Fairness versus profitability in automated machine learning

Abstract We consider the application of automated machine learning models in a real credit lending platform, and empirically study whether the trade-off between fairness and profitability can be improved by means of fairness processing methods. Fairness is evaluated along the principle of Separation, while profitability is computed as a loan-level profit function, aggregated at the portfolio level. The empirical findings reveal that none of the considered fairness processors reduces bias without an increase in costs, in the form of higher false positive or of higher false negative rates.