Recommendations as Treatments

Authors

  • Thorsten Joachims Cornell University
  • Ben London Amazon
  • Yi Su Cornell University
  • Adith Swaminathan Microsoft Research
  • Lequn Wang Cornell University

DOI:

https://doi.org/10.1609/aimag.v42i3.18141

Abstract

In recent years, a new line of research has taken an interventional view of recommender systems, where recommendations are viewed as actions that the system takes to have a desired effect. This interventional view has led to the development of counterfactual inference techniques for evaluating and optimizing recommendation policies. This article explains how these techniques enable unbiased offline evaluation and learning despite biased data, and how they can inform considerations of fairness and equity in recommender systems.

Downloads

Published

2021-11-20

How to Cite

Joachims, T., London, B., Su, Y., Swaminathan, A., & Wang, L. (2021). Recommendations as Treatments. AI Magazine, 42(3), 19-30. https://doi.org/10.1609/aimag.v42i3.18141

Issue

Section

Special Topic Articles