基于Grey Markov模型的股票价格研究

发布时间：2019-06-10 21:59

【摘要】：股票市场是证券市场的重要组成部分,随着人们对证券市场的深入了解,人们越来越关心的股市问题归根结底就是股票价格变化及走向情况,以期获得短期收益。股票价格有很大的波动性、不确定性,要掌握所有影响股票价格的信息是极其困难的,现在已有多种股票价格预测模型产生,并取得了良好的效果,但只根据股票价格做预测模型的方法并不多,其中较为典型的数学模型有灰色模型和马尔可夫链。灰色模型就是一个研究预测股价走向的灰色系统,在该系统中股票市场除了股票价格信息被看作已知外,其他任何信息均看作未知,即在模型中股价被看作一个灰色量,然后采用已知的指定股价序列通过该模型来预测该只股票未来短期内的价格走向甚至价格；在应用过程中该模型表现出了建立数学模型所需数据较少、模型简单、预测精度较高等特点。灰色模型预测是建立在GM(1,1)数学模型基础之上,该模型以具体量化的形式来预测某股票未来价格走向；它的解集表现为指数型曲线,它不适合对具有较大波动性的股票价格走向进行研究预测。马尔可夫过程是一种随机过程,马尔可夫链以具体形式反映了马尔可夫过程,它先依据不同的标准将已知的股票价格序列数据划分到不同的状态中,再依据各状态之间的转移概率来预测股票价格未来所处的状态,反映了股票价格之间的内在规律性,它适合对波动性较大及数目足够准确的股票价格序列进行预测。因此将两种方法结合起来,作灰色马尔可夫预测,既避免了两者的缺点,又发扬了两者的优点,可以明显提高股票价格的预测精度。本文节选了2012年1月4日到2012年6月13日的沪深300指数日收盘价格作为模型的样本序列,通过对该样本序列建立灰色马尔可夫模型,预测出了该股票未来5天内的价格值。结果表明：虽然该模型下的预测结果和实际结果之间有误差,但误差很小,且预测精度比GM(1,1)模型高,表明了该模型用于股票价格预测的优越性；利用该模型做股票价格预测能够为人们者提供部分的投资参考作用。
[Abstract]:The stock market is an important part of the securities market. With the in-depth understanding of the securities market, people are more and more concerned about the stock market in the final analysis is the stock price change and trend, in order to obtain short-term returns. The stock price has great volatility and uncertainty, so it is extremely difficult to master all the information that affects the stock price. Now a variety of stock price prediction models have been produced, and good results have been achieved. However, there are not many methods to make prediction models only according to stock price, among which the more typical mathematical models are grey model and Markov chain. Grey model is a grey system to predict the trend of stock price. In this system, except that the stock price information is regarded as known, any other information is regarded as unknown, that is to say, the stock price is regarded as a gray quantity in the model. Then the known specified stock price sequence is used to predict the price trend and even the price of the stock in the short term in the future. In the process of application, the model shows the characteristics of less data needed to establish the mathematical model, simple model and high prediction accuracy. Grey model prediction is based on GM (1, 1) mathematical model, which forecasts the future price trend of a stock in a specific quantitative form. Its solution set is an exponential curve, which is not suitable for the research and prediction of the stock price trend with great volatility. Markov process is a kind of stochastic process. Markov chain reflects Markov process in concrete form. It first divides the known stock price sequence data into different states according to different standards. Then, according to the transition probability between the states, the future state of the stock price is predicted, which reflects the inherent regularity between the stock prices, and it is suitable for predicting the stock price series with large volatility and sufficient accuracy. Therefore, combining the two methods to make grey Markov prediction can not only avoid the shortcomings of the two methods, but also carry forward the advantages of the two methods, which can obviously improve the prediction accuracy of stock price. In this paper, the daily closing price of Shanghai and Shenzhen 300 Index from January 4, 2012 to June 13, 2012 is selected as the sample sequence of the model. Through the establishment of grey Markov model for the sample sequence, the price value of the stock in the next five days is predicted. The results show that although there is an error between the prediction results and the actual results, the error is very small, and the prediction accuracy is higher than that of GM (1, 1) model, which shows the superiority of the model in stock price prediction. Using this model to predict the stock price can provide some investment reference for people.
【学位授予单位】：北方工业大学
【学位级别】：硕士
【学位授予年份】：2013
【分类号】：F224;F830.91

【参考文献】