Work

Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models

Year: 2016
Type: preprint
Abstract: Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite potential gains in productivity and efficiency, several potential problems have yet to be addressed, particularly the potential for unintentional discrimination. We present an iterative procedure, based on orthogonal projection of input attributes, for enabling interpretability of black-box predictive models. Through our iterative procedure, one can quantify the relative dependence of a black-box model on its input attributes.The relative significance of the inputs to a predictive model can then be used to assess the fairness (or discriminatory extent) of such a model.
Language: English
Open Access status: green
OpenAlex ID: W2563486500
Cites: 10
Cited by: 70
Related to: 10