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.
@article{arxiv.2108.05390,
title = {Seven challenges for harmonizing explainability requirements},
author = {Jiahao Chen and Victor Storchan},
journal= {arXiv preprint arXiv:2108.05390},
year = {2021}
}
Comments
5 pages; Spotlight paper at the ACM SIGKDD Workshop on Machine Learning in Finance 2021