【摘要】：股票市場(chǎng)是一個(gè)高度復(fù)雜的非線性系統(tǒng)。股市的變化既有其自身規(guī)律性，又受政治、經(jīng)濟(jì)、投資心理等諸多因素的影響。傳統(tǒng)的基于數(shù)理統(tǒng)計(jì)的預(yù)測(cè)方法很難對(duì)其進(jìn)行有效地描述，而具備解決非線性問題能力、網(wǎng)絡(luò)學(xué)習(xí)能力和系統(tǒng)擬合能力的人工神經(jīng)網(wǎng)絡(luò)可以在任意精度內(nèi)實(shí)現(xiàn)變量間的非線性關(guān)系的映像，逼近證券價(jià)格隨時(shí)間變換的函數(shù)，從而對(duì)股票市場(chǎng)進(jìn)行模擬和學(xué)習(xí)。 迄今為止，針對(duì)不同的股市，國(guó)外許多學(xué)者都建立了很多相應(yīng)的預(yù)測(cè)模型，給出了很好的預(yù)測(cè)方法，也取得了良好的預(yù)測(cè)效果。但由于我國(guó)證券市場(chǎng)僅有二十多年的發(fā)展歷史，還很不完善，，國(guó)外成熟市場(chǎng)上流行和行之有效的經(jīng)驗(yàn)和方法未必適合目前中國(guó)股票市場(chǎng)。BP神經(jīng)網(wǎng)絡(luò)是一種常用股票價(jià)格預(yù)測(cè)方法，它具有強(qiáng)大的非線性擬合能力，許多學(xué)者在這一領(lǐng)域進(jìn)行了深入的研究。但由于股票市場(chǎng)可選用預(yù)測(cè)參數(shù)太多，使BP神經(jīng)網(wǎng)絡(luò)內(nèi)部運(yùn)算混亂，常常導(dǎo)致運(yùn)算量過大，而且精確度下降。因此，本文在國(guó)內(nèi)外研究基礎(chǔ)上，提出了一種股票價(jià)格預(yù)測(cè)的BP神經(jīng)網(wǎng)絡(luò)輸入變量選擇方法。首先采用主成分分析法降低輸入向量的維數(shù)；然后采用層次分析法和德爾菲法相結(jié)合的方法調(diào)整輸入向量的信息結(jié)構(gòu)；最后將2種方法得到的輸入向量組進(jìn)行了仿真實(shí)驗(yàn)進(jìn)行比較。結(jié)果表明，綜合主成分分析法和結(jié)合層次分析法的德爾菲法得到的改進(jìn)主成分向量組對(duì)于BP神經(jīng)網(wǎng)絡(luò)股票預(yù)測(cè)具有較好的性能。
[Abstract]:The stock market is a highly complex nonlinear system. The change of stock market has its own regularity, and it is influenced by many factors such as politics, economy, investment psychology and so on. The traditional method of forecasting based on mathematical statistics is difficult to describe it effectively, but has the ability to solve non linear problems, network learning ability and system fitting. The artificial neural network of force can realize the image of the nonlinear relation between variables in any precision, and approximate the function of the change of the stock price with time, so as to simulate and learn the stock market.
So far, many foreign scholars have set up a number of corresponding prediction models for different stock markets, give a good prediction method, and have achieved good prediction results. However, because China's securities market has only more than 20 years of development history, it is still very imperfect, the popular and effective foreign market experience and methods are not. The.BP neural network in Chinese stock market is a kind of common stock price prediction method, which has strong non-linear fitting ability. Many scholars have carried on deep research in this field. However, because the stock market can choose too many predictive parameters to make the internal operation of BP neural network chaotic, and often leads to too much computation. Therefore, on the basis of research at home and abroad, this paper puts forward a BP neural network input variable selection method for stock price prediction. Firstly, the principal component analysis method is used to reduce the dimension of the input vector. Then the information structure of the input vector is adjusted by the combination of AHP and Delphi method; finally, 2 The simulation experiment of the input vector group obtained by the method is compared. The results show that the improved principal component vector group obtained by the integrated principal component analysis method and the analytic hierarchy process (AHP) method by Delphy Fa has good performance for the stock prediction of BP neural network.
【學(xué)位授予單位】：河北大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：F224;F832.51

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 袁曉東;神經(jīng)網(wǎng)絡(luò)在股票價(jià)格預(yù)測(cè)中的應(yīng)用[J];北京機(jī)械工業(yè)學(xué)院學(xué)報(bào);2002年03期

2 韓永學(xué);特爾菲法與“拿來主義”[J];哈爾濱師專學(xué)報(bào);2000年02期

3 楊啟文,韓玉兵;BP自適應(yīng)學(xué)習(xí)率設(shè)計(jì)[J];河海大學(xué)常州分校學(xué)報(bào);2001年03期

4 李松;劉力軍;谷晨;;混沌時(shí)間序列預(yù)測(cè)模型的比較研究[J];計(jì)算機(jī)工程與應(yīng)用;2009年32期

5 楊奎河;王寶樹;趙玲玲;;基于神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)模型中輸入變量的選擇[J];計(jì)算機(jī)科學(xué);2003年08期

6 朱群雄;郎娜;;工業(yè)軟測(cè)量模型結(jié)構(gòu)與輸入變量選擇的研究[J];控制工程;2011年03期

7 魏海坤,徐嗣鑫,宋文忠;神經(jīng)網(wǎng)絡(luò)的泛化理論和泛化方法[J];自動(dòng)化學(xué)報(bào);2001年06期

8 吳振坤;迎接知識(shí)經(jīng)濟(jì)時(shí)代的挑戰(zhàn)[J];施工企業(yè)管理;1999年11期

9 高仁祥,張世英,劉豹;基于神經(jīng)網(wǎng)絡(luò)的變量選擇方法[J];系統(tǒng)工程學(xué)報(bào);1998年02期

10 郭剛,史忠科,戴冠中;基于混沌理論進(jìn)行股票市場(chǎng)的多步預(yù)測(cè)[J];信息與控制;2000年02期

相關(guān)博士學(xué)位論文 前1條

1 殷光偉;中國(guó)股票市場(chǎng)預(yù)測(cè)方法的研究[D];天津大學(xué);2003年

相關(guān)碩士學(xué)位論文 前2條

1 翟曼;基于PSO優(yōu)化混沌BP神經(jīng)網(wǎng)絡(luò)的股票指數(shù)預(yù)測(cè)模型研究[D];河北大學(xué);2011年

2 溫渤;基于人工神經(jīng)元網(wǎng)絡(luò)的股票分析及其邏輯設(shè)計(jì)[D];哈爾濱工程大學(xué);2003年

本文編號(hào)：2169358