911����

Digital matching platforms—from professional networking to ridesharing and accommodation services—add value by bringing supply and demand into balance. But deep-seated asymmetries can prove difficult to expunge, causing platforms’ functionality and productivity to suffer. This imbalance is common for many dual-matching platforms, including online dating services where men vastly outnumber women.

The matrimonial matching platforms popular among people of Indian descent are a prime example, says , assistant professor of information systems and operations management at the at 911����. “The typical men-to-women ratio on these platforms ranges between 60:40 and 90:10,” he specifies.

In a forthcoming paper in Information Systems Research, Karmegam and co-authors Jui Ramaprasad of University of Maryland and Anand Gopal of Nanyang Technological University discuss the results of their experimental study examining engagement practices and outcomes for users seeking lifelong partners through a leading matrimonial platform in India.

As a result of the lopsided gender composition on the platform, men tended to send large numbers of invitations indiscriminately to increase their chances of finding a match. This resulted in a sizable skew in the number of invitations received by women: In Karmegam’s study, women received on average about 40 times as many expressions of interest (EIs) as men did.

The deluge of EIs left women feeling “extremely overwhelmed in the initial couple of days after joining the platform,” Karmegam says. “Once they were flooded with all these requests, it was hard for them to figure out what the platform was all about. Congestion led to reduced engagement by women and potential exit from the platform. Under prevailing social norms in India, families often share in that sorting burden.” The skewed design also left men dissatisfied with the platform due to the competition effect.

To improve the user experience for both parties, Karmegam and his co-authors tested the process of “gender gating,” which made women’s profiles visible only to men who meet culturally acceptable criteria for education, income, and age. For example, the “gender gate” prevented a man in his forties from viewing profiles of women more than 10 years younger or a couple of years older than he was. Women could override the “gender-gated” default settings with their own preferences, but men could not opt out of the restrictions.

The experimental design included two groups (one control and one treatment), each representing a state in India. The two states in the study were similar in size, socioeconomic indicators and located in close geographic proximity, but different in language and cultural characteristics. This minimized interference and helped isolate the effect of the intervention.

The researchers found that without negatively affecting male users, “gender gating” significantly improved women’s platform interaction, increased the number of matches, and improved match quality. It also resulted in women initiating more matches due to reduced screening time for finding a potential match.

Women in the treatment group received 6 percent fewer post-intervention EIs, compared to the control group, while the efficacy of the matches improved by 72 percent. The paper attributes this improvement both to the lower number of EIs received and to better alignment with social norms.

Women over 25, who sit at prime marriageable age and so align in age with more of the marriage-seeking men on the platform, experienced a 103 percent improvement in matching efficacy. They also sent 113 percent more EIs post-intervention, demonstrating increased agency.

In this case, a match is not a marriage but an open line of communication with a serious prospect. “Most of the conversation happens offline,” Karmegam says. “A lot of things need to happen outside the platform for things to work out, and our study does not capture that.”

Still, the “gender gating” experiment was such a success that the platform decided to extend the intervention across the entire user pool, Karmegam reports. In doing so, the platform joined other matchmaking services such as JDate and SKY People that use culturally appropriate criteria as a sorting mechanism to improve matchmaking accuracy.

Karmegam believes similar interventions could be used in non-romantic matchmaking scenarios. “This is something that can be applied to any people-to-people matching. For example, the majority of Uber drivers are men. Parents could ask for their daughter’s Uber teen account to be ‘gender gated’, as an extra layer of protection,” he says.

Hiring in competitive fields such as academia could also benefit from criteria-based sorting. “Narrowing the search to candidates who meet specific criteria, such as schools from which the applicants might have received their PhD degrees, would help raise the effectiveness of the process,” Karmegam says.