<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In this paper, the enterprise data is processed without outline, PCA is used for data dimensionality reduction SVM is used to categorize the dimensionality reduction data, and the prediction of future trends is made based on the categorization situation. The PCA-SVM risk control model based on big data is established, and the PSO particle swarm algorithm is used to find the optimal parameters for SVM to improve its classification performance and optimize the prediction of enterprise management risks. In order to test the effect of risk management and control optimization, data processing is carried out for two types of companies, namely, banking and real estate industries, and predictions are made for their future operation based on the processing results. During the period from 2022Q1 to 2022Q2, the CSI banking index falls from 0.11 to −0.59; the output of this paper’s model is 1, i.e., there is a risk, and it is predicted that the values of Q1 and Q2 in 2024 are 1, and a financial risk may occur. The PCA-SVM model has a 95% determination rate for training samples, and it can predict low-risk sample companies accurately with a comprehensive error rate of only 6.67%. The data proves that the model can effectively predict the future risk status of enterprises according to the existing information and provide optimization reference for enterprises to change their economic management mode.</p>
</abstract>

In this paper, the enterprise data is processed without outline, PCA is used for data dimensionality reduction SVM is used to categorize the dimensionality reduction data, and the prediction of future trends is made based on the categorization situation. The PCA-SVM risk control model based on big data is established, and the PSO particle swarm algorithm is used to find the optimal parameters for SVM to improve its classification performance and optimize the prediction of enterprise management risks. In order to test the effect of risk management and control optimization, data processing is carried out for two types of companies, namely, banking and real estate industries, and predictions are made for their future operation based on the processing results. During the period from 2022Q1 to 2022Q2, the CSI banking index falls from 0.11 to −0.59; the output of this paper’s model is 1, i.e., there is a risk, and it is predicted that the values of Q1 and Q2 in 2024 are 1, and a financial risk may occur. The PCA-SVM model has a 95% determination rate for training samples, and it can predict low-risk sample companies accurately with a comprehensive error rate of only 6.67%. The data proves that the model can effectively predict the future risk status of enterprises according to the existing information and provide optimization reference for enterprises to change their economic management mode.

Optimization of economic management mode and risk control based on the background of big data

Shandong University of Finance and Economics

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

In this paper, the enterprise data is processed without outline, PCA is used for data dimensionality reduction SVM is used to categorize the dimensionality...

Optimization of economic management mode and risk control based on the background of big data

Publicado en línea: 31 ene 2024

Páginas: -

Recibido: 18 dic 2023

Aceptado: 24 dic 2023

DOI: https://doi.org/10.2478/amns-2024-0182

Palabras clave
PCA, SVM, Particle swarm algorithm, Risk control, Economic management mode

© 2024 Yiran Chen, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Optimization of economic management mode and risk control based on the background of big data

Publicado en línea: 31 ene 2024

Páginas: -

Recibido: 18 dic 2023

Aceptado: 24 dic 2023

DOI: https://doi.org/10.2478/amns-2024-0182

Palabras clavePCA, SVM, Particle swarm algorithm, Risk control, Economic management mode

© 2024 Yiran Chen, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Palabras clave
PCA, SVM, Particle swarm algorithm, Risk control, Economic management mode