本文選題：人工神經(jīng)網(wǎng)絡(luò) + BP算法�。� 參考：《華東理工大學(xué)》2013年碩士論文

【摘要】：隨著人們對(duì)投資思想的重視,人們?cè)谌粘；顒?dòng)中越來(lái)越關(guān)注股市。然而股票投資屬于一種高風(fēng)險(xiǎn)和高收益并存的投資領(lǐng)域,因此投資者們一直都非常關(guān)注有關(guān)股票價(jià)格的預(yù)測(cè)。自從股票市場(chǎng)開(kāi)始出現(xiàn),它就一直為國(guó)內(nèi)外的許多學(xué)者所研究,同時(shí)眾多的有關(guān)股票價(jià)格的預(yù)測(cè)方法也相應(yīng)被提出。本文在基于各種分析之后提出了利用三層BP神經(jīng)網(wǎng)絡(luò)來(lái)構(gòu)建股票預(yù)測(cè)模型。然而傳統(tǒng)的BP網(wǎng)絡(luò)尚存諸多不足之處,例如對(duì)初始權(quán)值的敏感、算法搜索時(shí)很難達(dá)到全局最優(yōu)值、訓(xùn)練速率較慢等,因此應(yīng)用于股票預(yù)測(cè)的效果欠佳。基于以上存在的缺陷,本文提出首先使用主成分分析法預(yù)處理網(wǎng)絡(luò)輸入變量,可以減少變量維數(shù),降低股價(jià)數(shù)據(jù)的噪聲。然后利用遺傳算法優(yōu)化網(wǎng)絡(luò)參數(shù),在網(wǎng)絡(luò)訓(xùn)練過(guò)程中,選擇LM算法以避免網(wǎng)絡(luò)陷入局部極小值并促進(jìn)網(wǎng)絡(luò)的收斂速度。最后,詳細(xì)討論了網(wǎng)絡(luò)的拓?fù)浣Y(jié)構(gòu)及其參數(shù)的確定原則,例如隱含層節(jié)點(diǎn)數(shù)和訓(xùn)練參數(shù)等。預(yù)測(cè)結(jié)果表明本文使用的優(yōu)化算法的可行性。
[Abstract]:With the attention of people to the investment thought, people pay more and more attention to the stock market in their daily activities. However, stock investment is a high risk and high yield investment field, so investors have been very concerned about the stock price forecast. Since the emergence of stock market, it has been studied by many scholars both at home and abroad, and many forecasting methods about stock price have been put forward accordingly. In this paper, based on various analyses, a three-layer BP neural network is proposed to build stock forecasting model. However, the traditional BP network still has many shortcomings, such as sensitivity to initial weights, difficulty to reach the global optimal value in algorithm search, slow training rate, and so on, so the effect of applying it to stock prediction is not good. Based on the above defects, this paper proposes that the principal component analysis (PCA) is first used to preprocess the input variables of the network, which can reduce the dimension of variables and reduce the noise of stock price data. Then genetic algorithm is used to optimize the network parameters. In the process of network training, LM algorithm is selected to avoid the network falling into a local minimum and to promote the convergence speed of the network. Finally, the topological structure of the network and the determination principle of its parameters, such as the number of hidden layer nodes and the training parameters, are discussed in detail. The prediction results show the feasibility of the optimization algorithm used in this paper.
【學(xué)位授予單位】：華東理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類(lèi)號(hào)】：TP183;F830.91

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 蔣云彩,萬(wàn)頃波;MATLAB遺傳算法工具箱(GAOT)的應(yīng)用[J];江西電力職業(yè)技術(shù)學(xué)院學(xué)報(bào);2004年03期

2 陳智軍;基于改進(jìn)型遺傳算法的前饋神經(jīng)網(wǎng)絡(luò)優(yōu)化設(shè)計(jì)[J];計(jì)算機(jī)工程;2002年04期

3 姬春煦;張駿;;基于主成分分析的股票指數(shù)預(yù)測(cè)研究[J];計(jì)算機(jī)工程與科學(xué);2006年08期

4 吳成東,王長(zhǎng)濤;人工神經(jīng)元BP網(wǎng)絡(luò)在股市預(yù)測(cè)方面的應(yīng)用[J];控制工程;2002年03期

5 王曉東;薛宏智;賈雯超;;基于BP神經(jīng)網(wǎng)絡(luò)的股票漲跌預(yù)測(cè)模型[J];價(jià)值工程;2010年31期

6 蘇高利,鄧芳萍;論基于MATLAB語(yǔ)言的BP神經(jīng)網(wǎng)絡(luò)的改進(jìn)算法[J];科技通報(bào);2003年02期

7 陳希;朱眾望;王玉峰;;基于遺傳神經(jīng)網(wǎng)絡(luò)上市公司股價(jià)向基本面回歸的分析研究[J];科學(xué)技術(shù)與工程;2011年27期

8 高雪鵬,叢爽;BP網(wǎng)絡(luò)改進(jìn)算法的性能對(duì)比研究[J];控制與決策;2001年02期

9 武振,鄭丕諤;基于遺傳神經(jīng)網(wǎng)絡(luò)的股價(jià)波動(dòng)預(yù)測(cè)[J];天津大學(xué)學(xué)報(bào)(社會(huì)科學(xué)版);2004年04期

10 李杰;王建中;胡紅萍;;基于PCA的BP神經(jīng)網(wǎng)絡(luò)股票預(yù)測(cè)研究[J];太原師范學(xué)院學(xué)報(bào)(自然科學(xué)版);2011年03期

，

本文編號(hào)：2014903