Demographic parity requires equal proportion of positive predictions in each group (“No Disparate Impact”).
Is statistical parity the same as demographic parity?
Demographic parity (also known as statistical parity): A classifier satisfies demographic parity under a distribution over ( X , A , Y ) if its prediction is statistically independent of the sensitive feature ..
What is an example of demographic parity?
In the binary classification scenario, demographic parity refers to equal selection rates across groups. For example, in the context of a resume screening model, equal selection would mean that the proportion of applicants selected for a job interview should be equal across groups..
What is the demographic parity in math?
Demographic Parity. P(C=.
A=a)=P(C=
A=b).
Demographic parity requires equal proportion of positive predictions in each group (“No Disparate Impact”). The evaluation metric requiring parity in this case is the prevalence.
What is the formula for demographic parity difference?
Disparity metrics, group metrics They can either compare the behavior across different groups in terms of ratios or in terms of differences. For example, for binary classification: Demographic parity difference is defined as ( max a E [ h ( X ) A = a ] ) − ( min a E [ h ( X ) A = a ] ) ..
What is the problem with demographic parity?
Demographic parity almost always cannot be implemented if individuals are members of multiple protected groups because you may not be able to impose the equal probabilities across all groups. Demographic parity can also be fair at a group level, but unfair at an individual level..
Demographic parity (also known as statistical parity): A classifier satisfies demographic parity under a distribution over ( X , A , Y ) if its prediction is statistically independent of the sensitive feature .
demographic parity A fairness metric that is satisfied if the results of a model's classification are not dependent on a given sensitive attribute.Aug 8, 2023
The demographic parity difference is defined as the difference between the largest and the smallest group-level selection rate, E [ h ( X ) A = a ] , across all values of the sensitive feature(s). The demographic parity difference of 0 means that all groups have the same selection rate.
demographic parity
A fairness metric that is satisfied if the results of a model's classification are not dependent on a given sensitive attribute.
Demographic Parity states that the proportion of each segment of a protected class (e.g. gender) should receive the positive outcome at equal rates. A positive outcome is the preferred decision, such as “getting to university”, “getting a loan” or “being shown the ad”.
In the binary classification scenario, demographic parity refers to equal selection rates across groups. For example, in the context of a resume screening model, equal selection would mean that the proportion of applicants selected for a job interview should be equal across groups.
Abstract
This post will be the first post on the series. The purpose of this post is to: 1. give a quick but relatively comprehensive survey of Fair ML. 2
Introduction
Fairness is becoming one of the most popular topics in machine learning in recent years. Publications explode in this field (see Fig1)
Motivations
The first question to ask is that why we care about fairness
Causes
One would ask: “what causes bias in ML systems?” Essentially, the bias comes from human bias existing in training dataset due to historical reason(s)
Definitions of Fairness
A natural question to ask is “how to define fairness?”, specifically, “How can we formulate fairness such that it can be considered in ML systems”
Fair Algorithms
There are many algorithms that claim to help improve fairness. Most of them fall into three categories: preprocessing, optimization at training time
What is demographic parity in machine learning?
Demographic parity is a fairness metric whose goal is to ensure a machine learning model’s predictions are independent of membership in a sensitive group
In other words, demographic parity is achieved when the probability of a certain prediction is not dependent on sensitive group membership
What is equalized opportunity compared to demographic parity?
As compared to demographic parity, if a large number of unqualified male applicants apply for the job, the hiring of qualified female applicants in other protected groups is not affected
Equalized opportunity means matching the true positive rates for different values of the protected attribute
What is the condition for demographic parity?
The condition for demographic parity is, for all a, b ∈ A a, b ∈ A P(C = 1|A = a) = P(C = 1|A = b)
P ( C = 1 | A = a) = P ( C = 1 | A = b)
Demographic parity requires equal proportion of positive predictions in each group (“No Disparate Impact”)
The evaluation metric requiring parity in this case is the prevalence
Demographic parity is one of the most popular fairness indicators in the literature. Demographic parity is achieved if the absolute number of positive predictions in the subgroups are close to each other. This measure does not take true class into consideration and only depends on the model predictions. Formula: (TP + FP)Demographic parity is a fairness metric whose goal is to ensure a machine learning model’s predictions are independent of membership in a sensitive group. In other words, demographic parity is achieved when the probability of a certain prediction is not dependent on sensitive group membership. InDemographic parity The outcome is independent of the protected attribute. For example, the probability of being hired is independent of gender. Demographic parity almost always cannot be implemented if individuals are members of multiple protected groups because you may not be able to impose the equal probabilities across all groups.
Demographic parity
Socioeconomic index
Released by UNESCO, the Gender Parity Index (GPI) is a socioeconomic index usually designed to measure the relative access to education of males and females. It is used by international organizations, particularly in measuring the progress of developing countries. For example, some UNESCO documents consider gender parity in literacy.
A parity progression ratios (PPR) is a measure commonly used in demography to study fertility. The PPR is simply the proportion of women with a certain number of children who go on to have another child. Calculating the PPR, also known as mwe-math-element>, can be achieved by using the following formula:
