Aug 2026· Frontiers in Artificial Intelligence· Vol 9· 0 citations· 95 references
Medicine
TL;DR
The findings indicate that XAI is mainly applied to fraud detection, credit assessment, financial auditing, and decision-support processes, with a predominance of techniques such as SHAP and LIME.
Abstract
Explainable Artificial Intelligence (XAI) has emerged as a response to the need to understand and make transparent the decisions of machine learning models, particularly in sensitive contexts such as accounting and financial auditing. In this domain, XAI enables the interpretation of results generated by automated systems applied to fraud detection, risk management, financial analysis, and regulatory compliance, thereby strengthening the trust of auditors and regulators. The objective of this study was to systematically analyze the literature on XAI in accounting and financial auditing in order to identify its application domains, the methods employed, and the main challenges reported. The research was conducted through a systematic literature review following the PRISMA protocol, based on studies retrieved from Scopus and Web of Science. The selected works were organized and synthesized using an analysis matrix, resulting in 85 primary studies. The findings indicate that XAI is mainly applied to fraud detection, credit assessment, financial auditing, and decision-support processes, with a predominance of techniques such as SHAP and LIME. Although these tools enhance transparency, limitations related to computational cost, data quality, explanation stability, and regulatory adaptation persist, highlighting the need to strengthen their integration into auditing processes. Systematic review registration https://osf.io/pb5cy/.
This study aims to systematically identify, review, and synthesize the role of statistical concepts in AI development for auditing, including their implementation, benefits, challenges, and future directions.
Nibrisatul Hana, Shofyan Hadi, Lintang Budiarti et al.· Journal of Creative Power a...· 0 citations
This study examines the extent to which artificial intelligence (AI) applications contribute to reducing accounting errors in bank financial statements, with a focus on the obstacles facing their adoption in accounting practice. Using a descriptive-analytical approach, a structured questionnaire was distributed to 100 preparers and auditors of financial statements in the Iraqi banking sector, yielding 91 valid responses for analysis. The findings indicate that AI applications can detect discrepancies between the methods used to prepare banking financial statements and standard or cross-country practices, and can identify the party responsible for an accounting error, regardless of its size. However, the results also show that AI applications lack the discretionary judgement that human auditors apply in assessing the materiality of an error and its broader implications for banking operations. The study recommends that preparers and auditors of bank financial statements leverage AI's error-detection capabilities, irrespective of error size, to improve the accuracy and reliability of financial statements in the banking sector. The findings contribute to the growing literature on AI-enabled auditing and offer practical implications for bank management, financial statement preparers, and regulators in emerging banking markets.
Ali H. N. BniLam· International journal of bus...· 0 citations
This study investigated the impact of artificial intelligence (AI), external audit quality on
financial accountability of Deposit Money Banks (DMBs) in Lagos State, Nigeria. More
specifically, this study examined the elements of the level of AI, effectiveness of AI in fraud
detection, reliability and accuracy of the audit, as well as timeliness and efficiency of the
audit, and the impact of these elements on financial accountability. Guided by Agency
Theory, the study employed a survey research design. External auditors and audit specialists
working in the four largest international audit firms (PwC, KPMG, EY and Deloitte) in Lagos
were surveyed, and 912 usable responses were collected. Data were analyzed using
descriptive statistics, reliability analysis using Cronbach’s alpha, and simple and multiple
regression analyses. The outcomes of the study revealed that the four model’s independent
variables had a positive and significant influence on financial accountability with a
confidence level of 95%. The level of AI adoption (β = 0.591, R² = 0.541), effectiveness of AI
in fraud detection (β = 0.624, R² = 0.573), reliability and accuracy of the audit (β = 0.573,
R² = 0.502), and timeliness and efficiency of the audit (β = 0.558, R² = 0.487). The combined
model was significantly high (R² = 0.714, F = 558.46, p < 0.05) and accounted for 71.4% of
the variance in financial accountability in which the effectiveness of AI in fraud detection was
the strongest of the four variables. The study found that the use of AI in external auditing
strengthened financial accountability in Nigerian Deposit Money Banks (DMBs). It suggested
the banks should allocate more resources toward the development of AI-based fraud
detection systems and real-time auditing. It is recommended that the Central Bank of Nigeria
(CBN) establishes a policy framework that balances the need to enhance the accountability of
banks and the development of responsible AI in auditing.
