Towards the Right Kind of Fairness in AI

To implement fair machine learning in a sustainable way, identifying the right fairness definition is key. However, fairness is a concept of justice, and various definitions exist. Some of them are in conflict with each other and there is no uniformly accepted notion of fairness. The most appropriate fairness definition for an artificial intelligence system is often a matter of application and the right choice depends on ethical standards and legal requirements. In the absence of officially binding rules, the objective of this document is to structure the complex landscape of existing fairness definitions. We propose the "Fairness Compass", a tool which formalises the selection process and makes identifying the most appropriate fairness metric for a given system a simple, straightforward procedure. We further argue that documenting the reasoning behind the respective decisions in the course of this process can help to build trust from the user through explaining and justifying the implemented fairness.