Casualty Actuarial Society Releases Additional Reports in Race & Insurance Pricing Research Series

The Casualty Actuarial Society (CAS) is pleased to announce the release of a new two-part report that explores ways that actuaries can detect and address potential bias in property and casualty insurance pricing. “Practical Application of Bias Measurement and Mitigation Techniques in Insurance Pricing, Parts 1 & 2” is intended as a practitioners’ guide for actuaries and insurance professionals responsible for building, maintaining, or updating insurance pricing models that satisfy multiple views of fairness.

As part of the CAS Research Paper Series on Race & Insurance Pricing, the report was authored by volunteer members of the CAS Race and Insurance Pricing Research Task Force. The two parts are summarized as follows:

Part 1 - Types of Bias, Imputing Protected Class, and Simple Fairness Tests provides an overview of various types of bias and their relevance to insurance processes, illustrates the use of imputation methods to add protected class labels to an insurance data set, and lays out simple fairness tests that build on three statistical fairness criteria presented in the 2022 CAS paper, “Methods for Quantifying Discriminatory Effects on Protected Classes in Insurance.”

Part 2 - Advanced Fairness Tests, Bias Mitigation, and Non-Modeling Considerations explores fairness analyses that can accommodate some of the key complexities found in insurance pricing data, reviews several technical bias mitigation methods that can be applied at various stages of pricing model development, and discusses non-modeling considerations that can contribute to fairness concerns in insurance pricing.

Launched in 2022, the CAS Research Paper Series on Race & Insurance Pricing has produced a series of  papers that ranges from the topic’s historical foundations to forward-looking solutions for quantifying and addressing potential bias. They also reflect the CAS’s commitment to equipping and empowering actuaries and the broader insurance industry with tools to better understand and address potential bias in insurance pricing.

Four papers in the series were released last fall:

“A Practical Guide to Navigating Fairness in Insurance Pricing” by Jessica Leong, FCAS; Richard Moncher, FCAS; and Kate Jordan

“Regulatory Perspectives on Algorithmic Bias and Unfair Discrimination” by Lauren Cavanaugh, FCAS; Scott Merkord, FCAS; Taylor Davis, FCAS; and David Heppen, FCAS

“Balancing Risk Assessment and Social Fairness: An Auto Telematics Case Study” by Jean-Philippe Boucher, Ph.D. and Mathieu Pigeon, Ph.D.

“Comparison of Regulatory Framework for Non-Discriminatory AI Usage in Insurance,” By David Schraub, FSA; Jing Lang, FSA; Zhibin Zhang, FSA; and Mark A. Sayre, FSA. Produced with the Society of Actuaries.

To view the entire series, visit the CAS Research Paper Series on Race & Insurance Pricing web page.

The CAS invites interested parties to collaborate on future research or educational opportunities on these critical topics to contact diversity@casact.org.