• Home
  • Dating apps
  • Researchers sharpen Cupid”s lens on dating apps with new algorithm

Researchers sharpen Cupid”s lens on dating apps with new algorithm

By on June 8, 2022 0

A new algorithm proposed by a researcher at the University of Texas at Dallas and his colleagues could help dating app users find the perfect partner.

In a study published online April 7 in the journal INFORMS Management of manufacturing and service operationscorresponding author Dr Ignacio Riosassistant professor of operations management in the Naveen Jindal School of Managementand the co-authors explored a central problem facing online dating companies.

“One of the biggest issues is how to decide which profiles to show each user to ensure they get meaningful matches,” Rios said. “In many dating apps, we see a lot of frustrated users because they’re struggling to find a match that leads to a longer-term relationship. Part of that is because of the inefficiencies in how these apps.

The $12 billion online dating industry includes hundreds of services. Over the past two decades, online dating platforms have become one of the most common dating channels for couples. Previous research found that nearly 40% of couples who met in the United States in 2017 did so online.

During the COVID-19 pandemic, the use of online dating platforms has seen massive growth due to lockdowns and concerns about the spread of the virus, Rios said.

how they work

Many dating apps limit the number of profiles a user can see each day. Some platforms, including Tinder and Bumble, implement this by imposing swipe limits, while others, like Hinge, limit the number of likes.

Therefore, one of the main roles of the platforms is to select a daily set of profiles to be displayed for each user based on the preferences and characteristics of the persons concerned.

In September 2018, researchers collaborated with a major American online dating company to study how its platform should select the set of potential partners to show to each user in order to maximize the number of expected matches.

The platform has approximately 800,000 active users in over 150 geographic markets and uses the same algorithm in all markets. Users can declare a preferred age range, height range, maximum distance from their location and more. From this data, the platform calculates a set of potential partners for each user.

A new method

Rios and his colleagues have developed a model that incorporates a new component: user experiences.

Using data from the industry partner, the researchers studied user preferences, such as age, religion and race, as well as behavior, such as whether each user logged in and, if so, , how he assessed the profiles presented to him.

The study found that the more matches a person has had in the recent past, the less likes they give to other profiles. That suggests a historic effect, Rios said.

Estimates show that each additional match reduced the likelihood of a new like by at least 3%.

“We observed that users are less likely to like other profiles when they recently managed to get more matches,” he said. “This may be because users keep in mind how much time and energy they can devote to the app, and so if they’ve had a lot of matches in the recent past, they expect to spend their time on these matches instead of liking other profiles.

“Another likely reason is that users update their beliefs about their own attractiveness and thus become more demanding. Finally, a third possible reason is that users trust their new matches will work, so they avoid liking new profiles.

The researchers incorporated these findings into a new algorithm to solve the platform problem. Rios said the algorithm considers the likelihood of both parties liking each other and prioritizing users who haven’t gotten matches in the recent past, assuming they’ll be more likely to like profiles that are presented to them.

Results and implications

Using simulations on real data, the researchers found that the proposed algorithm improved the overall match rate between 20% and 45% compared to the industry partner’s current algorithm. These results convinced the company to test the algorithm in practice.

In field experiments in the Houston and Austin markets in August 2020, the researchers’ algorithm yielded at least 27% more matches than the company’s algorithm.

Rios said the findings underscore the importance of properly accounting for user preferences, behavior and activity metrics to improve the operational efficiency of matching platforms.

“The implication is that users will get more matches and potentially find a long-term partner,” Rios said. “From an app perspective, generating more matches is one of the key performance indicators, and it’s closely tied to engagement, retention, growth, and other relevant outcomes.

“We observed that users are less likely to like other profiles when they have recently managed to get more matches. This may be due to users keeping in mind the time and energy that ‘they can devote to the application.

Dr. Ignacio Rios, Assistant Professor of Operations Management at Naveen Jindal School of Management

“The methodology can be applied to any dating app that offers a limited set of profiles each day. Other companies could use our framework to increase the number of matches they generate.

The industry partner recently expanded the use of the proposed algorithm to other markets, Rios said. The results were similar.

Next, the platform will implement the framework in its largest markets.

Other contributors to the study included Dr. Daniela Saban of Stanford University and Dr. Fanyin Zheng of Columbia University. The paper received an honorable mention in the 2021 Management of manufacturing and service operations Practice-oriented research competition.


Source link