EqualityML: Open-source fair ML for everyone
Develop and fine tune ML models to detect bias and unfairness using bias mitigation methods and fairness metrics. Built for data scientists and ML engineers.
Equality AI
Let's end algorithmic bias together!
Equality AI is a public-benefit corporation dedicated to providing ML developers with evidence-based tools to end algorithmic bias. Our tools are built by developers for developers. So, we know that developers want their models to be fair, but we also understand that bias is difficult and intimidating.
​
Our opensource repository on GitHub provides tools and guidance on how to include fairness and bias mitigation methods to model fitting to safeguard the humans on the receiving end of machine learning models.​​
​​
Features
​​
Pre-processing workflow guidance:
​
-
Fairness Metric Selection Questionnaire and Decision Tree​ to guide you through your use-case
-
Fairness Metrics and Bias Mitigation methods​ to use in your model development
-
23 fairness metric evaluation methods
-
13 bias mitigation methods
-
-
Compute model results and fairness metric after bias mitigation methods
-
Compare model results and fairness metrics before and after mitigation
​
​
Visit GitHub and give it a try! If you like what we're doing please give us a !
