ImRec: Learning Reciprocal Preferences Using Images

James O Neve, Ryan Mcconville

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

8 Citations (Scopus)
305 Downloads (Pure)


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.
Original languageEnglish
Title of host publicationRecSys '20
Subtitle of host publicationFourteenth ACM Conference on Recommender Systems
PublisherAssociation for Computing Machinery (ACM)
Number of pages10
ISBN (Print)978-1-4503-7583-2
Publication statusAccepted/In press - 23 Jul 2020
Event14th ACM Conference on Recommender Systems -
Duration: 22 Sept 202026 Sept 2020


Conference14th ACM Conference on Recommender Systems


  • Reciprocal Recommender Systems
  • Content-Based Recommendation
  • Siamese Networks
  • Social Recommendation


Dive into the research topics of 'ImRec: Learning Reciprocal Preferences Using Images'. Together they form a unique fingerprint.

Cite this