Title: Judgement method of enterprise financial data abnormality based on high-order dynamic Bayesian network

Authors: Lili Wang

Addresses: Department of Economics and Management, Harbin University, Harbin, 150086, China

Abstract: This paper proposes a judgement method of enterprise financial data anomaly based on high-order dynamic Bayesian network. Firstly, the enterprise financial data is divided into normal data and abnormal data, and the original training samples are classified to obtain the data classification results. Input the classification results into the enterprise financial data management platform based on cloud computing to improve the efficiency of data anomaly judgement. The high-order dynamic Bayesian network is used to initialise and modify the network, and the chromosome coding method is used to realise the abnormal judgement of enterprise financial data. The experimental results show that the method has a higher accuracy rate of anomaly judgement, and a lower miss rate and error rate.

Keywords: high-order dynamic Bayesian network; financial data; network modification; chromosome coding; data classification.

DOI: 10.1504/IJISE.2023.132270

International Journal of Industrial and Systems Engineering, 2023 Vol.44 No.3, pp.369 - 379

Received: 30 Jun 2021
Accepted: 23 Aug 2021
Published online: 14 Jul 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article