HackerPapers

arXiv:1610.02413cs.LG

Equality of Opportunity in Supervised Learning

Moritz Hardt, Eric Price, Nathan Srebro

Abstract

We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assuming data about the predictor, target, and membership in the protected group are available, we show how to optimally adjust any learned predictor so as to remove discrimination according to our definition. Our framework also improves incentives by shifting the cost of poor classification from disadvantaged groups to the decision maker, who can respond by improving the classification accuracy. In line with other studies, our notion is oblivious: it depends only on the joint statistics of the predictor, the target and the protected attribute, but not on interpretation of individualfeatures. We study the inherent limits of defining and identifying biases based on such oblivious measures, outlining what can and cannot be inferred from different oblivious tests. We illustrate our notion using a case study of FICO credit scores.

arXiv comments
Journal reference
DOI
Subjects
cs.LGMachine Learning

On Hacker News

Linked by 5 identifiable commenters in 5 comments across 5 threads, from Jan 2017 to Aug 2021.

Comments linking this paper, per year.

Discussed in comments5 threads

  1. Moving beyond “algorithmic bias is a data problem” 1 comment

    • Differences in lending rates between groups due to less data or confounding features is the motivating example in the oft-cited 'Equality of Opportunity in Supervised Learning'. Highly recommend it: https://arxiv.org/abs/1610.02413

      3wolfView on HNParent context

  2. Ask HN: What's the best paper you've read in 2020? 1 comment

    • Difficult to choose one this year (plenty of things happened + plenty of time to read things due to lock down). "Equality of Opportunity in Supervised Learning" (https://arxiv.org/abs/1610.02413) It explain the basic concept about fairness in ML. Very practical exemple in my…

      lcrmorinView on HNParent context

  3. Making a racist AI without really trying (2017) 1 comment

    • > Some people expect that fighting algorithmic racism is going to come with some sort of trade-off. Um, that's because we know it comes with trade-offs once you have the most optimal algorithm. See for instance https://arxiv.org/pdf/1610.02413.pdf. If your best performing…

      lalaland1125View on HNParent context

  4. Harvard discrimination lawsuit: data show penalization of Asian-Americans 1 comment

    • > The goal should be equality of opportunity and evaluation rather than equality of outcome. In general, that will still require taking race into account. https://arxiv.org/abs/1610.02413 "Equality of Opportunity in Supervised Learning" discusses various fairness measures in the…

      yorwbaView on HNParent context

  5. U.S. sues Oracle, alleges salary and hiring discrimination 1 comment

    • Google has actually released a paper on codifying what discrimination looks like for lending (https://arxiv.org/abs/1610.02413 + blog post: https://research.googleblog.com/2016/10/equality-of-opportun...). It can be trivially extended to discuss hiring. Basically a fair hiring…

      dlssView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.