Demographic Benchmarking: Bridging Socio-Technical Gaps in Bias Detection

TL;DR

This paper presents a demographic benchmarking framework integrated into an AI auditing platform to measure and reduce bias in recommender systems, aiding responsible AI practices and regulatory efforts.

Contribution

It introduces a novel demographic benchmarking framework that measures impact, identifies biases, and monitors drift, enhancing fairness and transparency in AI auditing.

Findings

Defined control datasets for specific demographics.

Compared impacted populations with overall demographics.

Quantified model drift for ongoing monitoring.

Abstract

Artificial intelligence (AI) models are increasingly autonomous in decision-making, making pursuing responsible AI more critical than ever. Responsible AI (RAI) is defined by its commitment to transparency, privacy, safety, inclusiveness, and fairness. But while the principles of RAI are clear and shared, RAI practices and auditing mechanisms are still incipient. A key challenge is establishing metrics and benchmarks that define performance goals aligned with RAI principles. This paper describes how the ITACA AI auditing platform developed by Eticas.ai tackles demographic benchmarking when auditing AI recommender systems. To this end, we describe a Demographic Benchmarking Framework designed to measure the populations potentially impacted by specific AI models. The framework serves us as auditors as it allows us to not just measure but establish acceptability ranges for specific performance indicators, which we share with the developers of the systems we audit so they can build balanced training datasets and measure and monitor fairness throughout the AI lifecycle. It is also a valuable resource for policymakers in drafting effective and enforceable regulations. Our approach integrates socio-demographic insights directly into AI systems, reducing bias and improving overall performance. The main contributions of this study include:1. Defining control datasets tailored to specific demographics so they can be used in model training; 2. Comparing the overall population with those impacted by the deployed model to identify discrepancies and account for structural bias; and 3. Quantifying drift in different scenarios continuously and as a post-market monitoring mechanism.