The artificial neural networks in audits

2026

Closed access Metadata (CSL-JSON)
DOI 10.55871/2072-9847-2026-72-3-149-160
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

In the context of rapidly growing data volumes and stricter auditing requirements, artificial intelligence technologies–particularlyArtificialNeuralNetworks(ANNs)–arebecomingincreasinglyrelevantintheauditing field. This study investigates the impact of expert systems, machine learning methods, and intelligent agents on audit quality.The empirical data were collected through a structured questionnaire survey conducted among accounting and auditing consulting firms located in Astana, Aktobe, Atyrau, and Aktau. A purposive sampling methodwasappliedtodeterminethesamplesizeof375respondents.Thecollectedprimarydatawereanalyzedusing descriptive statistics and Ordinary Least Squares (OLS) regression analysis.The findings reveal a significant positive correlation between the use of expert systems, machine learning, intelligent agents, and audit quality. The application of ANNs enhances the quality of audit reporting and is expected to become a dominant trend in the coming decades, as intelligent systems increasingly take over decision-making tasks.The study recommends continuous training for accountants and auditors in ANN methodologies to improve auditquality.Furthermore,auditingfirmsareadvisedtoinvestinmachinelearningtoolsandexpandtheuseof intelligent agents to assist in classifying audit objects across different categories.