aequitas
Bias auditor
Toolkit to audit and mitigate biases in machine learning models
Bias Auditing & Fair ML Toolkit
701 stars
42 watching
116 forks
Language: Python
last commit: about 2 years agoLinked from 4 awesome lists
biasfairnessfairness-testingmachine-bias
jphall663/awesome-machine-learning-interpretability
krzjoa/awesome-python-data-science
datamllab/awesome-fairness-in-aiRelated projects:
| Repository | Description | Stars |
|---|---|---|
 algofairness/blackboxauditing | A software package for auditing and analyzing machine learning models to detect unfair biases | 130 |
 adebayoj/fairml | An auditing toolbox to assess the fairness of black-box predictive models | 361 |
 responsiblyai/responsibly | A toolkit for auditing and mitigating bias in machine learning systems | 96 |
 i-gallegos/fair-llm-benchmark | Compiles bias evaluation datasets and provides access to original data sources for large language models | 115 |
 ethicalml/xai | An eXplainability toolbox for machine learning that enables data analysis and model evaluation to mitigate biases and improve performance | 1,135 |
 privacytrustlab/bias_in_fl | This project investigates how bias can be introduced and spread in machine learning models during federated learning, and aims to detect and mitigate this issue. | 11 |
 nyu-mll/bbq | A dataset and benchmarking framework to evaluate the performance of question answering models on detecting and mitigating social biases. | 92 |
 modeloriented/fairmodels | A tool for detecting bias in machine learning models and mitigating it using various techniques. | 86 |
 koaning/scikit-fairness | A Python library providing tools and algorithms for fairness in machine learning model development | 29 |
 fairlearn/fairlearn | A tool to assess and mitigate unfairness in AI systems, helping developers ensure their models do not disproportionately harm certain groups of people. | 1,974 |
 btschwertfeger/python-cmethods | A collection of bias correction techniques for climate data analysis | 60 |
 visionjo/facerec-bias-bfw | This project provides a data proxy to evaluate bias in facial recognition systems across demographic groups. | 47 |
 cgnorthcutt/cleanlab | A tool for evaluating and improving the fairness of machine learning models | 57 |
 google/ml-fairness-gym | An open-source tool for simulating the long-term impacts of machine learning-based decision systems on social environments | 314 |
 amiratag/datashapley | Calculates fair valuation of individual training data points in machine learning models. | 259 |