Explainable Machine Learning for Automated Audit Risk Assessment and Materiality Estimation
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
The integration of machine learning (ML) technologies into financial auditing has transformed traditional audit practices by enabling automated risk assessment and materiality estimation at unprecedented scales. However, the black-box nature of many ML models has raised significant concerns regarding transparency, accountability, and regulatory compliance in audit contexts. This paper examines the application of explainable artificial intelligence (XAI) techniques to address these challenges, focusing specifically on audit risk assessment and materiality estimation processes. We systematically review recent developments in explainable ML methodologies, including Local Interpretable Model-Agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), and attention mechanisms within neural network architectures. Through comprehensive analysis of existing literature and methodological frameworks, we demonstrate how XAI techniques can enhance auditor decision-making by providing interpretable insights intomodel predictions while maintaining predictive performance. Our findingsindicate that explainable ML approaches not only improve the transparency of automated audit systems but also facilitate better alignment with professional auditing standards and regulatory requirements. This research contributes to the growing discourse on responsible AI adoption in financial auditing and provides practical guidance for implementing explainable ML systems in audit risk assessment and materiality determination contexts.
Fields of Study & Subjects
Explainable Artificial Intelligence (XAI)
Auditing
Earnings Management
Governance
Robotic Process Automation Applications
Publication details
- Journal / source
- American Journal of Artificial Intelligence and Neural Networks
- Volume
- 7
- Issue
- 1
- Pages
- 46–67
- Publication date
- 28 February 2026
- Language
- EN