Learning Fair Decisions with Factor Models: Applications to Annuity Pricing

2024-12-05

AI Summary

To address group bias inherent in factor models for annuity pricing, this paper proposes a decision-layer modeling framework incorporating fairness regularization—introducing the first formal definition and implementation of Decision Error Parity (DEP), which constrains the expected pricing error to be equal across protected groups (e.g., gender, race). Unlike existing approaches that impose fairness constraints solely at the prediction layer, our method embeds DEP directly into the decision layer of the factor model, preserving business interpretability while jointly optimizing fairness and predictive accuracy. Empirical evaluation on Australian mortality data demonstrates that the proposed method reduces inter-group decision error disparity by up to 62%, while simultaneously improving overall prediction accuracy. It outperforms both conventional actuarial factor models and state-of-the-art fair factor models in comprehensive performance metrics.

Technology Category

• Machine Learning: Ethics, Bias, and Fairness
• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Game Theory and Economic Paradigms: Fair Division

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

Fairness-aware statistical learning is essential for mitigating discrimination against protected attributes such as gender, race, and ethnicity in data-driven decision-making. This is particularly critical in high-stakes applications like insurance underwriting and annuity pricing, where biased business decisions can have significant financial and social consequences. Factor models are commonly used in these domains for risk assessment and pricing; however, their predictive outputs may inadvertently introduce or amplify bias. To address this, we propose a Fair Decision Model that incorporates fairness regularization to mitigate outcome disparities. Specifically, the model is designed to ensure that expected decision errors are balanced across demographic groups - a criterion we refer to as Decision Error Parity. We apply this framework to annuity pricing based on mortality modelling. An empirical analysis using Australian mortality data demonstrates that the Fair Decision Model can significantly reduce decision error disparity while also improving predictive accuracy compared to benchmark models, including both traditional and fair factor models.

Problem

• Mitigate bias in factor models for fair decisions
• Ensure balanced decision errors across demographic groups
• Improve annuity pricing accuracy with fairness regularization

Innovation

• Fair Decision Model with fairness regularization
• Ensures Decision Error Parity across groups
• Improves accuracy and reduces disparity