Бухгалтерлік есептегі көпөлшемді жасанды нейронды желілер

2025

Полный текст Открытый доступ: Gold Метаданные (CSL-JSON)
DOI 10.26577/be202515442
Достоверность данных 70 средняя
Как считается эта оценка

Складывается из проверяемых признаков самой записи: есть ли у статьи DOI, сколько независимых источников подтвердили её данные, заполнены ли обязательные поля и насколько свежо последнее подтверждение. Снижают оценку расхождения между источниками и отсутствие идентификатора. Значение от 80 означает, что запись опубликована без дополнительной проверки; от 60 до 79 — что она опубликована с пониженной достоверностью и ручная проверка желательна. Запись, выверенную редактором вручную, пересчёт не опускает ниже 90. Это оценка наших данных о статье, а не оценка самой статьи.

Аннотация

The artificial neural networks exert a significant influence on business processes through their capacity for automation and data integration. However, the unrestricted application of automated procedures entails risks that are particularly evident in the field of accounting. Multidimensional accounting systems are affected by expert systems, neural networks, genetic algorithms, and intelligent agents. The research methodology was based on a mixed approach, combining quantitative and qualitative methods. To collect data on the adoption of artificial neural network applications and their projected multidimensional impact on accounting, a survey was conducted among professionals in accounting and auditing. A range of statistical methods, including correlation and regression analysis, was employed to examine the relationship between the adoption of neural network applications and formal outcomes. The findings revealed that the use of genetic algorithms is among the most significant and effective applications of artificial neural networks, contributing to the improvement of accounting information quality. In contrast, expert systems, neural networks, and intelligent agents demonstrated no statistically significant effect on the quality of accounting data. The positive impact of genetic algorithms may be attributed to the professional and technological environment in Astana, which has not yet reached the maturity required for the effective implementation of more complex artificial intelligence technologies, but fosters the development of practical analytical tools. The study concludes with a set of recommendations, the most important of which emphasize the need to deepen understanding and expand the adoption of artificial neural network technologies in accounting and auditing practice. Key words: artificial neural networks, analytical systems, neural networks, genetic algorithms, intelligent agents.