fairness-auditing

What problem does it solve?

It helps you determine whether a system that allocates outcomes across groups is equitable by selecting explicit fairness definitions, measuring disparities, and identifying where bias enters.

Core Features & Use Cases

• Fairness-definition scoping: Chooses and documents the fairness criteria (e.g., demographic parity, equal opportunity, predictive parity) and clarifies value trade-offs.
• Data and proxy investigation: Checks for historical bias, label bias, representation gaps, and proxy variables that reconstruct protected attributes.
• Disparity measurement and intersectional analysis: Computes group-level and intersectional disparities, including significance and calibration considerations.
• Mitigation planning: Recommends pre-, in-, and post-processing interventions and assesses likely fairness gains versus accuracy trade-offs.

Quick Start

Ask the AI to perform a fairness audit for your allocation system by stating the decision type, affected groups, relevant protected attributes, and the fairness definition(s) you want to test.