Fairness Metrics
Quantitative measures of model behavior across groups.
"Several mathematical definitions of fairness. They conflict."
What is Fairness Metrics? Quantitative measures of model behavior across groups. Trade-offs require explicit choices.
Demographic parity, equalized odds, calibration.
Trade-offs require explicit choices.
Pick fairness criteria deliberately. Document the choice.
Pick what to reward the model for.
Quantitative measures of model behavior across groups. In the wild: Demographic parity, equalized odds, calibration.
Pick a lever. There are no neutral ones — every incentive funds a behavior somewhere.
Pick a reaction to Fairness Metrics
One tap. We'll point you at the most useful next surface based on how this hits.
The full taxonomy entry
Every concept in the Atlas uses the same structure — so Fairness Metrics can be compared, recombined, and cited like an element on a periodic table.
- Business
- Leadership
- Government
- Healthcare
- Education
- Sales
- Marketing
- AI
- Negotiation
- Media
- Public Policy
- Relationships
- Where in our org would Fairness Metrics most often show up unnoticed?
- Which metric, ritual, or contract clause quietly rewards Fairness Metrics?
- If we removed every payoff for Fairness Metrics, what behavior would replace it?
- Who benefits when Fairness Metrics persists — and who pays the cost?
- People defend the status quo using the language of fairness metrics.
- Decisions cluster around the easiest narrative rather than the strongest evidence.
- New data changes the slide deck but not the decision.
- Anyone naming the pattern is treated as the problem.
Every Atlas entry is a node in a knowledge graph. See the related rail below to follow the connections.
See Fairness Metrics through 5 lenses
Each layer of the Incentives OS reframes this concept with its own thinkers, vocabulary, and diagnostic question.
- Layer 6Evolutionary Psychology
What ancestral instinct is being triggered?
- Layer 8Organizational Psychology
What is the org actually rewarding — versus claiming to reward?
- Layer 11Economics & Mechanism Design
Who pays, who is paid, and what does the price signal hide?
- Layer 15AI & Alignment
What proxy reward is the AI optimizing — and what is it ignoring?
- Layer 21Mental Models & Mastery
Which model — or stack of models — are we missing here?
Do you actually know Fairness Metrics?
Three quick questions. Result is saved into your review streak — come back when the term is due to lock it in.
Which best describes Fairness Metrics?
Worked example, counter-example & concept map
On-demand AI analysis grounded in the Lab's research. Cached on your device after first run.
When you encounter Fairness Metrics, your insula registers the body's discomfort before your mind can name it — that 'something's off' feeling is data, not noise.
Disgust, fairness, gut-feel, interoception (sensing your own body). Why an obviously rational deal can feel viscerally wrong. Why fairness violations make you queasy.
See Insula in the Brain Atlas →Picked for you, from the Atlas
Ranked by shared learning paths, overlapping chips, and what you've saved.
When the agent acts, who's responsible?
Categorizing AI use cases by risk level.
Systematic skew in model behavior across groups.
Testing model behavior on hypothetical alternate inputs.
Adding noise to data to protect individual privacy.
Training models across devices without centralizing data.
Send the card, not just the link
A pre-rendered social card with the title, eyebrow, and URL. Copy the link, post it anywhere, or download the SVG for slides.
More definitions to follow
Every term in the Atlas connects to a dozen others. Pick any of these and see where it takes you.
Psychological distance shifts thinking between abstract and concrete.
Reasoning in distributions — ranges and probabilities — rather than points.
Assuming that because B followed A, A caused B.
Hard tactics use pressure and authority; soft tactics use rapport, reasoning, and inspiration.
Adults move through orders of mind: socialized → self-authoring → self-transforming.
Frequent evaluation amplifies loss aversion and produces overly conservative behavior.
Choosing to restrict your future options now, to avoid making a worse choice later.
In any dispute, the intensity of feeling is inversely proportional to the value of the stakes.
Past investment is irrelevant to future decisions.
Criteria for a workable outcome: stated positively, in your control, sensory-specific, ecological, and worth the cost.
Believing something is true because of the consequences of its truth.
Adding manpower to a late software project makes it later.