Dissertation > Excellent graduate degree dissertation topics show

Study on Stock Time Series Based on Rough Set and RBF Network

Author: WangTianE
Tutor: YeDeQian
School: Qingdao Technological University
Course: Applied Computer Technology
Keywords: Time Series Rough Set RBF network Stock trend Stock inflection point Decision Support Model
CLC: TP183
Type: Master's thesis
Year: 2009
Downloads: 62
Quote: 1
Read: Download Dissertation

Abstract


Traditional time series analysis methods to deal with simple linear problem and achieved good results , but the stock complex nonlinear systems appeared to be inadequate . The emergence of artificial neural networks to nonlinear time series analysis provides a new effective way , but there are still some drawbacks . Problems encountered by the neural network stock prediction , the subject will be rough set theory introduced predictive models and conduct in-depth research . (1 ) the use of rough set theory pretreatment stock data extracted from a large number of raw data in the core knowledge and to improve the efficiency of the analysis . Conditional information entropy discretization method of calculation is very complex , and the choice of the subject of the original algorithm of discrete points and calculation process improvement, be an inspiration shows information entropy discretization method , and the stock data discretization . (2) the genetic algorithm is applied to a minimum reduction of looking for the weaknesses of the basic genetic algorithm , to improve its genetic . Stock data reduction using attribute reduction method based on improved genetic algorithm , so as to get better reduction results . ( 3) the radial basis function (RBF) neural network learning algorithms have their own advantages and disadvantages, in practical applications , it is difficult to determine which algorithm is more ideal . The subject through experiments , analyze and compare the performance of three commonly used algorithm of RBF network , neural network model to determine stock prediction . ( 4) The proposed definition and classification of stock inflection point ( three types of inflection point ) , set the inflection point parameters corresponding decision support model , select the appropriate level of stock data , predict stock trend inflection point , the actual operation for small and medium investors to provide decision support . Finally , through a large number of experiments to prove the accuracy of the stock time series analysis method based on rough sets and RBF network integration , as well as the effectiveness solve complex network structure , slow learning .

Related Dissertations

  1. Research on Clustering Algorithm Based on Genetic Algorithm and Rough Set Theory,TP18
  2. Based on Data Mining Technologies in Urban Water Supply Analysis and Decision,F299.24;F224
  3. Based on Neural Network Model of Hot-rolling,TP183
  4. Study on the Decision Tree Classification Algorithm and Its Application Based on Rough Set Theory,TP18
  5. Short-term load forecasting technology,TM715
  6. Study on the Development of Textile and Apparel Enterprises in Jiangsu and Zhejiang Provinces Based on Cycle Economics,F426.8
  7. Study on Short-Term Power Load Prediction Based on Support Vector Regression Modeling Method,TM715
  8. Yunnan Highway Traffic Safety Prevention,U492.8
  9. Fault Diagnosis Method Based on Support Vector Machine,TP18
  10. Analysis and Forecast of Yunnan Province, production safety accidents statistics,X928.01
  11. The Research of the Uncertainty Quest Under the Dominance Relation,O159
  12. Research on Attribute Reduction and Constructing Algorithm of Concept Lattice,O159
  13. Research on Fault Diagnosis Method of Brushless Dc Motor Driver,TM33
  14. The Synthesis Evaluation of Cleaner Production in Thermal Power Plants,F205
  15. Theresearch of Model and Methods of House of Maintenance of Requirement-Oriented Maintenance,F274
  16. The Gas Predicting and Scheduling Model for Steel Enterprises,F426.31
  17. Bayesian Methods for Time Series Outliers Detection and Applications in GPS Data Processing,O212.8
  18. Fuzzy time series forecasting model based on differential heuristic information,F830
  19. Application of Wavelet Network in Economic Prediction,F201
  20. Analysis of Characteristics of Chaotic Time Series and Research of Phase Space Reconstruction,O415.5

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Artificial Neural Networks and Computing
© 2012 www.DissertationTopic.Net  Mobile