Contributed by: kellyseal on Friday, July 15 2022 @ 08:07 am
Last modified on Friday, July 15 2022 @ 08:11 am
Researchers from the University of Texas in Dallas, Stanford and Columbia Universities have developed a new dating app algorithm that they say can improve match rates up to 45 percent.
Their study was published in the INFORMS journal Manufacturing & Service Operations Management by authors Dr. Ignacio Rios from the Naveen Jindal School of Management at UT Dallas, along with Dr. Daniela Saban of Stanford University and Dr. Fanyin Zheng of Columbia University.
“One of the biggest issues is how to decide which profiles to show to each user in order to ensure that they will get meaningful matches,” Rios told the University of Texas Dallas[*1] news. “In many dating apps, we see a lot of frustrated users because they struggle to find a match that leads to a longer-term relationship. This is partly because of inefficiencies in how these apps work.”
Rios and his team discovered that the more matches a person has had in the recent past, the fewer likes they give to new profiles. In fact, each additional match reduced the probability of a new like by 3 percent, which compounds quickly. So, their algorithm includes whether a user has recently matched as a factor - and prioritizes users who haven’t had matches in the recent past with the assumption that they will probably like more profiles.
When they tested simulated data, match rates increased between 20 and 45 percent compared to the current matching algorithms in dating apps today. When the researchers tested the new algorithm among dating app users in Houston and Austin, matches increased by 27 percent.
Rio told the UT Dallas news that peoples’ tendency to match less over time could be due to many factors, including the amount of time and energy they want to spend on the app sifting through profiles, instead preferring to see what happens with current matches; or that they become pickier the more matches they receive; or that they are so optimistic about a new match’s potential they avoid liking new profiles, at least for a while.
The original question is still unknown despite the increase in matches among the study groups: will the new algorithm succeed in creating better matches that develop into long-term relationships? Rio said: “The implication is that users will get more matches and potentially find a long-term partner. From the app’s perspective, generating more matches is one of the key performance indicators, and it is closely related with engagement, retention, growth and other relevant outcomes.”
The researchers worked with an industry partner, who just expanded the test of the new algorithm to new markets.