發(fā)布時(shí)間：2018-04-14 04:14

  本文選題：人工神經(jīng)網(wǎng)絡(luò) + BP算法��； 參考：《大連理工大學(xué)》2012年碩士論文

【摘要】：股票市場(chǎng)自誕生以來(lái),隨著經(jīng)濟(jì)的發(fā)展,在金融市場(chǎng)中占據(jù)著非常重要的地位。但是股市受到國(guó)家政策、經(jīng)濟(jì)環(huán)境、突發(fā)事件和人為操控等諸多因素的影響,使投資者在享受高收益的同時(shí)也承擔(dān)著巨大的風(fēng)險(xiǎn)。對(duì)于占股市大多數(shù)的中小投資者來(lái)說(shuō),如果可以預(yù)測(cè)股市的走勢(shì),那么就可以盡可能地實(shí)現(xiàn)收益最大化和風(fēng)險(xiǎn)最小化。在股票市場(chǎng)中,股市指數(shù)體現(xiàn)著股市的整體走勢(shì),因此對(duì)股指進(jìn)行預(yù)測(cè)不僅具有理論研究意義,更具有重要的現(xiàn)實(shí)意義。 通過(guò)對(duì)股市預(yù)測(cè)的分析,了解到股市是一個(gè)復(fù)雜的非線性動(dòng)態(tài)系統(tǒng),傳統(tǒng)的線性預(yù)測(cè)方法的預(yù)測(cè)效果不甚理想,而B(niǎo)P神經(jīng)網(wǎng)絡(luò)具有很強(qiáng)的非線性逼近能力、自學(xué)習(xí)能力和自適應(yīng)能力,由于具有這些優(yōu)點(diǎn),BP神經(jīng)網(wǎng)絡(luò)成為股市預(yù)測(cè)領(lǐng)域使用廣泛的方法之一。 本文對(duì)基于BP神經(jīng)網(wǎng)絡(luò)的股指預(yù)測(cè)系統(tǒng)進(jìn)行了功能性需求和非功能性需求的分析,在需求分析的基礎(chǔ)上,根據(jù)系統(tǒng)需求提出的設(shè)計(jì)目標(biāo)和原則,進(jìn)行了系統(tǒng)的架構(gòu)設(shè)計(jì)和功能設(shè)計(jì),然后在詳細(xì)設(shè)計(jì)階段,對(duì)各模塊進(jìn)行了詳細(xì)的功能設(shè)計(jì)和數(shù)據(jù)庫(kù)設(shè)計(jì)。系統(tǒng)的核心模塊為股指預(yù)測(cè)模塊,本文重點(diǎn)對(duì)BP神經(jīng)網(wǎng)絡(luò)的模型設(shè)計(jì)、參數(shù)選取進(jìn)行了實(shí)驗(yàn)分析,并結(jié)合優(yōu)化網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu)、加入動(dòng)量項(xiàng)和改進(jìn)激活函數(shù)來(lái)對(duì)BP神經(jīng)網(wǎng)絡(luò)進(jìn)行改進(jìn),解決BP神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)精度不高、收斂速度慢和不穩(wěn)定等問(wèn)題,以提高系統(tǒng)的性能和預(yù)測(cè)準(zhǔn)確率。 最后通過(guò)預(yù)測(cè)結(jié)果表明,本文實(shí)現(xiàn)的基于BP神經(jīng)網(wǎng)絡(luò)的股指預(yù)測(cè)系統(tǒng)具有收斂速度快和預(yù)測(cè)精度高的優(yōu)點(diǎn),具有很高的實(shí)用價(jià)值。但是該預(yù)測(cè)系統(tǒng)還存在著一些缺點(diǎn),如預(yù)測(cè)范圍單一,只進(jìn)行了上證綜合指數(shù)的預(yù)測(cè)；預(yù)測(cè)精度尚有提高的空間以及系統(tǒng)的實(shí)用性尚待進(jìn)一步的驗(yàn)證。本文的下一階段工作是研究如何將使系統(tǒng)的應(yīng)用范圍更加廣泛以及如何結(jié)合其他算法對(duì)BP神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型進(jìn)行改進(jìn),以獲得更好的預(yù)測(cè)結(jié)果。
[Abstract]:Since the birth of the stock market, with the development of economy, it occupies a very important position in the financial market.However, the stock market is affected by many factors, such as national policy, economic environment, unexpected events and artificial manipulation, which make investors enjoy high returns and bear huge risks at the same time.For the small and medium-sized investors who make up the majority of the stock market, if they can predict the trend of the stock market, they can maximize the return and minimize the risk as far as possible.In the stock market, the stock market index reflects the overall trend of the stock market, so the prediction of the stock index is not only of theoretical significance, but also of practical significance.Through the analysis of the stock market forecast, it is found that the stock market is a complex nonlinear dynamic system, the traditional linear forecasting method is not very good, and the BP neural network has a strong nonlinear approximation ability.Self-learning ability and adaptive ability, because of these advantages, BP neural network has become one of the widely used methods in the field of stock market prediction.This paper analyzes the functional requirements and non-functional requirements of the stock index forecasting system based on BP neural network. On the basis of the demand analysis, the design objectives and principles are put forward according to the requirements of the system.The architecture and function of the system are designed, and then in the detailed design stage, the detailed functional design and database design of each module are carried out.The core module of the system is stock index prediction module. This paper focuses on the model design and parameter selection of BP neural network, and combines with the optimization of network topology.In order to improve the performance and prediction accuracy of BP neural network, momentum term and activation function are added to solve the problems of low prediction accuracy, slow convergence rate and instability of BP neural network.Finally, the prediction results show that the stock index prediction system based on BP neural network has the advantages of fast convergence and high prediction accuracy, and has high practical value.However, there are still some shortcomings in the prediction system, such as the single range of prediction, only the prediction of the Shanghai Composite Index, the room for improvement of the prediction accuracy and the practicability of the system need to be further verified.The next stage of this paper is to study how to make the application of the system more extensive and how to improve the BP neural network prediction model combined with other algorithms in order to obtain better prediction results.
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：TP183;F832.5

