A taxonomy of explanations to support Explainability-by-Design
This work addresses the problem of generating explanations for various stakeholders in automated systems, but it is incremental as it builds on existing explainability frameworks.
The paper tackles the need for meaningful explanations in automated decision-making by presenting a taxonomy of explanations with nine dimensions, developed as part of an 'Explainability-by-Design' approach to support compliance and business needs.
As automated decision-making solutions are increasingly applied to all aspects of everyday life, capabilities to generate meaningful explanations for a variety of stakeholders (i.e., decision-makers, recipients of decisions, auditors, regulators...) become crucial. In this paper, we present a taxonomy of explanations that was developed as part of a holistic 'Explainability-by-Design' approach for the purposes of the project PLEAD. The taxonomy was built with a view to produce explanations for a wide range of requirements stemming from a variety of regulatory frameworks or policies set at the organizational level either to translate high-level compliance requirements or to meet business needs. The taxonomy comprises nine dimensions. It is used as a stand-alone classifier of explanations conceived as detective controls, in order to aid supportive automated compliance strategies. A machinereadable format of the taxonomy is provided in the form of a light ontology and the benefits of starting the Explainability-by-Design journey with such a taxonomy are demonstrated through a series of examples.