Data Science Weekly has an interview with Kang Zhao, the head of a research team from the University of Iowa, who have devised a new algorithm for online dating.
The engine recommends partners by assessing the user’s tastes and attractiveness to other singles.
It applies Machine Learning to online dating, working in a similar way to recommendation engines on Amazon or Netflix.
It analyses the history of people contacted by members and then forms groups of users with similar tastes.
However unlike the one-way Netflix model, the engine also analyses the replies the user receives and uses this to evaluate their attractiveness.
As Zhao says: “We try to address user recommendation for the unique situation of reciprocal and bipartite social networks (e.g., dating, job seeking).
“The idea is to recommend dating partners who a user will like and will like the user back. In other words, a recommended partner should match a user’s taste, as well as attractiveness.”