Online Dating App Algorithms Favor Popular and Attractive Users
A recent study by researchers from Carnegie Mellon University and the University of Washington suggests that the algorithms used by online dating platforms may have inherent biases. According to Tech Xplore, the study found that these algorithms tend to favor more popular and attractive users over their less popular and less attractive counterparts.
The researchers examined data from over 240,000 users on a major Asian online dating platform over a three-month period. They observed a correlation between a user’s average attractiveness score and their likelihood of being recommended by the platform’s algorithm.
Soo-Haeng Cho, IBM Professor of Operations Management and Strategy at Carnegie Mellon’s Tepper School of Business and co-author of the study, commented on the rapid growth of online dating and raised questions about the fairness of recommendation algorithms used by dating platforms.
The study suggests that the platforms, which aim to generate revenue through ads, subscriptions, and in-app purchases, may prioritize keeping users engaged rather than maximizing their chances of finding an ideal match.
The researchers also analyzed the incentives for platforms to favor popular users when seeking to maximize revenue or matches. They found that unbiased recommendations, where popular and unpopular users have equal chances of being recommended, led to lower revenue and fewer matches for dating platforms. Popular users were shown to contribute to increased engagement and more successful matches, making them essential for revenue generation.
The study, published in the Manufacturing & Service Operations Management journal, suggests that online dating platforms can leverage these findings to understand user behavior and refine recommendation systems.
In conclusion, the study highlights the potential biases in online dating app algorithms and the implications for both users and the platforms themselves.
