Google Research

Fairness and Bias in Online Selection

  • Andres Cristi
  • Ashkan Norouzi Fard
  • Jose Correa
  • Paul Duetting
Proceedings of the 2021 International Conference on Machine Learning (ICML'21) (to appear)

Abstract

There is growing awareness and concern about fairness in machine learning and algorithm design. This is particularly true in online selection problems where decisions are often biased, for example, when assessing credit risks or hiring staff. We address the issues of fairness and bias in online selection by introducing multi-color versions of the classic secretary and prophet problem. We develop optimal fair algorithms for these new problems, and provide tight bounds on the competitiveness of these new algorithms. We validate the efficacy and fairness of these algorithms and natural benchmarks on real-world data.

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work