Bias & Fairness

Beginner

Understanding and mitigating harmful biases in AI systems.

Last updated: Sep 13, 2026

What is AI Bias?

AI bias occurs when machine learning systems produce systematically unfair outcomes for certain groups. Biases can arise from training data, model design, or deployment context.

Sources of Bias

Where bias enters AI systems.

Training Data

Historical biases in the data are learned by the model.

Label Bias

Human annotators introduce their own biases.

Selection Bias

Training data doesn't represent the deployment population.

Measurement Bias

Proxies used for measurement encode bias.

Types of Bias

Common categories of bias in AI systems.

Stereotyping

Reinforcing harmful stereotypes about groups.

Erasure

Underrepresenting or ignoring certain groups.

Disparate Impact

Different outcomes for different groups.

Mitigation Strategies

Approaches to reduce bias.

Diverse Data

Ensure training data represents all relevant groups.

Bias Auditing

Systematically test for bias across demographics.

Fairness Constraints

Incorporate fairness metrics into training.

⚖️

Group error-rate explorer

Inspect a constructed dataset and the consequences of a shared threshold.

Compare error rates, not a “fairness score”

Constructed dataset: two groups, six cases each. Scores and reference outcomes are visible. Move the shared decision threshold and compare errors. The labels are assumed correct here; real label quality and the choice of groups require separate scrutiny.

Group A

ScoreReference positiveSelected
90YesYes
70YesYes
40YesNo
60NoYes
30NoNo
10NoNo
True-positive rate
2/3 = 67%
False-positive rate
1/3 = 33%
Selection rate
3/6 = 50%

Group B

ScoreReference positiveSelected
80YesYes
50YesYes
20YesNo
70NoYes
40NoNo
10NoNo
True-positive rate
2/3 = 67%
False-positive rate
1/3 = 33%
Selection rate
3/6 = 50%

TPR = selected positives / all reference positives. FPR = selected negatives / all reference negatives. Selection rate = selected / all cases. No single rate determines whether a decision system is fair; examine purpose, harms, uncertainty and data collection.

Key Takeaways

  • 1Bias is often inherited from training data
  • 2Different fairness metrics can conflict—choose carefully
  • 3Regular auditing is essential for deployed systems
  • 4Bias mitigation is an ongoing process, not a one-time fix