Adapting SQuaRE for Quality Assessment of Artificial Intelligence Systems
This work addresses the problem of quality assessment for software practitioners developing industrial AI systems, offering an incremental adaptation of existing standards.
The paper tackles the challenge of assessing quality in AI systems, where traditional software quality principles are insufficient due to machine learning's training-based behavior and new requirements like fairness and explainability. It adapts the ISO/IEC 25000 series (SQuaRE) to incorporate ML-specific aspects and AI ethics guidelines, providing holistic insights for quality evaluation.
More and more software practitioners are tackling towards industrial applications of artificial intelligence (AI) systems, especially those based on machine learning (ML). However, many of existing principles and approaches to traditional systems do not work effectively for the system behavior obtained by training not by logical design. In addition, unique kinds of requirements are emerging such as fairness and explainability. To provide clear guidance to understand and tackle these difficulties, we present an analysis on what quality concepts we should evaluate for AI systems. We base our discussion on ISO/IEC 25000 series, known as SQuaRE, and identify how it should be adapted for the unique nature of ML and $\textit{Ethics guidelines for trustworthy AI}$ from European Commission. We thus provide holistic insights for quality of AI systems by incorporating the ML nature and AI ethics to the traditional software quality concepts.