Concern 389 · Working draft · editorial review in progress
Intersectional fairness
Intersectional fairness asks whether people face distinct disadvantages at the overlap of characteristics such as race, gender, disability and age.
Understanding the concern
A system may look balanced when each category is examined separately. Yet a smaller group at their intersection can still receive poor results. For example, a good average for women and a good average for older adults do not establish good performance for older women. Broad totals can hide the pattern.
It is like checking a city's average travel time without noticing one neighbourhood has no reliable route. More detailed tests can help, but small samples make estimates uncertain and raise privacy concerns. Community input and careful analysis are needed so that looking more closely does not turn into unsupported claims about tiny groups.
An example
An audit reports acceptable results by gender and by age, but never checks their combination.
Illustrative unless identified as a documented case.
Evidence and its limits
The research demonstrates limits of coarse grouping and intersectional evaluation. Small-group findings require uncertainty and privacy safeguards.
Kearns, Neel, Roth and Wu · Research paper
Preventing Fairness Gerrymandering ↗ (opens in a new tab)Why coarse group checks can miss harms to subgroups and methods for auditing them.
Buolamwini and Gebru · FAT 2018 · Research study
Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification ↗ (opens in a new tab)Studies gender-classification accuracy and skin-tone intersections in the tested commercial systems. Classification is distinct from face identification.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
Which overlapping groups might disappear inside the averages, and do we have enough evidence to assess them responsibly?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Justice
Justice means fair treatment, fair procedures, and attention to who receives benefits and burdens. It asks whether people with less power can be heard and seek repair.
Look at outcomes across different groups and individual cases. Provide a usable way to challenge decisions and correct harm. Equal wording in a policy does not guarantee equal treatment in practice.
Ask together: Who benefits, who bears the cost, and who can challenge the decision?
Dignity
Dignity means recognizing each person's worth regardless of usefulness, status, or a system's score. People deserve respect and a voice in matters that affect them.
Explain important decisions, avoid humiliating treatment, and keep room for a person's story. Do not treat a prediction as a complete account of who someone is.
Ask together: Does this use treat each person as someone whose experience matters?
Listening
Listening means trying to understand someone's experience before preparing an answer. People who use a service, work with it, or are judged by it may notice problems its designers miss.
Invite people to describe what happened in their own words. Repeat back what you understood and let them correct it. A quiet person or a complaint that is hard to measure may still reveal something important.
Ask together: Whose experience have we not heard yet?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.