Reducing Offline Evaluation Bias in Recommendation Systems

Abstract : Recommendation systems have been integrated into the majority of large online systems. They tailor those systems to individual users by filtering and ranking information according to user profiles. This adaptation process influences the way users interact with the system and, as a consequence, increases the difficulty of evaluating a recommendation algorithm with historical data (via offline evaluation). This paper analyses this evaluation bias and proposes a simple item weighting solution that reduces its impact. The efficiency of the proposed solution is evaluated on real world data extracted from Viadeo professional social network.
Type de document :
Communication dans un congrès
23rd annual Belgian-Dutch Conference on Machine Learning (Benelearn 2014), Jun 2014, Bruxelles, Belgium. pp.55-62


https://hal.archives-ouvertes.fr/hal-01017734
Contributeur : Fabrice Rossi <>
Soumis le : jeudi 3 juillet 2014 - 09:52:04
Dernière modification le : dimanche 8 février 2015 - 01:01:24
Document(s) archivé(s) le : vendredi 3 octobre 2014 - 10:56:23

Identifiants

  • HAL Id : hal-01017734, version 1
  • ARXIV : 1407.0822

Citation

Arnaud De Myttenaere, Bénédicte Le Grand, Boris Golden, Fabrice Rossi. Reducing Offline Evaluation Bias in Recommendation Systems. 23rd annual Belgian-Dutch Conference on Machine Learning (Benelearn 2014), Jun 2014, Bruxelles, Belgium. pp.55-62. <hal-01017734>

Partager

Métriques

Consultations de
la notice

375

Téléchargements du document

157