Extended Empirical Validation of the Explainability Solution Space

TL;DR

This paper extends the validation of the Explainability Solution Space (ESS) across different domains, demonstrating its adaptability and effectiveness as a general decision-support tool for explainable AI in complex socio-technical systems.

Contribution

It introduces a heterogeneous urban resource allocation system and evaluates ESS in this new context, showing its domain-independence and adaptability.

Findings

ESS rankings are not domain-specific

ESS adapts systematically to governance roles and stakeholder configurations

Results reinforce ESS as a generalizable decision-support instrument

Abstract

This technical report provides an extended validation of the Explainability Solution Space (ESS) through cross-domain evaluation. While initial validation focused on employee attrition prediction, this study introduces a heterogeneous intelligent urban resource allocation system to demonstrate the generality and domain-independence of the ESS framework. The second case study integrates tabular, temporal, and geospatial data under multi-stakeholder governance conditions. Explicit quantitative positioning of representative XAI families is provided for both contexts. Results confirm that ESS rankings are not domain-specific but adapt systematically to governance roles, risk profiles, and stakeholder configurations. The findings reinforce ESS as a generalizable operational decision-support instrument for explainable AI strategy design across socio-technical systems.