Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks

Massimo Quadrana, Alexandros Karatzoglou, Balázs Hidasi, Paolo Cremonesi
6/13/2017
cs.LGcs.HCcs.IR

Official code: mquad/hgru4rec (215 stars, MIT, last commit 2022-12-07).

Abstract

Session-based recommendations are highly relevant in many modern on-line services (e.g. e-commerce, video streaming) and recommendation settings. Recently, Recurrent Neural Networks have been shown to perform very well in session-based settings. While in many session-based recommendation domains user identifiers are hard to come by, there are also domains in which user profiles are readily available. We propose a seamless way to personalize RNN models with cross-session information transfer and devise a Hierarchical RNN model that relays end evolves latent hidden states of the RNNs across user sessions. Results on two industry datasets show large improvements over the session-only RNNs.

View on arXivView PDF

Code Implementations(1)

mquad/hgru4recOfficial100%
MIT

Code for our ACM RecSys 2017 paper "Personalizing Session-based Recommendation with Hierarchical Recurrent Neural Networks"

21567Shell, PythonJun 13, 20173 years agoMIT

Similar Papers

Personalized Graph Neural Networks with Attention Mechanism for Session-Aware Recommendation

86% match1 repo852019

Session-based Recommendation with Graph Neural Networks

86% match1 repo8532018

Session-aware Linear Item-Item Models for Session-based Recommendation

84% match1 repo342021

Performance Comparison of Session-based Recommendation Algorithms based on GNNs

83% match2023

Enhancing User Intent Capture in Session-Based Recommendation with Attribute Patterns

82% match1 repo112023

Neural Attentive Session-based Recommendation

81% match1 repo1342017

Cite this paper

@article{quadrana2017personalizing,
  title  = {Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks},
  author = {Massimo Quadrana and Alexandros Karatzoglou and Balázs Hidasi and Paolo Cremonesi},
  year   = {2017},
  eprint = {1706.04148},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1706.04148}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1706.04148.svg)](https://codeofpaper.com/paper/1706.04148)

Discussion