Fairness

Counterfactual fairness ensures AI decisions are unbiased by considering how outcomes would change under different circumstances.

Demographic parity ensures equal outcomes across different demographic groups in AI decision-making.

Equalized Odds is a fairness criterion ensuring equal true positive and false positive rates across different groups.

Fairness constraints are guidelines ensuring AI systems treat all individuals equitably, minimizing bias in outcomes.

Group Fairness ensures that AI systems treat different demographic groups equitably.

Individual fairness ensures similar individuals receive similar treatment in AI systems.

Pre-Processing Fairness refers to techniques that address bias in data before it is used for training AI models.