Fairness of Ratemaking for Catastrophe Insurance: Lessons from Machine Learning

Abstract

Catastrophe insurance is an important element of disaster management. Yet the historic presence of inequalities in insurance, from redlining to pricing disparity, has had a devastating impact on minority communities. While the fairness of insurance ratemaking has been studied in general, we identify a unique challenge for fair ratemaking in catastrophe insurance that sets it apart from other lines of insurance, and for which the literature is still nascent. Drawing upon the recent advances in machine learning for fair data valuation, we reveal striking connections between the two seemingly unrelated problems, and lean on insights from the success of an axiomatic approach in machine learning to mathematically and empirically study the fairness of ratemaking methods for catastrophe insurance. Our results indicate the potential existence of disparate impact against minorities across all existing methods, and point to a unique mathematical solution that can satisfy a few commonly assumed properties of fair ratemaking for catastrophe insurance.

Keywords: Catastrophe Insurance, Machine Learning, Fairness

JEL Classification: G22