No abstract

No abstract

Reciprocal Recommender Systems are recommender systems for social platforms that connect people to people. They are commonly used in online dating, social networks and recruitment services. The main difference between these and conventional user-item recommenders that might be found on, for example, a shopping service, is that they must consider the interests of both parties. In this study, we present a novel method of making reciprocal recommendations based on image data. Given a user's history of positive and negative preference expressions on other users images, we train a siamese network to identify images that fit a user's personal preferences. We provide an algorithm to interpret those individual preference indicators into a single reciprocal preference relation. Our evaluation was performed on a large real-world dataset provided by a popular online dating service. Based on this, our service significantly improves on previous state-of-the-art content-based solutions, and also out-performs collaborative filtering solutions in cold-start situations. The success of this model provides empirical evidence for the high importance of images in online dating.

No abstract

Online dating constitutes one out of myriad popular services that can be accessed via the Internet nowadays. This paper introduces a novel detection system for identifying dubious users, i.e. users who utilize a Japanese online dating service for purposes besides dating. Examples of such purposes include sales and multi-level marketing, amongst others. More specifically, the proposed detection is characterized by simultaneously analyzing: (i) user profile data; (ii) user actions over their first few hours; and (iii) data retrieved from Facebook in order to find the likelihood that the user is a spammer. The resulting system successfully detects a number of spammers every day, thereby becoming a valuable tool for the customer service team in Eureka Inc, where it has been deployed.