EconBase
← All papers

Cohort Shapley value for algorithmic fairness

Masayoshi Mase, Art B. Owen, Benjamin B. Seiler

arXiv 15 May 2021 · Machine Learning · 3 citations (OpenAlex)

arXiv:2105.07168 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Cohort Shapley value is a model-free method of variable importance grounded in game theory that does not use any unobserved and potentially impossible feature combinations. We use it to evaluate algorithmic fairness, using the well known COMPAS recidivism data as our example. This approach allows one to identify for each individual in a data set the extent to which they were adversely or beneficially affected by their value of a protected attribute such as their race. The method can do this even if race was not one of the original predictors and even if it does not have access to a proprietary algorithm that has made the predictions. The grounding in game theory lets us define aggregate variable importance for a data set consistently with its per subject definitions. We can investigate variable importance for multiple quantities of interest in the fairness literature including false positive predictions.

Citation extraction

30
references
46
in-text mentions
30
distinct cited
2
self-citations
5,792
main-text words

appendix boundary found by appendix_command · 86% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Mase, M., Owen, A. B., and Seiler, B. B (2019) Explaining black box decisions by Shapley cohort refinement self0.92843100%
2Angwin, J., Larson, J., Mattu, S., and Kirchner, L (2016) Machine bias: there’s software used across the country to predict future criminals. and it’s biased against blacks0.87452100%
3Chouldechova, A (2017) Fair prediction with disparate impact: A study of bias in recidivism prediction instruments0.81142100%
4Lundberg, S. M. and Lee, S.-I (2017) A unified approach to interpreting model predictions0.64422100%
5Razavi, S., Jakeman, A., Saltelli, A., Prieur, C., Iooss, B., Borgon… (2021) The future of sensitivity analysis: An essential discipline for systems modeling and policy support0.64422100%
6Shapley, L. S (1953) A value for n-person games0.64422100%
7Sundararajan, M. and Najmi, A (2020) The many Shapley values for model explanation0.58531100%
8Flores, A. W., Bechtel, K., and Lowenkamp, C. T (2016) False positives, false negatives, and false analyses: A rejoinder to machine bias: There's software used across the country to p…0.51121100%
9Adler, P., Falk, C., Friedler, S. A., Nix, T., Rybeck, G., Scheidegg… (2018) Auditing black-box models for indirect influence0.40511100%
10Berk, R., Heidari, H., Jabbari, S., Kearns, M., and Roth, A (2018) Fairness in criminal justice risk assessments: The state of the art0.40511100%

Showing the top 10 of 30 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Variable importance without impossible data0.51121