Intermediate · Safety
Disparate treatment
Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.
TL;DR. When an algorithm explicitly uses sensitive attributes to make different decisions for different population subgroups.
Technical Definition
When an algorithm explicitly uses sensitive attributes to make different decisions for different population subgroups.
How it works
Disparate treatment, also known as explicit bias, happens when an algorithm intentionally uses protected characteristics like race, gender, or religion to make different decisions for different groups. This is a direct form of discrimination. For example, an algorithm that assigns loan approvals differently based on an applicant's ethnicity is practicing disparate treatment.
Related Concepts
- Fairness — The principle that AI systems should treat individuals and groups equitably.
- Bias (ethics/fairness) — Unfair prejudice or favoritism towards certain groups or things, which can influence data, system design, and user interactions.
- Responsible AI (RAI) — A holistic framework encompassing the ethical, legal, and societal implications of AI, promoting trustworthy and beneficial systems.