Enterprise Intelligent Audit Model by Using Deep Learning Approach

Rui Ding ()
Additional contact information
Rui Ding: Nanjing University of Science and Technology

Computational Economics, 2022, vol. 59, issue 4, No 3, 1335-1354

Abstract: Abstract The purpose is to apply artificial intelligence to enterprise intelligent audit, improve the efficiency of enterprise audit, and finally supervise and manage the enterprise revenue and expenditure timely and accurately. First, the classification, processing and storage of enterprise intelligent audit data are analyzed. An improved DLNN (Dynamic Learning Neural Network) algorithm model is proposed according to the deep learning theory to carry out intelligent audit on enterprise data, and BiLSTM (Bi-directional Long Short-Term Memory) model is adopted to analyze the classification accuracy of audit. Then, the Auto Encoder based on data compression algorithm is adopted to analyze the audit data. Finally, genetic algorithm is applied to the weight optimization of a deep learning network. The economic benefit evaluation data information of X enterprise in 2018 is selected. The current values of relevant indexes are compared with historical data. The results suggest that the performance of the deep learning neural network model optimized by the genetic algorithm is improved. After optimization, the precision of the model is improved from 81 to 87%, the accuracy of the model is improved from 92 to 96%, and the F1 score of the model is reduced from 3.5 to 2.3%. From 2014 to 2017, the current ratio, quick ratio, cash ratio and asset liability ratio of enterprise X decreased in 2015, while they were basically flat from 2015 to 2017. The return on assets and return on net assets corresponding to a competitive value and current value are basically the same, while the operating profit rate and cost profit rate corresponding to competitive value are slightly higher than the current value. Thereby, the data layer conversion model of enterprise intelligent audit based on deep learning has fast data conversion speed, and the audit results obtained are in line with the benchmark evaluation index with high reliability.

Keywords: Artificial intelligence; Deep learning; Enterprise intelligent audit data; Genetic algorithm (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10614-021-10192-9 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:compec:v:59:y:2022:i:4:d:10.1007_s10614-021-10192-9

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-021-10192-9

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().