Modeling and Computing of Stock Index Forecasting Based on Neural Network and Markov Chain

The stock index reflects the fluctuation of the stock market. For a long time, there have been a lot of researches on the forecast of stock index. However, the traditional method is limited to achieving an ideal precision in the dynamic market due to the influences of many factors such as the economic situation, policy changes, and emergency events. Therefore, the approach based on adaptive modeling and conditional probability transfer causes the new attention of researchers. This paper presents a new forecast method by the combination of improved back-propagation (BP) neural network and Markov chain, as well as its modeling and computing technology. This method includes initial forecasting by improved BP neural network, division of Markov state region, computing of the state transition probability matrix, and the prediction adjustment. Results of the empirical study show that this method can achieve high accuracy in the stock index prediction, and it could provide a good reference for the investment in stock market.

[1]  Weihui Dai,et al.  Emergency Event: Internet Spread, Psychological Impacts and Emergency Management , 2011, J. Comput..

[2]  Wei Liu,et al.  Volatility Forecasting in the Hang Seng Index using the GARCH Approach , 2009 .

[3]  Ingoo Han,et al.  Hybrid knowledge integration using the fuzzy genetic algorithm: prediction of the Korea stock price index , 2004, Intell. Syst. Account. Finance Manag..

[4]  Jinsung Oh,et al.  Fuzzy models for predicting time series stock price index , 2010 .

[5]  龚健,et al.  基于隐马尔可夫链的上证股指建模 A Hidden Markov Chain Modeling of Shanghai Stock Index , 2012 .

[6]  Ping-Feng Pai,et al.  A hybrid ARIMA and support vector machines model in stock price forecasting , 2005 .

[7]  P. Srinivasan.  Modeling and Forecasting the Stock Market Volatility of S&P 500 Index Using GARCH Models , 2011 .

[8]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[9]  Michel Verleysen,et al.  Non-linear financial time series forecasting application to the Bel 20 stock market index , 2000 .

[10]  Fan Yanmin,et al.  A Stock Index Forecasting Model Based on Grey Relation Theory and GNNM (1, N) , 2012 .

[11]  M. Kaboudan.  Genetic Programming Prediction of Stock Prices , 2000 .

[12]  San Antonio,et al.  Academy of Information and Management Sciences , 2013 .

[13]  M. P. Hanias,et al.  Time Series Prediction with Neural Networks for the Athens Stock Exchange Indicator , 2012 .

[14]  Zhang Jun.  ANN-Based Mid-Term Stock Forecasting , 2006 .

[15]  Salvatore Ercolano,et al.  Exploring Public Social Expenditure Trends in the Globalization Era , 2012 .

[16]  Su Gao.  On the Improving Backpropagation Algorithms of the Neural Networks Based on MATLAB Language:A Review , 2003 .

[17]  P. K. Mahesh,et al.  An Efficient Process of Human Recognition Fusing Palmprint and Speech features , 2010 .

[18]  Yuan Xiao-lin,et al.  Research of improved BP algorithm based on self-adaptive learning rate , 2009 .

[19]  Lynn Kuo,et al.  Forecasting stock prices using a hierarchical Bayesian approach , 2005 .

[20]  Sehwan Yoo,et al.  Forecasting Korean Stock Price Index (KOSPI) Using Back Propagation Neural Network Model, Bayesian Chiao's Model, and Sarima Model , 2008 .

[21]  Amir H. Alizadeh,et al.  A Markov regime switching approach for hedging stock indices , 2004 .

[22]  N. R. Sakthivel,et al.  A Decision Tree- Rough Set Hybrid System for Stock Market Trend Prediction , 2010 .

[23]  Baikunth Nath,et al.  A fusion model of HMM, ANN and GA for stock market forecasting , 2007, Expert Syst. Appl..

[24]  Hui Xiao-feng.  A new stock index fuzzy stochastic prediction model developed by introducing a Markov chain , 2011 .