Research of Early Warning of Corporate Financial Crisis Based on Machine Learning Neural Network
Konferenz: CIBDA 2022 - 3rd International Conference on Computer Information and Big Data Applications
25.03.2022 - 27.03.2022 in Wuhan, China
Tagungsband: CIBDA 2022
Seiten: 4Sprache: EnglischTyp: PDF
Autoren:
Zhao, Yanli (The School of Business Administration, Wuhan Business University, Wuhan, China)
Yang, Guang (The School of Information and Safety Engineering, Zhongnan University of Economics and Law, Wuhan, China)
Inhalt:
In order to predict the financial crisis more accurately, based on kernel principal component analysis (KPCA) and Multilayer Perceptron (MLP), a financial crisis early warning model is proposed. Firstly, to eliminate random noise in massive financial data, the KPCA is used to extract the key information of financial data. Secondly, the MLP is adopted to predict the financial crisis. Finally, compared with other traditional machine learning financial early warning methods, our proposed method obtains the best prediction capability.