EconBase
← All papers

Quantifying fairness and discrimination in predictive models

Arthur Charpentier

arXiv 19 Dec 2022 · Econometrics · 4 citations (OpenAlex)

arXiv:2212.09868 · PDF · DOI · OpenAlex · Extracted main text

Abstract

The analysis of discrimination has long interested economists and lawyers. In recent years, the literature in computer science and machine learning has become interested in the subject, offering an interesting re-reading of the topic. These questions are the consequences of numerous criticisms of algorithms used to translate texts or to identify people in images. With the arrival of massive data, and the use of increasingly opaque algorithms, it is not surprising to have discriminatory algorithms, because it has become easy to have a proxy of a sensitive variable, by enriching the data indefinitely. According to Kranzberg (1986), "technology is neither good nor bad, nor is it neutral", and therefore, "machine learning won't give you anything like gender neutrality `for free' that you didn't explicitely ask for", as claimed by Kearns et a. (2019). In this article, we will come back to the general context, for predictive models in classification. We will present the main concepts of fairness, called group fairness, based on independence between the sensitive variable and the prediction, possibly conditioned on this or that information. We will finish by going further, by presenting the concepts of individual fairness. Finally, we will see how to correct a potential discrimination, in order to guarantee that a model is more ethical

Citation extraction

101
references
156
in-text mentions
101
distinct cited
6
self-citations
18,557
main-text words

appendix boundary found by none_found · 100% 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
1Hardt, M., Price, E., and Srebro, N (2016) Equality of opportunity in supervised learning1.00093100%
2Kearns, M. and Roth, A (2019) The ethical algorithm: The science of socially aware algorithm design1.00063100%
3Corbett-Davies, S., Pierson, E., Feller, A., Goel, S., and Huq, A (2017) Algorithmic decision making and the cost of fairness0.87452100%
4Kusner, M. J., Loftus, J., Russell, C., and Silva, R (2017) Counterfactual fairness0.73732100%
5Dwork, C., Hardt, M., Pitassi, T., Reingold, O., and Zemel, R (2012) Fairness through awareness0.73732100%
6Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., and Venk… (2015) Certifying and removing disparate impact0.73732100%
7Chouldechova, A (2017) Fair prediction with disparate impact: A study of bias in recidivism prediction instruments0.69351100%
8Kleinberg, J., Lakkaraju, H., Leskovec, J., Ludwig, J., and Mullaina… (2017) Human Decisions and Machine Predictions0.64441100%
9Kleinberg, J., Mullainathan, S., and Raghavan, M (2016) Inherent trade-offs in the fair determination of risk scores0.64441100%
10Berk, R., Heidari, H., Jabbari, S., Joseph, M., Kearns, M., Morgenst… (2017) A convex framework for fair regression0.58531100%

Showing the top 10 of 101 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
1Optimal Transport for Counterfactual Estimation: A Method for Causal Inference0.40511