Post-hoc explanations for complex model recommendations using simple methods

Dorin Shmaryahu, Guy Shani, Bracha Shapira

Research output: Contribution to journalConference articlepeer-review

5 Scopus citations


Many leading approaches for generating recommendations, such as matrix factorization and autoencoders, compute a complex model composed of latent variables. As such, explaining the recommendations generated by these models is a difficult task. In this paper, instead of attempting to explain the latent variables, we provide post-hoc explanations for why a recommended item may be appropriate for the user, by using a set of simple, easily explainable recommendation algorithms. When the output of the simple explainable recommender agrees with the complex model on a recommended item, we consider the explanation of the simple model to be applicable. We suggest both simple collaborative filtering and content based approaches for generating these explanations. We conduct a user study in the movie recommendation domain, showing that users accept our explanations, and react positively to simple and short explanations, even if they do not truly explain the mechanism leading to the generated recommendations.

Original languageEnglish
Pages (from-to)26-36
Number of pages11
JournalCEUR Workshop Proceedings
StatePublished - 1 Jan 2020
Event7th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems, IntRS 2020 - Virtual, Online, Brazil
Duration: 26 Sep 2020 → …


  • Collaborative filtering explanations
  • Content-base explanations
  • Explainable Recommendation
  • Recommender Systems
  • User-study

ASJC Scopus subject areas

  • General Computer Science


Dive into the research topics of 'Post-hoc explanations for complex model recommendations using simple methods'. Together they form a unique fingerprint.

Cite this