BLOB : A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

BLOB : A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals

Otmane Sakhi
  • Fonction : Auteur
  • PersonId : 1076039
Stephen Bonner
  • Fonction : Auteur
  • PersonId : 1076013
David Rohde
  • Fonction : Auteur
  • PersonId : 1053680
Flavian Vasile
  • Fonction : Auteur
  • PersonId : 1053681

Résumé

A common task for recommender systems is to build a pro le of the interests of a user from items in their browsing history and later to recommend items to the user from the same catalog. The users' behavior consists of two parts: the sequence of items that they viewed without intervention (the organic part) and the sequences of items recommended to them and their outcome (the bandit part). In this paper, we propose Bayesian Latent Organic Bandit model (BLOB), a probabilistic approach to combine the 'or-ganic' and 'bandit' signals in order to improve the estimation of recommendation quality. The bandit signal is valuable as it gives direct feedback of recommendation performance, but the signal quality is very uneven, as it is highly concentrated on the recommendations deemed optimal by the past version of the recom-mender system. In contrast, the organic signal is typically strong and covers most items, but is not always relevant to the recommendation task. In order to leverage the organic signal to e ciently learn the bandit signal in a Bayesian model we identify three fundamental types of distances, namely action-history, action-action and history-history distances. We implement a scalable approximation of the full model using variational auto-encoders and the local re-paramerization trick. We show using extensive simulation studies that our method out-performs or matches the value of both state-of-the-art organic-based recommendation algorithms, and of bandit-based methods (both value and policy-based) both in organic and bandit-rich environments.
Fichier principal
Vignette du fichier
main.pdf (262.89 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02923774 , version 1 (27-08-2020)

Identifiants

Citer

Otmane Sakhi, Stephen Bonner, David Rohde, Flavian Vasile. BLOB : A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals. 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Aug 2020, San Diego, United States. ⟨10.1145/3394486.3403121⟩. ⟨hal-02923774⟩

Collections

UNIV-PARIS-SACLAY
228 Consultations
300 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More