Decision support for efficient XAI services - A morphological analysis, business model archetypes, and a decision tree

Abstract

The black-box nature of Artificial Intelligence (AI) models and their associated explainability limitations create a major adoption barrier. Explainable Artificial Intelligence (XAI) aims to make AI models more transparent to address this challenge. Researchers and practitioners apply XAI services to explore relationships in data, improve AI methods, justify AI decisions, and control AI technologies with the goals to improve knowledge about AI and address user needs. The market volume of XAI services has grown significantly. As a result, trustworthiness, reliability, transferability, fairness, and accessibility are required capabilities of XAI for a range of relevant stakeholders, including managers, regulators, users of XAI models, developers, and consumers. We contribute to theory and practice by deducing XAI archetypes and developing a user-centric decision support framework to identify the XAI services most suitable for the requirements of relevant stakeholders. Our decision tree is founded on a literature-based morphological box and a classification of real-world XAI services. Finally, we discussed archetypical business models of XAI services and exemplary use cases.

Explainable Artificial Intelligence for Drug Discovery and Development: A Comprehensive Survey

“…Decision trees can be visualized as tree-like structures, which makes it easy to understand the model's decision-making process. The advantage of decision trees is that they are easy to interpret and understand, making them a good choice for XAI models [66]. They also tend to be relatively fast to train and can handle both numerical and categorical data, which makes them well-suited for a variety of applications.…”

Explainable AI for Cyber-Physical Systems: Issues and Challenges

“…XAI is not just needed for understanding AI; it is critical for managing it [35]. XAI is used to explain and justify decisions made by AI models, control and improve AI models, and explore relationships within data [36]. AI has changed the way humans live, interact, spend their money, and even vote [12], [35].…”

Human Centricity in the Relationship Between Explainability and Trust in AI

“…Explainability can be categorized into two levels for better comprehension [18]. 1) Model explainability by design: In the past half-century of machine learning (ML) research, numerous fully or partially explainable ML models have been devised.…”