Summary

2011 International Symposium on Nonlinear Theory and Its Applications

2011

Session Number:A4L-D

Session:

Number:A4L-D1

NIKKEI Stock Price Forecast Using Bayesian Network

Yi Zuo,  Eisuke Kita,  

pp.270-273

Publication Date:2011/9/4

Online ISSN:2188-5079

DOI:10.34385/proc.45.A4L-D1

PDF download (168KB)

Summary:
In this study, the stock price earnings ratio(PER) forecast algorithm using Bayesian Network(BN) is presented. Firstly, discrete value set of stock PER distribution is determined by clustering the PER distribution by Ward method. The BN is used for modeling the conditional probability of the PER values. NIKKEI stock average(NIKKEI225) is consider as a numerical example. The results show that the accuracy of the present algorithm is better by 15% than that of the time-series forecast algorithms.