Title: Information system operational efficiency prediction algorithm based on deep learning
Authors: Dayong Chang; Xiaofeng Gao; Yongqiang Guo; Du Wang
Addresses: Digital Work Department of State Grid Henan Electric Power Company, Zhengzhou, Henan, China ' Digital Work Department of State Grid Henan Electric Power Company, Zhengzhou, Henan, China ' State Grid Henan Electric Power Company Information Communication Branch Data Management Centre, Zhengzhou, Henan, China ' State Grid Henan Electric Power Company Information Communication Branch Data Management Centre, Zhengzhou, Henan, China
Abstract: This article aims to use deep learning algorithms to accurately predict and analyse the operational efficiency of enterprise information systems, provide key management insights and decision support for enterprises. This article applies deep learning technology to predict the operational efficiency of enterprise information systems, uses Back Propagation Neural Network (BPNN) and Deep Belief Network (DBN) to analyse the total assets, operating expenses, investment expenses, operating revenue, operating profits, and other data of enterprises, in order to predict the operational efficiency of enterprises. This article trained data from five retail listed companies in the Chinese A-share market, and the results showed that the average prediction accuracy of operating efficiency using BPNN algorithm was 97.72%, while the average prediction accuracy of operating efficiency using DBN algorithm was 98.88%. The DBN algorithm has good computational efficiency and predictive performance in enterprise information system data analysis.
Keywords: operating efficiency; enterprise information system; deep learning; back propagation neural network; deep belief network.
DOI: 10.1504/IJGUC.2024.140127
International Journal of Grid and Utility Computing, 2024 Vol.15 No.3/4, pp.370 - 379
Received: 27 May 2023
Accepted: 20 Mar 2024
Published online: 24 Jul 2024 *