A Discrimination-Free Premium Under a Causal Framework

26 Pages Posted: 20 Apr 2022 Last revised: 23 Apr 2022

See all articles by Carlos Andrés Araiza Iturria

Carlos Andrés Araiza Iturria

University of Waterloo

Mary Hardy

University of Waterloo

Paul Marriott

University of Waterloo - Department of Statistics and Actuarial Science

Date Written: April 8, 2022

Abstract

We examine the discrimination-free premium in Lindholm et al. (2021) within a theoretical causal inference framework, and we consider its societal context, to assess when the pricing formula should be used. We consider the insurance pricing problem through the use of directed acyclic graphs. This particular tool allows us to rigorously define an insurance risk factor in a causal framework. We then use this definition in assessing the appropriate application of the discrimination-free premium through three simplified pricing examples, including a health insurance policy and two personal automobile insurance policies with different coverages. From our findings, we suggest criteria for the application of the discrimination-free premium that is dependent on the risk factors and the social context.

Keywords: Risk and rating factors, directed acyclic graphs, insurance pricing, discrimination-free prices, actuarially fair pricing

JEL Classification: G22, C13

Suggested Citation

Araiza Iturria, Carlos Andrés and Hardy, Mary and Marriott, Paul, A Discrimination-Free Premium Under a Causal Framework (April 8, 2022). Available at SSRN: https://ssrn.com/abstract=4079068 or http://dx.doi.org/10.2139/ssrn.4079068

Carlos Andrés Araiza Iturria (Contact Author)

University of Waterloo ( email )

200 University Avenue West
Waterloo, Ontario N2L 3G1
Canada

Mary Hardy

University of Waterloo ( email )

Waterloo, Ontario N2L 3G1
Canada

Paul Marriott

University of Waterloo - Department of Statistics and Actuarial Science ( email )

200 University Avenue West
Waterloo, Ontario N2L 3G1
Croatia

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
331
Abstract Views
839
Rank
158,582
PlumX Metrics