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

TL;DR

This paper surveys explanation frameworks across multiple domains, integrating insights into a software tool using GP algorithms, and highlights the importance of explainability features like feature importance and counterfactuals.

Contribution

It introduces a universal explanation framework based on survey insights, implemented with GP algorithms, emphasizing explainability over accuracy and including publicly available questionnaires.

Findings

Universal preference for explainability over accuracy

Feature importance and counterfactual explanations are critical

Insights are incorporated into a software tool using GP algorithms

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.