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 吳微,陳維強(qiáng),劉波;用BP神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)股票市場(chǎng)漲跌[J];大連理工大學(xué)學(xué)報(bào);2001年01期

2 高琴;談玲;;基于BP神經(jīng)網(wǎng)絡(luò)的股市預(yù)測(cè)模型[J];電腦知識(shí)與技術(shù)(學(xué)術(shù)交流);2007年02期

3 姚培福;許大丹;;BP神經(jīng)網(wǎng)絡(luò)在股票預(yù)測(cè)中的應(yīng)用研究[J];廣東自動(dòng)化與信息工程;2006年01期

4 鄭建剛;王行愚;牛玉剛;;基于改進(jìn)免疫遺傳算法的神經(jīng)網(wǎng)絡(luò)及其在股票預(yù)測(cè)中的應(yīng)用[J];華東理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2006年11期

5 王億楷;賴國(guó)明;;BP神經(jīng)網(wǎng)絡(luò)的改進(jìn)及其在股票預(yù)測(cè)中的應(yīng)用[J];韓山師范學(xué)院學(xué)報(bào);2008年06期

6 歐陽(yáng)金亮;陸黎明;;綜合改進(jìn)BP神經(jīng)網(wǎng)絡(luò)算法在股價(jià)預(yù)測(cè)中的應(yīng)用[J];計(jì)算機(jī)與數(shù)字工程;2011年02期

7 尹紹飛;蘇勇;;BP神經(jīng)網(wǎng)絡(luò)在股指預(yù)測(cè)中的應(yīng)用[J];科學(xué)技術(shù)與工程;2009年24期

8 李智;趙子先;鄭君;;動(dòng)量梯度下降法訓(xùn)練BP網(wǎng)絡(luò)[J];內(nèi)蒙古科技與經(jīng)濟(jì);2006年12期

9 王愛(ài)平;陶嗣干;王占鳳;;BP神經(jīng)網(wǎng)絡(luò)在股票預(yù)測(cè)中的應(yīng)用[J];微型機(jī)與應(yīng)用;2010年06期

10 楊一文,劉貴忠,張宗平;基于嵌入理論和神經(jīng)網(wǎng)絡(luò)技術(shù)的混沌數(shù)據(jù)預(yù)測(cè)及其在股票市場(chǎng)中的應(yīng)用[J];系統(tǒng)工程理論與實(shí)踐;2001年06期

相關(guān)碩士學(xué)位論文 前1條

1 鄭高峰;帶動(dòng)量項(xiàng)的BP神經(jīng)網(wǎng)絡(luò)收斂性分析[D];大連理工大學(xué);2005年

，

本文編號(hào)：1747655