Explaining how your AI system is fair

TL;DR

This paper advocates using decision trees to explain and justify fairness definitions in AI, aiming to enhance transparency, ethical alignment, and trust in AI systems by mapping principles to specific use cases.

Contribution

It introduces a decision tree approach to explain and document fairness choices in AI, facilitating ethical alignment and transparency for practitioners and users.

Findings

Decision trees can clarify fairness decision processes.

Mapping ethics to fairness improves transparency.

Sharing reasoning enhances trust in AI systems.

Abstract

To implement fair machine learning in a sustainable way, choosing the right fairness objective is key. Since fairness is a concept of justice which comes in various, sometimes conflicting definitions, this is not a trivial task though. The most appropriate fairness definition for an artificial intelligence (AI) system is a matter of ethical standards and legal requirements, and the right choice depends on the particular use case and its context. In this position paper, we propose to use a decision tree as means to explain and justify the implemented kind of fairness to the end users. Such a structure would first of all support AI practitioners in mapping ethical principles to fairness definitions for a concrete application and therefore make the selection a straightforward and transparent process. However, this approach would also help document the reasoning behind the decision making. Due to the general complexity of the topic of fairness in AI, we argue that specifying "fairness" for a given use case is the best way forward to maintain confidence in AI systems. In this case, this could be achieved by sharing the reasons and principles expressed during the decision making process with the broader audience.