Skip to Main content Skip to Navigation
Conference papers

Study of a bias in the offline evaluation of a recommendation algorithm

Abstract : Recommendation systems have been integrated into the majority of large online systems to filter and rank information according to user profiles. It thus influences the way users interact with the system and, as a consequence, bias the evaluation of the performance of a recommendation algorithm computed using historical data (via offline evaluation). This paper describes this bias and discuss the relevance of a weighted offline evaluation to reduce this bias for different classes of recommendation algorithms.
Document type :
Conference papers
Complete list of metadatas
Contributor : Fabrice Rossi <>
Submitted on : Thursday, October 29, 2015 - 7:17:01 PM
Last modification on : Sunday, January 19, 2020 - 6:38:32 PM
Long-term archiving on: : Friday, April 28, 2017 - 7:04:55 AM


Files produced by the author(s)


Distributed under a Creative Commons Attribution - ShareAlike 4.0 International License


  • HAL Id : hal-01222395, version 1
  • ARXIV : 1511.01280



Arnaud de Myttenaere, Boris Golden, Bénédicte Le Grand, Fabrice Rossi. Study of a bias in the offline evaluation of a recommendation algorithm. 11th Industrial Conference on Data Mining, ICDM 2015, Jul 2015, Hamburg, Germany. pp.57-70. ⟨hal-01222395⟩



Record views


Files downloads