Testing software for non-discrimination: an updated and extended audit in the Italian car insurance domain

2025-02-10

AI Summary

This study investigates algorithmic discrimination in Italian auto insurance pricing, focusing on the impact of protected attributes—particularly country of birth—on pricing fairness. We conduct a large-scale black-box audit and controlled experiments across 12 major online insurance platforms, employing ANOVA and logistic regression for rigorous statistical significance testing. Our analysis reveals, for the first time empirically, that country of birth remains a primary discriminatory factor, inducing up to a 37% premium differential. Moreover, certain applicants—especially those lacking local driving history—are systematically denied quotes altogether, exposing systemic exclusion violating opportunity fairness. By expanding both the dimensionality of tested variables and the scale of empirical evaluation, this work establishes a reproducible methodological framework for auditing insurance algorithms under the EU AI Act, delivering critical empirical evidence to inform regulatory compliance and fairness-aware algorithm design.

Technology Category

• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Machine Learning: Ethics, Bias, and Fairness
• Humans and AI: AI for Accessibility

Application Category

• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Context. As software systems become more integrated into society's infrastructure, the responsibility of software professionals to ensure compliance with various non-functional requirements increases. These requirements include security, safety, privacy, and, increasingly, non-discrimination. Motivation. Fairness in pricing algorithms grants equitable access to basic services without discriminating on the basis of protected attributes. Method. We replicate a previous empirical study that used black box testing to audit pricing algorithms used by Italian car insurance companies, accessible through a popular online system. With respect to the previous study, we enlarged the number of tests and the number of demographic variables under analysis. Results. Our work confirms and extends previous findings, highlighting the problematic permanence of discrimination across time: demographic variables significantly impact pricing to this day, with birthplace remaining the main discriminatory factor against individuals not born in Italian cities. We also found that driver profiles can determine the number of quotes available to the user, denying equal opportunities to all. Conclusion. The study underscores the importance of testing for non-discrimination in software systems that affect people's everyday lives. Performing algorithmic audits over time makes it possible to evaluate the evolution of such algorithms. It also demonstrates the role that empirical software engineering can play in making software systems more accountable.

Problem

• Audit pricing algorithms for non-discrimination
• Extend tests on demographic variables impact
• Highlight persistent discrimination in insurance pricing

Innovation

• Extended black box testing
• Analyzed demographic variables impact
• Audited pricing algorithms evolution