2017/06/30 by Massimo Quadrana, Alexandros Karatzoglou, Balázs Hidasi +1 · 1 citation
Computer Science · #Artificial neural network #Deep neural networks #Identifier #Image and Video Quality Assessment #Key (lock) #Machine Learning in Healthcare #Recommender Systems and Techniques #Recommender system #Recurrent neural network #cs.HC #cs.IR #cs.LG
paper · pdf · doi:10.1145/3109859.3109896
openalex created_date 2017/06/23 · arxiv created 2017/08/23 · openalex publication_date 2017/08/24 · arxiv updated 2017/08/25 · openalex updated_date 2026/08/05
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.