---
title: "Fairness, Accountability and the Limits of a Model"
description: "A model trained on past decisions reproduces the pattern in them, including the parts nobody would defend out loud. Several reasonable definitions of fairness cannot all hold at once, so a team has to"
canonical: https://lightmysky.com/learn/computing/fairness-accountability-and-the-limits-of-a-model-mt_tTh4WtAyk5
source: https://lightmysky.com/learn/computing/fairness-accountability-and-the-limits-of-a-model-mt_tTh4WtAyk5.md
retrieved: 2026-09-12
---

> **Agent view.** This is the Markdown twin of the page, for tools and assistants.
> When to use this site, and the call that answers each job: https://lightmysky.com/agent-instructions.md
> API description (OpenAPI 3.1): https://lightmysky.com/openapi.json · Authentication: https://lightmysky.com/auth.md
> Pricing: https://lightmysky.com/pricing.md · Catalog: https://lightmysky.com/llms.txt · Full catalog: https://lightmysky.com/llms-full.txt
> Every machine-readable file on this domain: https://lightmysky.com/.well-known/ai-catalog.json
> Ask for Markdown with `Accept: text/markdown`, a `.md` address, or `?mode=agent`.

# Fairness, Accountability and the Limits of a Model

A model trained on past decisions reproduces the pattern in them, including the parts nobody would defend out loud. Several reasonable definitions of fairness cannot all hold at once, so a team has to choose one, say which, and be able to explain a decision to the person it lands on.

Subject: Computing · Area: Machine Learning · Ages 21 to 22
Page: https://lightmysky.com/learn/computing/fairness-accountability-and-the-limits-of-a-model-mt_tTh4WtAyk5

## Ready when they can

- Show how a model can be accurate overall and much worse for one group
- State two fairness criteria that cannot both hold and say what forces the choice
- Say what a person affected by an automated decision is owed

## Lesson: Accurate overall can still be unfair

A model trained on past decisions copies their pattern, including the parts nobody would defend. Old lending maps drew red lines around neighbourhoods, and a model can relearn those lines without anyone naming them. That is why you audit errors group by group.

**Example.** Your model scores ninety percent overall yet fails half the cases from one neighbourhood. Overall accuracy hides the gap, while a per-group table shows it. The team must say which gap it will close first.

Several fair rules cannot all hold at once, so a team must pick one and say which. Accountability means someone stays answerable for the choice and can explain a decision to the person it lands on. An audit then checks the system kept its promise.

**Tip.** When you fix fairness, name the criterion you chose and what it gives up. A person affected by an automated decision is owed a clear reason and a path to challenge it.

**Recap.** Audit by group, choose one fair rule openly, and stay answerable to every person the model touches.

## Practice

8 questions on this page, each with its working shown.

## Needs first

- [Bias in AI Systems](https://lightmysky.com/learn/computing/bias-in-ai-systems-mt__BbOjiY5A5)
- [Designing Fair AI Rules](https://lightmysky.com/learn/computing/designing-fair-ai-rules-mt_1z-gJBJFlM)
- [Beyond Accuracy: Precision, Recall and the Cost of an Error](https://lightmysky.com/learn/computing/beyond-accuracy-precision-recall-and-the-cost-of-an-error-mt_BHGgZM7tak)
- [Agents That Take Actions, Not Just Answer](https://lightmysky.com/learn/computing/agents-that-take-actions-not-just-answer-mt_D7KzIdIsjb)
- [Deep Learning: Convolution, Sequence and Scale](https://lightmysky.com/learn/computing/deep-learning-convolution-sequence-and-scale-mt_karzGN5JnI)

## Opens up

- [Interpretability: Probes, Features and Circuits](https://lightmysky.com/learn/computing/interpretability-probes-features-and-circuits-mt_C8POKvRkq6)