B1156
Title: Countering racial discrimination in algorithmic lending: A case for model-agnostic interpretation methods
Authors: Parvati Neelakantan - Dublin City University (Ireland) [presenting]
Abstract: In respect to racial discrimination in lending, the usefulness of Global Shapley Value and Shapley-Lorenz methods to attain algorithmic justice is examined. Using 157,269 loan applications during 2017 in New York from the Home Mortgage Disclosure Act data set, we confirm that these methods, consistent with the parameters of a logistic regression model, reveal prima facie evidence of racial discrimination. We show, critically, that these explainable AI methods can enable a financial institution to select an opaque creditworthiness model which blends out-of-sample performance with ethical considerations.