Research map / Label-efficient and robust learning / Recognition and long-tail
Equality of Opportunity in Supervised Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| enforce equal opportunity instead of demographic parity | FICO threshold classifier · FICO credit scores | profit as % of max profit: 69.8 -> 92.8 | Helped |
| enforce equal opportunity instead of equalized odds | FICO threshold classifier · FICO credit scores | profit as % of max profit: 80.2 -> 92.8 | Helped |
| race-blind single threshold instead of per-group | FICO threshold classifier · FICO credit scores | profit as % of max profit: 99.3% of max profit | No clear effect |
| race-blind or max-profit thresholds versus fairness-constrained thresholds | FICO threshold classifier · FICO credit scores | fraction of non-defaulting black applicants qualifying | Hurt |
| demographic parity thresholds | FICO threshold classifier · FICO credit scores | fraction of non-defaulters qualifying by group | Mixed |
Closest papers by meaning
- Accuracy vs. Accuracy: Computational Tradeoffs Between Classification Rates and Utility (NeurIPS 2026 · similarity 0.87)
- On the Impossibility of Non-trivial Accuracy in Presence of Fairness Constraints (AAAI 2022 · similarity 0.85)
- Eliminating Latent Discrimination: Train Then Mask (AAAI 2019 · similarity 0.85)
- On preserving non-discrimination when combining expert advice (NeurIPS 2018 · similarity 0.85)
- Individual Fairness In Strategic Classification (NeurIPS 2025 · similarity 0.83)
- Learning with Selectively Labeled Data from Multiple Decision-makers (ICML 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.