arXiv (Cornell University)· 2016· Preprint
Equality of Opportunity in Supervised Learning
- 1,926citations
- 2016year
Short summary
Researchers propose a new criterion for measuring and removing discrimination against sensitive attributes in supervised machine learning models, shifting the cost of poor classification to the decision-maker.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces a new criterion for measuring discrimination in supervised learning.
- Provides a method to optimally adjust predictors to remove discrimination.
- Shifts the cost of poor classification from disadvantaged groups to the decision-maker.
- The proposed notion is oblivious, depending only on joint statistics.
AI-generated from the title and abstract; the full text is not read.
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.
The authors' abstract, as published at the source. arXiv (Cornell University), 2016 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Safety Research
Safety ResearchSocial Sciences