Python package which helps to debug machine learning classifiers and explain their predictions.
Open source
24 alternativesFairlearn
A Python package to assess and improve fairness of machine learning models.
About Fairlearn
Fairlearn is an open-source Python package for assessing and improving the fairness of machine learning models. It uses a group fairness framework focused on harms to people, including allocation harms (when AI systems withhold opportunities, resources, or information) and quality-of-service harms (when a system performs worse for some groups than others). The package provides metrics to evaluate which groups are negatively impacted by a model, as well as algorithms to mitigate unfairness under several common fairness definitions. It also includes example Jupyter notebooks, a user guide, and API reference documentation to support users.
Key features
- Fairness metrics to assess group-level model impacts
- Mitigation algorithms for common fairness definitions
- Example Jupyter notebooks for usage guidance
- Group fairness framework for allocation and quality-of-service harms
- Tools to compare models via fairness and accuracy metrics
- pip installation for easy setup
Best for: Data scientists and AI system developers seeking to evaluate and mitigate machine learning model unfairness.
Good for
- Open-source and freely available for use and modification
- Combines fairness assessment metrics and mitigation algorithms in one package
- Includes example notebooks and comprehensive user guides for learning
Watch out for
- Fairness is a sociotechnical challenge not fully captured by quantitative metrics
- Many common fairness metrics cannot be satisfied simultaneously
- Notebooks from the main branch may not be compatible with pip-installed versions
Fairlearn at a glance
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Fairlearn alternatives
Tools and sites you could use instead, ranked by how closely they match.
nilearn provides Python tools for machine learning and neuroimaging analysis.
Open source
24 alternatives
An open source Python library for drift detection in machine learning systems.
Open source
24 alternatives
AIF360 provides fairness metrics and explanations for datasets and models, along with algorithms to mitigate bias.
Open source
24 alternatives
Feature Engine provides Python tools for feature engineering and selection that are compatible with scikit-learn.
Open source
24 alternatives
modAL provides a modular active learning framework for Python built on top of scikit-learn.
Open source
24 alternativesPopular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
Fairlearn FAQ
How does Fairlearn define unfairness in AI systems?
Fairlearn defines unfairness as harms to people, including allocation harms and quality-of-service harms, evaluated via group fairness.
What core components does the Fairlearn package include?
The package includes fairness assessment metrics and mitigation algorithms for machine learning models.
Where can users get support for using Fairlearn?
Users can ask questions on Stack Overflow with the fairlearn tag or join the project's Discord community.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.