Exploring Commonalities in Explanation Frameworks: A Multi-Domain Survey Analysis

TL;DR

This paper surveys expert and practitioner perspectives across medical, retail, and energy domains to identify universal elements of explainable AI. It emphasizes genetic programming and symbolic expressions as interpretable representations, and highlights feature importance and counterfactual explanations as core components. Through interviews and questionnaires, it reveals a general preference for explainability over marginal accuracy, while proposing a two-module XAI tool—Counterfactual and Global Importance—for cross-domain applicability. The study outlines practical guidelines and points to future work on NLP-driven interactive explanations and expanded domain deployment. The findings aim to guide the development of an adaptable GP-based explainability tool that supports decision-making without replacing domain expertise.

Abstract

This study presents insights gathered from surveys and discussions with specialists in three domains, aiming to find essential elements for a universal explanation framework that could be applied to these and other similar use cases. The insights are incorporated into a software tool that utilizes GP algorithms, known for their interpretability. The applications analyzed include a medical scenario (involving predictive ML), a retail use case (involving prescriptive ML), and an energy use case (also involving predictive ML). We interviewed professionals from each sector, transcribing their conversations for further analysis. Additionally, experts and non-experts in these fields filled out questionnaires designed to probe various dimensions of explanatory methods. The findings indicate a universal preference for sacrificing a degree of accuracy in favor of greater explainability. Additionally, we highlight the significance of feature importance and counterfactual explanations as critical components of such a framework. Our questionnaires are publicly available to facilitate the dissemination of knowledge in the field of XAI.

Figures (3)

• Figure 1: Insights into doctors' preferences for medical case derived from the questionnaire.
• Figure 2: Insights into online retail decision-makers preferences derived from the questionnaire.
• Figure 3: The insights from the energy questionnaire from operational and facility managers