Tosin Olayemi Adeeko, A. O. Ayodele· Journal of Accounting and Fi...· 0 citations
Over the years, there has been an inclined growth in technology such that artificial intelligence (AI), accounting analytics, and machine learning have revolved in the practice of auditing in accounting field. Numerous substantial possibilities are presented by the above-mentioned technologies which include creating a robust framework of internal control and optimizing fraud detecting activities especially in the public organizational sector, where accountability and clarity are a necessity. The study examined the Impact of Artificial Intelligence (AI), Accounting Analytics and Machine Learning on Auditing: Enhancing Internal control and Fraud Detection in public sector organizations. This study employed a mixed-methods approach. It analyzed quantitative and qualitative data collected from: Government audit reports and financial statements, AI-driven risk assessment models and machine learning fraud detection datasets, Auditor and financial expert surveys (to gauge perception and practical AI implementation challenges), and Case studies from public sector organizations worldwide. The findings demonstrate that AI powered audit tools significantly reduce human errors, accelerate financial audits, and improve financial accuracy. Moreso, AI-based fraud detection models outperform traditional auditing methods, identifying fraudulent transactions with an 87% accuracy rate, compared to the 60-70% success rate of conventional audits.
Keywords: Artificial Intelligence, Machine Learning, Accounting Analytics, Fraud Detection, Internal Control, Public Sector.
Princess Ifeyinwa Nmezi· Radiant Journal of Business...· 0 citations
This study examines artificial intelligence (AI) in external auditing by synthesizing existing evidence, clarifying key concepts, identifying theoretical and methodological gaps, and outlining future research directions. A systematic literature review and bibliometric analysis were conducted on 130 peer-reviewed articles retrieved from Scopus and Web of Science databases. The review followed the PRISMA 2020 guidelines, while VOSviewer was used to map research trends, and thematic clusters. Research on AI in auditing has grown substantially, with the United States, China, and the United Kingdom leading scholarly contributions. The analysis identified three dominant research streams: machine learning and fraud detection, audit analytics and big data, and AI adoption and governance. Commonly applied AI techniques include machine learning, neural networks, natural language processing, robotic process automation, and expert systems. The study suggested that AI enhances fraud detection, risk assessment, and audit quality, while raising concerns regarding algorithmic bias, transparency, and professional skepticism. The study develops an integrated framework linking AI applications to audit quality and provides a research agenda to guide future inquiry. The findings offer practical insights for auditors, regulators, and organizations seeking to implement AI responsibly and effectively in audit processes.
The purpose of this study is to examine the effect of Artificial Intelligence (AI) on the performance of selected audit firms in Nigeria. Globally, major auditing firms, especially the “Big Four” Deloitte, PricewaterhouseCoopers (PwC), Ernst & Young (EY), and KPMG have pioneered the integration of AI technologies into their audit processes. The study acknowledges that Artificial Intelligence encompasses a wide range of technologies including Natural Language Processing (NLP), Expert Systems, Computer-Assisted Audit Techniques (CAATs), and Data Mining. The study adopted descriptive survey research design. The population of this study comprises audit professionals working in selected audit firms within Lagos, Abuja, and Port Harcourt. Primary data was collected through a structured questionnaire divided into sections. The study recommends that audit firms in Nigeria, particularly those yet to fully integrate Machine Learning tools, should invest in machine learning-based audit software capable of detecting unusual transactions, identifying fraud patterns, and classifying high-risk transactions.
Ibrahim Oluwanifemi, Adedeji Elijah Adeyinka· International Journal of App...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
