Audience-Dependent Explanations for AI-Based Risk Management Tools: A Survey

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.

Formal Verification of Tree Ensembles in Safety-Critical Applications

“…In many practical applications of machine learning, the ability to explain why a prediction model arrives at a certain decision is crucial (Hadji Misheva et al, 2021). Although significant progress has been made to understand the intricacies of machine learning systems and how their predictions can be explained (for a comprehensive survey, see e.g., Ras et al, 2022;Kaur et al, 2022), there are still open research questions.…”