Holistic Explainable AI (H-XAI): Extending Transparency Beyond Developers in AI-Driven Decision Making

TL;DR

H-XAI is a comprehensive framework that enhances transparency in AI decision-making by involving stakeholders through interactive, causality-based explanations, addressing bias and fairness in real-world applications.

Contribution

It introduces a novel holistic approach combining causality and post-hoc explanations for stakeholder-aligned AI transparency beyond traditional developer-focused methods.

Findings

Supports stakeholder engagement in AI explanations

Effectively reveals model bias and instability

Improves accountability in sociotechnical systems

Abstract

As AI systems increasingly mediate decisions in domains such as credit scoring and financial forecasting, their lack of transparency and bias raises critical concerns for fairness and public trust. Existing explainable AI (XAI) approaches largely serve developers, focusing on model justification rather than the needs of affected users or regulators. We introduce Holistic eXplainable AI (H-XAI), a framework that integrates causality-based rating methods with post-hoc explanation techniques to support transparent, stakeholder-aligned evaluation of AI systems deployed in online decision contexts. H-XAI treats explanation as an interactive, hypothesis-driven process, allowing users, auditors, and organizations to ask questions, test hypotheses, and compare model behavior against automatically generated random and biased baselines. By combining global and instance-level explanations, H-XAI helps communicate model bias and instability that shape everyday digital decisions. Through case studies in credit risk assessment and stock price prediction, we show how H-XAI extends explainability beyond developers toward responsible and inclusive AI practices that strengthen accountability in sociotechnical systems.