Seven challenges for harmonizing explainability requirements
This work highlights practical implementation issues for regulators and practitioners in finance, but it is incremental as it reviews existing literature without proposing new methods.
The paper addresses the challenge of applying explainable AI (XAI) techniques in the financial services industry to meet diverse regulatory and operational needs, arguing that a highly contextualized approach is necessary based on current technical literature.
Regulators have signalled an interest in adopting explainable AI(XAI) techniques to handle the diverse needs for model governance, operational servicing, and compliance in the financial services industry. In this short overview, we review the recent technical literature in XAI and argue that based on our current understanding of the field, the use of XAI techniques in practice necessitate a highly contextualized approach considering the specific needs of stakeholders for particular business applications.