Explainable Artificial Intelligence (XAI) in auditing |
| |
Affiliation: | 1. Rutgers Business Schoo, United States & Research Institute of Economics and Management, Southwestern University of Finance and Economics, People''s Republic of China;2. Rutgers Business School, United States;1. Strategic Security Sciences, Argonne National Laboratory, Ames, IA 50010, United States;2. Ivy College of Business, Iowa State University, Ames, IA 50010, United States;3. Strategic Security Sciences, Argonne National Laboratory, Argonne, IL 60439, United States;1. School of Accountancy and MIS, DePaul University, United States;2. Graduate Institute of Accounting and Department of Finance, National Central University, Taoyuan, Taiwan;3. School of Management, Clark University, United States;1. School of Management, Clark University, Worcester, MA, 01610, United States;2. School of Accounting, Southwestern University of Finance and Economics, Sichuan, 611130, PR China;3. Anisfield School of Business, Ramapo College of New Jersey, Mahwah, NJ, 07430, United States;4. Rutgers Business School, Rutgers, the State University of New Jersey, Newark, NJ, 07102, United States;1. Faculty of Management, University of Tehran, Tehran, Iran;2. Fogelman College of Business and Economics, University of Memphis, United States;1. University of Northern Colorado, United States;2. University of Northern Colorado and Monash University, United States and Australia;3. Oregon State University, United States;4. Virginia Commonwealth University, United States;1. Dept. of Business Informatics, Hanyang University, Seoul, Korea;2. School of Business, Hanyang University, Seoul, Korea |
| |
Abstract: | Artificial Intelligence (AI) and Machine Learning (ML) are gaining increasing attention regarding their potential applications in auditing. One major challenge of their adoption in auditing is the lack of explainability of their results. As AI/ML matures, so do techniques that can enhance the interpretability of AI, a.k.a., Explainable Artificial Intelligence (XAI). This paper introduces XAI techniques to auditing practitioners and researchers. We discuss how different XAI techniques can be used to meet the requirements of audit documentation and audit evidence standards. Furthermore, we demonstrate popular XAI techniques, especially Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP), using an auditing task of assessing the risk of material misstatement. This paper contributes to accounting information systems research and practice by introducing XAI techniques to enhance the transparency and interpretability of AI applications applied to auditing tasks. |
| |
Keywords: | Explainable Artificial Intelligence (XAI) Auditing Machine learning Material restatement LIME SHAP |
本文献已被 ScienceDirect 等数据库收录! |
|