FairPilot: Automated Hyperparameter Optimization Through The Lens Of Fairness

Despite the potential benefits of machine learning in high-risk decision-making domains, the deployment of ML is not accessible to practitioners, and there is a risk of discrimination. To establish trust and acceptance of ML in such domains, democratizing ML tools and fairness consideration are crucial. For this reason, I introduce FairPilot, an interactive system designed to promote the responsible development of ML models by exploring a combination of various models, different hyperparameters, and a wide range of fairness definitions. FairPilot allows users to select a set of evaluation criteria and then displays the Pareto frontier of models and hyperparameters as an interactive map. FairPilot is the first system to combine these features, offering a unique opportunity for users to responsibly choose their model.