A new academic study explores how popular dating app users are more likely to be recommended to others, and how this biased model leads to more revenue and matches overall. Research data was collected from 240,000 users from a dating platform in Asia.
Researchers from Carnegie Mellon University and the University of Washington came together to investigate how a dating app interacts with its most popular users, and what impact this has on its success.
First of all, the study established that more popular, more attractive users were more likely to be recommended to others by the dating app algorithim.
With this in mind, researchers then compared two approaches: one where popular and unpopular users have equal chance to be recommended, and the current system where popular users get priority.
The study found that the ‘fairer’ unbiased system ultimately resulted in less matches and lower revenue for the dating platform. This means greater exposure of its popular users led to higher user engagement and a greater number of successful matches.
“Our findings suggest that an online dating platform can increase revenue and users’ chances of finding dating partners simultaneously,” explains Musa Eren Celdir, one of the researchers involved in the study.
“Although we focused on a specific dating platform, our model and analysis can be applied to other matching platforms, where the platform makes recommendations to its users and users have different characteristics”, added researcher Elina H. Hwang.
Ultimately the study recommends that dating platforms should be more open with users about how their recommendation algorithms operate. It also points out that more research could be done to find the balance between revenue growth, user satisfaction, and ethical algorithms.
