Dissertation > Excellent graduate degree dissertation topics show

Study of Financial Risk Prediction Based on Rough Set and ANN Model

Author: LanYuYe
Tutor: LiuYanWen
School: Dalian University of Technology
Course: Accounting
Keywords: Financial early warning BP neural network Rough Set Improved Algorithm
CLC: F224
Type: Master's thesis
Year: 2006
Downloads: 403
Quote: 0
Read: Download Dissertation

Abstract


Nurture the development of a competitive market economy opportunities, but also hidden risks and crisis endless. For listed companies, the financial crisis degenerated into \The company is in a financial crisis, not only the crisis of its own survival and development, and also brought huge losses to investors, creditors. Therefore, building an effective and practical financial crisis early warning model to meet the increasingly urgent needs of the stakeholders, it has not just an academic question, more important factors that affect the healthy development of China's capital market, with a strong practical significance. This study is to proceed from the perspective of intelligent theory, rough set theory and neural network technology is applied to the financial warning among China's listed companies. In this paper, first the rough set theory brief introduction and discussion of its calculation method for knowledge reduction; then introduces the principle of neural network technology as well as the basic principles of BP, with detailed descriptions of the BP network The improved algorithm. The theoretical basis of a rough set and neural network technology combination method, and the method is applied to the study of China's listed companies' financial early warning. This paper is divided into five parts. The first part introduces the research background and significance of the listed companies' financial crisis early warning system, and the second part of the research status at home and abroad; introduced rough sets and neural networks, several key technical point, the theoretical basis of the model built. Meanwhile, in order to make up for the deficiencies of the past, BP algorithm, this chapter focuses on the modified BP algorithm and the proposed algorithm is faster and more efficient, and the modified algorithm was tested. The third part of the rough set and neural network technology combined model building ideas and methods. A brief introduction to the basic idea of ??the network build steps. The fourth part is the empirical study, dynamic early warning combination model built using standard BP neural network model and this article, the financial condition of listed companies, accuracy and efficiency by comparing model predictions, the evidence shows that: (1) through rough set The combination of neural network model for enterprise financial risk early warning method, you can not reduce the prediction accuracy basically substantially reduces the the network computing time, improve the network model prediction efficiency. (2) the use of adaptive parameter to adjust the learning algorithm to adjust the network parameter, on the one hand to improve the subjectivity of the network parameters primaries, explain the mechanism of enhanced network, on the other hand can effectively circumvent the network into a local minimum, strengthen the network training accuracy and precision. The fifth part of the conclusion.

Related Dissertations

  1. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  2. Research on Visual Servo System of Mechanical ARM,TP242.6
  3. Fault Diagnosis Method Based on Support Vector Machine,TP18
  4. Municipal tourism land use planning environmental impact assessment,X820.3
  5. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  6. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  7. Research on Clustering Algorithm Based on Genetic Algorithm and Rough Set Theory,TP18
  8. Based on Rough Set of Urban Areas When Traffic Green Control System Research,TP18
  9. Mine Risk Information Integration and Intelligent Early Warning,X936
  10. Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
  11. Incremental rough set attribute reduction,TP18
  12. Calculation of Knowledge Granulation and Study of Its Application in Attribute Reduction,TP18
  13. Research of License Plate Recognition Based on Rough Sets and Fuzzy SVM,TP391.41
  14. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662
  15. Study on Luohe Technical Supervision Bureau of Food Safety Early Warrning System Based on Neural Network,F203
  16. Research of Adaptive Active Noise Control Based on Neural Network,TP183
  17. Research on Automatic Reading System for Digital Meters,TP391.41
  18. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  19. The Research of Evaluation Method in Connect6 Based on BP-TD Learning,TP18
  20. Research on State Diagnosis on Fan Based on Factor Analysis and BP Neural Network,F426.61
  21. The Research and Design of Converter Steelmaking Endpoint Guiding System,TF345

CLC: > Economic > Economic planning and management > Economic calculation, economic and mathematical methods > Economic and mathematical methods
© 2012 www.DissertationTopic.Net  Mobile