The Global Organizational Behavior Analysis for Financial Risk Management Utilizing Artificial Intelligence

Enterprise financial risks are analyzed utilizing the theory of organizational behavior, and a financial risk management system is constructed to improve the design and algorithm of the enterprise risk management system. Base on the CCER (China Center for Economic Research) database, the early warni...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of global information management Ročník 30; číslo 7; s. 1 - 24
Hlavní autoři: Yang, Shufang, Wu, Hainan
Médium: Journal Article
Jazyk:angličtina
Vydáno: Hershey IGI Global 01.01.2022
Témata:
Air pollution
Algorithms
Applied behavior analysis
Artificial intelligence
Back propagation
Back propagation networks
Bankruptcy
Comparative analysis
Data base management systems
Decision making
Design improvements
Economic research
Financial management
Information management
International finance
Market economies
Neural networks
Objective function
Organization theory
Organizational aspects
Organizational behavior
Organizational effectiveness
R&D
Regression analysis
Research & development
Risk assessment
Risk management
Statistical analysis
Support vector machines
Wavelet transforms
China
Taiwan
ISSN:1062-7375, 1533-7995
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Enterprise financial risks are analyzed utilizing the theory of organizational behavior, and a financial risk management system is constructed to improve the design and algorithm of the enterprise risk management system. Base on the CCER (China Center for Economic Research) database, the early warning model for enterprise financial risk management containing five indices is proposed for enterprises. Through Logistic regression analysis, the design principle of the financial risk management system based on AI (Artificial Intelligence) technology is explained. The proposed system innovatively introduces the AI integrated learning method, optimizes objective function through XGBoost (eXtreme Gradient Boosting) algorithm, and trains the model through BP (Backpropagation) NN (Neural Network). Finally, following comparative analysis, the effectiveness of the proposed method is verified.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1062-7375
1533-7995
DOI:10.4018/JGIM.292455