City Research Online

Abstract

Indirect discrimination and fairness are major concerns in algorithmic models. This is particularly true in insurance, where protected policyholder attributes are not allowed to be used for insurance pricing. Simply disregarding protected policyholder attributes is not an appropriate solution, as this still allows for the possibility of inferring protected attributes from non-protected covariates. Such inference leads to so-called proxy or indirect discrimination. Though proxy discrimination is qualitatively different from the group fairness concepts in the machine learning literature, group fairness criteria have been proposed to control the impact of protected attributes on the calculation of insurance prices. The purpose of this paper is to discuss the differences between, on the one hand, direct and indirect discrimination in insurance and, on the other, the most popular group fairness axioms. In particular, we show that one does not imply the other, as these concepts are materially different. Furthermore, we discuss input data pre-processing and model post-processing methods that achieve both discrimination-free insurance prices and group fairness by demographic parity. The main tool in these methods is the theory of optimal transport.

Publication Type:	Monograph (Working Paper)
Additional Information:	Copyright, the authors, 2023.
Publisher Keywords:	Discrimination, indirect discrimination, proxy discrimination, fairness, protected attributes, discrimination-free, unawareness, group fairness, demographic parity, statistical parity, independence axiom, equalized odds, separation axiom, predictive parity, sufficiency axiom, input pre-processing, output post-processing, optimal transport, Wasserstein distance
Subjects:	H Social Sciences > HG Finance H Social Sciences > HN Social history and conditions. Social problems. Social reform
Departments:	Bayes Business School > Actuarial Science & Insurance

Export

Downloads