Certifying and Removing Disparate Impact

@article{Feldman2014CertifyingAR,
  title={Certifying and Removing Disparate Impact},
  author={Michael Feldman and Sorelle A. Friedler and John Moeller and Carlos Eduardo Scheidegger and Suresh Venkatasubramanian},
  journal={ArXiv},
  year={2014},
  volume={abs/1412.3756}
}
What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. This legal determination hinges on a definition of a protected class (ethnicity, gender) and an explicit description of the process. When computers are involved, determining disparate impact (and hence bias) is harder. It might not be possible to disclose the… CONTINUE READING

Figures and Topics from this paper.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
SHOWING 1-10 OF 412 CITATIONS

2 Using SDR to Formulate Fairness Desiderata

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Learning Fair Representations for Kernel Models

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Benchmarking Four Approaches to Fairness-Aware Machine Learning

VIEW 12 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

The cost of fairness in classification

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Algorithmic Fairness

VIEW 8 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

Achieving Fairness in Determining Medicaid Eligibility through Fairgroup Construction

VIEW 7 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Learning Fair Naive Bayes Classifiers by Discovering and Eliminating Discrimination Patterns

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Learning Provably Useful Representations, with Applications to Fairness

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2014
2020

CITATION STATISTICS

  • 53 Highly Influenced Citations

  • Averaged 113 Citations per year from 2017 through 2019

  • 73% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-3 OF 3 REFERENCES

A multidisciplinary survey on discrimination analysis

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Classifying without discriminating

VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL