A Reciprocal Embedding Framework For Modelling Mutual Preferences


  • R. Ramanathan SBX Technologies Corporation, Tokyo
  • Nicolas K. Shinada SBX Technologies Corporation, Tokyo
  • Michinobu Shimatani Tapple Inc., Tokyo
  • Yuhei Yamaguchi Tapple Inc., Tokyo
  • Junichi Tanaka Tapple Inc., Tokyo
  • Yuta Iizuka Tapple Inc., Tokyo
  • Sucheendra K. Palaniappan SBX Technologies Corporation, Tokyo


Recommender Systems, Learning Latent Representations, Collaborative Filtering, Social Recommendation, Personalization


Understanding the mutual preferences between potential dating partners is core to the success of modern web-scale personalized recommendation systems that power online dating platforms. In contrast to classical user-item recommendation systems which model the unidirectional preferences of users to items, understanding the bidirectional preferences between people in a reciprocal recommendation system is more complex and challenging given the dynamic nature of interactions. In this paper, we describe a reciprocal recommendation system we built for one of the leading online dating applications in Japan. We also discuss the lessons learnt from designing, developing and deploying the reciprocal recommendation system in production.




How to Cite

Ramanathan, R., Shinada, N. K., Shimatani, M., Yamaguchi, Y., Tanaka, J., Iizuka, Y., & Palaniappan, S. K. (2021). A Reciprocal Embedding Framework For Modelling Mutual Preferences. Proceedings of the AAAI Conference on Artificial Intelligence, 35(17), 15385-15392. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17807



IAAI Technical Track on Emerging Applications of AI