Recurrent Neural Networks for Long and ...
Type de document :
Pré-publication ou Document de travail
Titre :
Recurrent Neural Networks for Long and Short-Term Sequential Recommendation
Auteur(s) :
Villatel, Kiewan [Auteur]
Sequential Learning [SEQUEL]
Criteo [Paris]
Smirnova, Elena [Auteur]
Criteo [Paris]
Mary, Jérémie [Auteur]
Criteo [Paris]
Preux, Philippe [Auteur]
Sequential Learning [SEQUEL]
Sequential Learning [SEQUEL]
Criteo [Paris]
Smirnova, Elena [Auteur]
Criteo [Paris]
Mary, Jérémie [Auteur]
Criteo [Paris]
Preux, Philippe [Auteur]

Sequential Learning [SEQUEL]
Mot(s)-clé(s) en anglais :
Recommender System
Sequence Modeling
Recurrent neural network
Sequential Recommendation
Sequence Modeling
Recurrent neural network
Sequential Recommendation
Discipline(s) HAL :
Informatique [cs]/Recherche d'information [cs.IR]
Résumé en anglais : [en]
Recommender systems objectives can be broadly characterized as modeling user preferences over short-or long-term time horizon. A large body of previous research studied long-term recommendation through dimensionality ...
Lire la suite >Recommender systems objectives can be broadly characterized as modeling user preferences over short-or long-term time horizon. A large body of previous research studied long-term recommendation through dimensionality reduction techniques applied to the historical user-item interactions. A recently introduced session-based recommendation setting highlighted the importance of modeling short-term user preferences. In this task, Recurrent Neural Networks (RNN) have shown to be successful at capturing the nuances of user's interactions within a short time window. In this paper, we evaluate RNN-based models on both short-term and long-term recommendation tasks. Our experimental results suggest that RNNs are capable of predicting immediate as well as distant user interactions. We also find the best performing configuration to be a stacked RNN with layer normalization and tied item embeddings.Lire moins >
Lire la suite >Recommender systems objectives can be broadly characterized as modeling user preferences over short-or long-term time horizon. A large body of previous research studied long-term recommendation through dimensionality reduction techniques applied to the historical user-item interactions. A recently introduced session-based recommendation setting highlighted the importance of modeling short-term user preferences. In this task, Recurrent Neural Networks (RNN) have shown to be successful at capturing the nuances of user's interactions within a short time window. In this paper, we evaluate RNN-based models on both short-term and long-term recommendation tasks. Our experimental results suggest that RNNs are capable of predicting immediate as well as distant user interactions. We also find the best performing configuration to be a stacked RNN with layer normalization and tied item embeddings.Lire moins >
Langue :
Anglais
Collections :
Source :
Fichiers
- https://hal.inria.fr/hal-01847127/document
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-01847127/file/dlrs_workshop_2018.pdf
- Accès libre
- Accéder au document
- http://arxiv.org/pdf/1807.09142
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-01847127/document
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-01847127/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- recurrent-neural-networks-long-short-term-recommendation.pdf
- Accès libre
- Accéder au document
- dlrs_workshop_2018.pdf
- Accès libre
- Accéder au document
- 1807.09142
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- recurrent-neural-networks-long-short-term-recommendation.pdf
- Accès libre
- Accéder au document
- dlrs_workshop_2018.pdf
- Accès libre
- Accéder au document