A Python package to assess and improve fairness of machine learning models.
Open source
24 alternativesAIF360
AIF360 provides fairness metrics and explanations for datasets and models, along with algorithms to mitigate bias.
About AIF360
AIF360 is an open-source library, available in Python and R, for detecting and mitigating bias in machine learning models and datasets. It is intended for use across the AI application lifecycle. The package includes metrics for testing datasets and models for bias, explanations for those metrics, and algorithms for reducing bias in datasets and models. The project states that it is designed to move algorithmic fairness research into practice in areas such as finance, human capital management, healthcare, and education.
The Python package is installed with pip from PyPI or within a conda environment. The project lists supported Python versions 3.10 to 3.13 on macOS, Ubuntu, and Windows. It requires specific versions of many Python packages, which may conflict with other projects, so the project recommends a virtual environment. The source states that the library is still in development. It also notes that the number of available metrics and algorithms can make it hard to choose the right one for a given use case, and it links to guidance material for that choice.
Key features
- Group fairness metrics based on selection rates and error rates
- Sample distortion metrics for datasets
- Generalized Entropy Index and differential fairness metrics
- Bias scan using multi-dimensional subset scan
- Fifteen listed bias mitigation algorithms for datasets and models
- Designed for extension with new metrics, explainers, and debiasing algorithms
Best for: Data scientists and researchers who need to test machine learning models and datasets for bias and apply mitigation methods in Python or R.
Good for
- Open source
- Combines fairness metrics, explanations for those metrics, and mitigation algorithms in one library
- Available in both Python and R
Watch out for
- The source states that the library is still in development
- The source notes that choosing appropriate metrics and algorithms can be confusing
- Requires specific versions of many Python packages, which may conflict with other projects
AIF360 at a glance
- Website
- github.com/Trusted-AI/AIF360
- 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 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
AIF360 alternatives
Tools and sites you could use instead, ranked by how closely they match.
AutoViz automatically creates visualizations for datasets of different sizes from a single line of code.
Open source
24 alternatives
pytorch tabular provides a unified framework for deep learning models on tabular data.
Open source
24 alternatives
Ultralytics supports detection, segmentation, image classification, pose estimation, and tracking across YOLO model versions.
Open source
24 alternatives
PySS3 supports interpretable text classification with SS3 and visualization tools for explainable AI.
Open source
24 alternatives
NALP covers Natural Adversarial Language Processing through a dedicated library.
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
AIF360 FAQ
Which Python versions are supported?
The project lists Python 3.10 to 3.13 on macOS, Ubuntu, and Windows.
How do I install the latest stable Python package?
Run pip install aif360 to install the latest stable version from PyPI.
How can I get in touch with the project?
The project invites contact through Slack, and the source links to an invitation.
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.