Skip to Main content Skip to Navigation
Conference papers

Recommendation from raw data with adaptive compound Poisson factorization

Abstract : Count data are often used in recommender sys-tems: they are widespread (song play counts,product purchases, clicks on web pages) andcan reveal user preference without any explicitrating from the user. Such data are known to besparse, over-dispersed and bursty, which makestheir direct use in recommender systems chal-lenging, often leading to pre-processing stepssuch as binarization. The aim of this paper isto build recommender systems from these rawdata, by means of the recently proposed com-pound Poisson Factorization (cPF). The papercontributions are three-fold: we present a uni-fied framework for discrete data (dcPF), lead-ing to an adaptive and scalable algorithm; weshow that our framework achieves a trade-offbetween Poisson Factorization (PF) applied toraw and binarized data; we study four specificinstances that are relevant to recommendationand exhibit new links with combinatorics. Ex-periments with three different datasets showthat dcPF is able to effectively adjust to over-dispersion, leading to better recommendationscores when compared with PF on either rawor binarized data.
Complete list of metadata

Cited literature [45 references]  Display  Hide  Download
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Thursday, July 2, 2020 - 12:10:07 PM
Last modification on : Wednesday, June 9, 2021 - 10:00:28 AM
Long-term archiving on: : Thursday, September 24, 2020 - 3:59:38 AM


Files produced by the author(s)


  • HAL Id : hal-02392075, version 2
  • OATAO : 26226


Olivier Gouvert, Thomas Oberlin, Cédric Févotte. Recommendation from raw data with adaptive compound Poisson factorization. Conference on Uncertainty in Artificial Intelligence - UAI 2019, Jul 2019, Tel Aviv, Israel. pp.0. ⟨hal-02392075v2⟩



Record views


Files downloads