Bandit algorithms for the multiple-play recommendation

Abstract : The multiple-play recommender systems (RS) are RS which recommend several items to the users. RS are based on learning models in order to choose the items to recommend. Among these models, the bandit algorithms offer the advantage to learn and exploite the learnt elements at the same time. Current approaches require running as many instances of a bandit algorithm as there are items to recommend. As opposed to that, we handle all recommendations simultaneously, by a single instance of a bandit algorithm. We show on two benchmark datasets (Movielens and Jester) that our method, MPB (Multiple Plays Bandit), obtains a learning rate about thirteen times faster while obtaining equivalent click-through rates. We also show that the choice of the bandit algorithm used impacts the level of improvement.
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01659313
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Friday, December 8, 2017 - 12:00:13 PM
Last modification on : Thursday, June 27, 2019 - 4:27:52 PM

File

louedec_18750.pdf
Files produced by the author(s)

Identifiers

Citation

Jonathan Louëdec, Max Chevalier, Aurélien Garivier, Josiane Mothe. Bandit algorithms for the multiple-play recommendation . Revue des Sciences et Technologies de l'Information - Série Document Numérique, Lavoisier, 2015, 18 (2-3), pp.59-79. ⟨10.3166/DN.18.2-3.59-79⟩. ⟨hal-01659313⟩

Share

Metrics

Record views

100

Files downloads

87