Libr-AI/fairlib
A framework for assessing and improving classification fairness.
This framework helps data scientists and machine learning engineers build more equitable classification models. It takes in structured data, text, or images used for classification tasks and helps identify and reduce biases related to protected characteristics. The output is a more fair and less discriminatory classification model.
No commits in the last 6 months.
Use this if you are developing AI/ML models for applications like hiring, loan approvals, or content moderation and need to ensure your models make fair and unbiased decisions across different demographic groups.
Not ideal if you are looking for a plug-and-play fairness solution without any programming or deep understanding of machine learning concepts.
Stars
33
Forks
9
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jun 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Libr-AI/fairlib"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
fairlearn/fairlearn
A Python package to assess and improve fairness of machine learning models.
Trusted-AI/AIF360
A comprehensive set of fairness metrics for datasets and machine learning models, explanations...
holistic-ai/holisticai
This is an open-source tool to assess and improve the trustworthiness of AI systems.
microsoft/responsible-ai-toolbox
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment...
datamllab/awesome-fairness-in-ai
A curated list of awesome Fairness in AI resources