Markov Chain Stock Market Trend Prediction Method Based On Rational Indicator

Stock market trend forecasting is an important guiding role for investment decisions.However,stock movements are affected with macroeconomic policies,the company's internal strategy and the existence of the stock market human disturbance and other factors,making the stock trend difficult to effectively predict.In this thesis,the rational indicator which is based on the technical analysis method is proposed for the problem of the buy and sale induced in stock market,and puts forward the effective build model;NRI_MCA and CD_MCA algorithms which are based on rational indicator and characteristic deviation are proposed to solve the stock of trend forecasting problem,Specific research work is as follows:(1)First,the main stock market rational characteristics are extracted and quantized;then,these characteristics are reasonably integrated into rational index through the principal component analysis and the buy and sale is also acquired to use these rational indicators;Finally,situation of the Stock Market to the buy and sale is led into Markov Chain to realize the stock market trend forecast.The buy and sale is affected by the reliability that the deviation of rational indicators and stock status,NRI_MCA algorithm(Markov Chain Stock Market Trend Prediction Algorithm Based on Rational Indicator Combining with Characteristics Deviate)is proposed by introducing characteristics deviate into RI_MCA algorithm which adjusts the RI_MCA algorithm results by the degree of the feature departure.NRI_MCA algorithm has higher prediction accuracy showed by the comparison and analysis of experimental results of Shanghai Composite Index.(2)In order to make rational indicator of predictive ability and universal application value fully exploited,the CD_MCA algorithm is proposed for the stock based on the characterized departing model.According to the technical analysis,the rationality of the stock is extracted,the validity of the feature is confirmed by the Bayesian network,and the principal component analysis can be used to construct the stock rational indicator;Secondly,the deviation value is obtained by the characteristic deviation formula.The Markov chain prediction model is used to divide the stock index corresponding to the deviation interval.Finally,according to the correlation between the stock and the market,the initial state of the stock index,different investment decisions are given,so as to carry out continuous stock forecast and the universal value of rational indicators is realized.