Fairkit, fairkit, on the wall, who’s the fairest of them all? Supporting fairness-related decision-making

•Fairkit-learn is an interactive toolkit for helping engineers reason about and understand fairness in machine learning.•Fairkit-learn computes and visualizes the Pareto-optimal frontier of models that describes fairness and quality trade-offs.•Users with fairkit-learn better balance fairness and accuracy than with scikit-learn and IBM AI Fairness 360.•With fairkit-learn, users select models up to 67% more fair and 10% more accurate than with scikit-learn.•Fairkit-learn supports over 70 fairness definition and works with state-of-the-art machine learning tools.