A Reciprocal Embedding Framework for Modelling Mutual Preferences
Abstract
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.
Cite
Text
Ramanathan et al. "A Reciprocal Embedding Framework for Modelling Mutual Preferences." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I17.17807Markdown
[Ramanathan et al. "A Reciprocal Embedding Framework for Modelling Mutual Preferences." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/ramanathan2021aaai-reciprocal/) doi:10.1609/AAAI.V35I17.17807BibTeX
@inproceedings{ramanathan2021aaai-reciprocal,
title = {{A Reciprocal Embedding Framework for Modelling Mutual Preferences}},
author = {Ramanathan, R. and Shinada, Nicolas K. and Shimatani, Michinobu and Yamaguchi, Yuhei and Tanaka, Junichi and Iizuka, Yuta and Palaniappan, Sucheendra K.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {15385-15392},
doi = {10.1609/AAAI.V35I17.17807},
url = {https://mlanthology.org/aaai/2021/ramanathan2021aaai-reciprocal/}
}