BP Neural Network Model Based on the K-Means Clustering to Predict the Share Price

Author

Zhang, Jichao ; Yang, Yueting

Author_Institution

Sch. of Math., Inst. of Appl. Math., Jilin, China

fYear

2012

fDate

23-26 June 2012

Firstpage

181

Lastpage

184

Abstract

A preprocessing procedure on dense type of data is presented using the error back propagation algorithm. In this paper, K-means are applied to BP neural network such that the data is preprocessed for the neural network. So appropriate pretreatment techniques of data could make the neural network execute more effectively to accept intensive data. Furthermore, some comparisons between the proposed algorithm and other algorithms will be provided. The BP algorithm may be applied to solve more practical nonlinear problem.

Keywords

backpropagation; economic forecasting; neural nets; pattern clustering; share prices; stock markets; BP algorithm; BP neural network model; K-means clustering; data dense type; data preprocessing; data pretreatment technique; error backpropagation algorithm; intensive data; nonlinear problem; share price prediction; stock price forecasting; Clustering algorithms; Indexes; Mathematical model; Neural networks; Predictive models; Stock markets; Time series analysis; BP neural network; K-means; data preprocessing; stock price forecasting; time series;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Sciences and Optimization (CSO), 2012 Fifth International Joint Conference on

Conference_Location

Harbin

Print_ISBN

978-1-4673-1365-0

Type

conf

DOI

10.1109/CSO.2012.46

Filename

6274704