--- title: "Fairness, Accountability and the Limits of a Model" description: "Models trained to imitate past decisions may repeat discrimination. Compare outcomes and errors by group. Demographic parity and equalized odds can conflict when eligible shares differ and the shared " 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: 2026-11-12 --- > **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 Models trained to imitate past decisions may repeat discrimination. Compare outcomes and errors by group. Demographic parity and equalized odds can conflict when eligible shares differ and the shared true positive rate exceeds the shared false positive rate. Teams should state their criteria, remain responsible and provide explanations and ways to challenge decisions. 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 - Define demographic parity and equalized odds, and explain their conflict when eligible shares differ and the shared true positive rate exceeds the shared false positive rate - Describe ethical responsibility, explanations, challenge routes and meaningful human review, while distinguishing these standards from legal rights that vary by place and use ## Lesson: A model can be accurate overall and still be unfair Regression checks numerical predictions with residuals. Here we audit loan approvals, rejections and their errors by group. Models trained to imitate past decisions may repeat unfair patterns. Redlining is discriminatory restriction of loans or insurance by neighbourhood, often excluding racial or ethnic minority communities. Location can carry group information even after group labels are removed, so removing a label alone may leave bias. Earlier approval does not prove eligibility. **Example.** In an invented audit, a model gets 800 of 800 cases correct in group A and 100 of 200 in group B. Overall accuracy is (800 + 100) / 1,000 = 90%. Group accuracies are 100% and 50%. Divide each group's correct cases by its own total. The larger group dominates the overall score. Also separate incorrect approvals from incorrect rejections, since they can cause different harms. *(drawing: A supplies 800 cases and B supplies 200. Combining them hides the 50-percentage-point accuracy gap.)* For a loan audit, define eligibility on a justified basis. Approval is the positive prediction. True positive rate (t) is approvals among eligible applicants divided by all eligible applicants. False positive rate (f) is approvals among ineligible applicants divided by all ineligible applicants. Demographic parity requires equal overall approval rates across groups. Equalized odds requires equal t and equal f across groups. **Example.** Let p be the eligible share, t the true positive rate and f the false positive rate. Approval share is tp + f(1 - p) = f + (t - f)p; tp means t times p. Equalized odds requires shared t and f. If p differs and t > f, approval shares differ, so demographic parity (equal approval shares) fails. For p = 0.2 and 0.6, t = 0.8 and f = 0.1 give 24% and 52%. Equal p or shared t = f allows both criteria. Neither settles every fairness question. *(drawing: Both groups have t = 80% and f = 10%. Their eligible shares differ, producing different overall approval rates.)* Accountability means a named person or team remains responsible for decisions. An audit checks evidence against stated rules; it does not prove every decision is fair. As an ethical standard, affected people should get an understandable reason, a way to challenge it and human review with authority to change it. Legal rights vary by place and use. Report the fairness criteria chosen, the measured rates and any criteria not met. **Recap.** Use each rate's correct denominator. Name the fairness criteria and their limits. Keep people responsible, with explanations and meaningful review. *Lesson, questions and study cards written for this dataset. Audit numbers and lending scenarios are hypothetical. Background study included the supplied textbook records on accountability, redlining, stakeholders and ethical values.* ## Practice 8 questions on this page, each with its working shown. ## Needs first - [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) ## Optional connections - [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) - [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)