Audience-dependent explanations for AI-based risk management tools : a survey

Hadji Misheva, Branka; Jaggi, David; Posth, Jan-Alexander; Gramespacher, Thomas; Osterrieder, Joerg

doi:10.3389/frai.2021.794996

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-23852

Publication type:	Article in scientific journal
Type of review:	Peer review (publication)
Title:	Audience-dependent explanations for AI-based risk management tools : a survey
Authors:	Hadji Misheva, Branka Jaggi, David Posth, Jan-Alexander Gramespacher, Thomas Osterrieder, Joerg
et. al:	No
DOI:	10.3389/frai.2021.794996 10.21256/zhaw-23852
Published in:	Frontiers in Artificial Intelligence
Volume(Issue):	4
Issue:	794996
Issue Date:	2021
Publisher / Ed. Institution:	Frontiers Research Foundation
ISSN:	2624-8212
Language:	English
Subjects:	Explainable AI; Responsible AI; Artificial intelligence; Machine learning; Finance; Risk management
Subject (DDC):	006: Special computer methods 332: Financial economics
Abstract:	Artificial Intelligence (AI) is one of the most sought-after innovations in the financial industry. However, with its growing popularity, there also is the call for AI-based models to be understandable and transparent. However, understandably explaining the inner mechanism of the algorithms and their interpretation is entirely audience-dependent. The established literature fails to match the increasing number of explainable AI (XAI) methods with the different stakeholders’ explainability needs. This study addresses this gap by exploring how various stakeholders within the Swiss financial industry view explainability in their respective contexts. Based on a series of interviews with practitioners within the financial industry, we provide an in-depth review and discussion of their view on the potential and limitation of current XAI techniques needed to address the different requirements for explanations.
URI:	https://digitalcollection.zhaw.ch/handle/11475/23852
Fulltext version:	Published version
License (according to publishing contract):	CC BY 4.0: Attribution 4.0 International
Departement:	School of Engineering School of Management and Law
Organisational Unit:	Institute of Data Analysis and Process Design (IDP) Institute of Wealth & Asset Management (IWA)
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
2021_HadjiMisheva-etal_AI-based-risk-management-tools.pdf		837.98 kB	Adobe PDF	View/Open

Show full item record

Hadji Misheva, B., Jaggi, D., Posth, J.-A., Gramespacher, T., & Osterrieder, J. (2021). Audience-dependent explanations for AI-based risk management tools : a survey. Frontiers in Artificial Intelligence, 4(794996). https://doi.org/10.3389/frai.2021.794996

Hadji Misheva, B. et al. (2021) ‘Audience-dependent explanations for AI-based risk management tools : a survey’, Frontiers in Artificial Intelligence, 4(794996). Available at: https://doi.org/10.3389/frai.2021.794996.

B. Hadji Misheva, D. Jaggi, J.-A. Posth, T. Gramespacher, and J. Osterrieder, “Audience-dependent explanations for AI-based risk management tools : a survey,” Frontiers in Artificial Intelligence, vol. 4, no. 794996, 2021, doi: 10.3389/frai.2021.794996.

HADJI MISHEVA, Branka, David JAGGI, Jan-Alexander POSTH, Thomas GRAMESPACHER und Joerg OSTERRIEDER, 2021. Audience-dependent explanations for AI-based risk management tools : a survey. Frontiers in Artificial Intelligence. 2021. Bd. 4, Nr. 794996. DOI 10.3389/frai.2021.794996

Hadji Misheva, Branka, David Jaggi, Jan-Alexander Posth, Thomas Gramespacher, and Joerg Osterrieder. 2021. “Audience-Dependent Explanations for AI-Based Risk Management Tools : A Survey.” Frontiers in Artificial Intelligence 4 (794996). https://doi.org/10.3389/frai.2021.794996.

Hadji Misheva, Branka, et al. “Audience-Dependent Explanations for AI-Based Risk Management Tools : A Survey.” Frontiers in Artificial Intelligence, vol. 4, no. 794996, 2021, https://doi.org/10.3389/frai.2021.794996.