better chance of getting responses," researchers say. As of now, this attractiveness sorting formula is just a concept, but with the proliferation of increasingly niche and novel dating apps and websites, it's probably only a matter of time.

Image: Flickr/lordkhan