Desiderata for Explainable AI in statistical production systems of the European Central Bank

TL;DR

This paper defines user-centric desiderata for explainable AI tailored to the needs of statistical production systems at the European Central Bank, linking them to user roles and practical use cases.

Contribution

It introduces clear, user-focused explainability requirements and connects them to specific techniques, grounded in real-world central banking data scenarios.

Findings

Identified key explainability needs for ECB's statistical systems

Linked user roles to specific explainability techniques

Provided practical examples from central bank data processes

Abstract

Explainable AI constitutes a fundamental step towards establishing fairness and addressing bias in algorithmic decision-making. Despite the large body of work on the topic, the benefit of solutions is mostly evaluated from a conceptual or theoretical point of view and the usefulness for real-world use cases remains uncertain. In this work, we aim to state clear user-centric desiderata for explainable AI reflecting common explainability needs experienced in statistical production systems of the European Central Bank. We link the desiderata to archetypical user roles and give examples of techniques and methods which can be used to address the user's needs. To this end, we provide two concrete use cases from the domain of statistical data production in central banks: the detection of outliers in the Centralised Securities Database and the data-driven identification of data quality checks for the Supervisory Banking data system.