Kush R. Varshney is a distinguished research scientist and manager with IBM Research – T. J. Watson Research Center, where he leads the machine learning group in the Foundations of Trustworthy AI department. AI Fairness 360 is an extensible open-source toolkit designed to help data science practitioners examine, report, and mitigate unwanted discrimination and bias in machine learning models throughout the artificial intelligence application lifecycle. Along with its companion toolkits AI Explainability 360, Adversarial Robustness 360, Uncertainty Quantification 360, AI Privacy 360, Causal Inference 360, and AI FactSheets 360, AI Fairness 360 is one component — coupled with inclusive governance practices that center the most vulnerable members of society — for working toward automated decision-making systems that are worthy of society’s trust. Applications of the toolkit include decision-making in employment, credit, health care, educational assessment, and criminal justice.

Further Activities to have a look at