# Trusted-AI/AIF360

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

Repository: https://github.com/Trusted-AI/AIF360
Canonical: https://ross.abutalabs.com/products/aif360
Homepage: https://aif360.res.ibm.com/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, fairness-ai, fairness, fairness-testing, fairness-awareness-model, bias-detection, bias, bias-correction, bias-reduction, bias-finder, artificial-intelligence, discrimination, ibm-research-ai, ibm-research, machine-learning, deep-learning, codait, trusted-ai, r, python
Last push: 2026-06-15T19:55:33+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 87, release rhythm 8, longevity 100
- inputs: {"age_days": 2933, "days_push": 79, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2857, forks 909 (observed 2026-08-28T04:07:25.920493+00:00)

## What it is
AI Fairness 360 is an open-source Python and R library from IBM Research providing fairness metrics, explanations, and bias mitigation algorithms for datasets and machine learning models. It supports the full AI lifecycle with pre-processing, in-processing, and post-processing debiasing techniques.

## Use cases
- detect bias in a machine learning model
- measure fairness metrics on a dataset
- mitigate discrimination in training data
- check disparate impact of model predictions
- apply debiasing algorithms to a classifier
- audit model fairness for regulated domains like finance or healthcare

## When to choose
- you need a comprehensive, research-backed toolkit of fairness metrics and mitigation algorithms
- you work in Python or R and want extensible bias testing integrated into your ML pipeline
- you need documented, citable fairness techniques from academic literature

## When to avoid
- you need real-time or production-scale low-latency fairness monitoring
- you want a simple one-click solution without understanding fairness metrics
- your project is not Python or R based

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, testing, data-science
- domain: machine-learning, artificial-intelligence, data-science
- platform: python, cross-platform
- tags: fairness, bias-detection, bias-mitigation, responsible-ai, explainability, r-package, algorithms

## Member repositories
- Trusted-AI/AIF360 (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:25.920493+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:36:29.637804+00:00, confidence not recorded.
  - readme: https://github.com/Trusted-AI/AIF360 (fetched 2026-08-28T04:07:25.920493+00:00, sha af8082bfd9e6)
  - registry_pypi: https://pypi.org/pypi/aif360/json (fetched 2026-08-29T09:52:11.733706+00:00, sha 649f70a46fde)
- Data as of 2026-08-30T08:39:29.467469+00:00.