Mitigating Discrimination in Insurance with Wasserstein Barycenters

TL;DR

This paper introduces a novel method using Wasserstein barycenters to reduce discrimination in insurance risk predictions, addressing biases from historical data and improving fairness without excluding sensitive features.

Contribution

It proposes a new bias mitigation technique with Wasserstein barycenters, offering an alternative to traditional exclusion of sensitive variables in insurance models.

Findings

Effective reduction of bias demonstrated on real insurance data

Wasserstein barycenters improve fairness without sacrificing predictive accuracy

Method provides a practical approach for industry adoption

Abstract

The insurance industry is heavily reliant on predictions of risks based on characteristics of potential customers. Although the use of said models is common, researchers have long pointed out that such practices perpetuate discrimination based on sensitive features such as gender or race. Given that such discrimination can often be attributed to historical data biases, an elimination or at least mitigation is desirable. With the shift from more traditional models to machine-learning based predictions, calls for greater mitigation have grown anew, as simply excluding sensitive variables in the pricing process can be shown to be ineffective. In this article, we first investigate why predictions are a necessity within the industry and why correcting biases is not as straightforward as simply identifying a sensitive variable. We then propose to ease the biases through the use of Wasserstein barycenters instead of simple scaling. To demonstrate the effects and effectiveness of the approach we employ it on real data and discuss its implications.