本文選題：股票指數(shù)預(yù)測(cè) + 神經(jīng)網(wǎng)絡(luò)�。� 參考：《大連海事大學(xué)》2012年碩士論文

【摘要】：證券是一個(gè)高度復(fù)雜的非線性動(dòng)態(tài)系統(tǒng),其變化規(guī)律既有一定的自身的趨勢(shì)性,又受政治、經(jīng)濟(jì)、心理等諸多因素的影響。證券市場(chǎng)的高風(fēng)險(xiǎn)高收益一直倍受投資者的關(guān)注,為了獲取豐厚的收益,如何建立一個(gè)成功率比較高的預(yù)測(cè)理論和模型,成為了學(xué)術(shù)界研究的熱點(diǎn)問題。 已有的研究工作是從技術(shù)分析、心理分析以及數(shù)理統(tǒng)計(jì)為基礎(chǔ)的的時(shí)間序列定量預(yù)測(cè)方法,然而其在股市的研究中面臨著許多困難,難以取得滿意的效果。隨著證券市場(chǎng)混沌和分形理論的逐步確立,人們開始利用神經(jīng)網(wǎng)絡(luò)對(duì)證券市場(chǎng)的變動(dòng)加以預(yù)測(cè)。神經(jīng)網(wǎng)絡(luò)具有自組織、自適應(yīng)和學(xué)習(xí)非線性映射強(qiáng)等特點(diǎn),能自動(dòng)從歷史數(shù)據(jù)中提取有關(guān)經(jīng)濟(jì)活動(dòng)中的知識(shí),非常適合應(yīng)用于經(jīng)濟(jì)領(lǐng)域的信息處理以及分析時(shí)間序列,對(duì)于解決股票預(yù)測(cè)領(lǐng)域中的一些問題比較實(shí)用。BP(Back Propagation)網(wǎng)絡(luò)是一種被廣泛運(yùn)用的神經(jīng)網(wǎng)絡(luò),它的核心是BP算法,是一種對(duì)于眾多基本子系統(tǒng)構(gòu)成的大系統(tǒng)進(jìn)行計(jì)算的嚴(yán)格而有效的方法。 本文首先分析了股票預(yù)測(cè)的需求,并介紹了神經(jīng)網(wǎng)絡(luò)的基本原理和方法。結(jié)合股票市場(chǎng)中的實(shí)際問題,提出了基于BP人工神經(jīng)網(wǎng)絡(luò)的股票預(yù)測(cè)模型,實(shí)現(xiàn)了三層的BP網(wǎng)絡(luò)來對(duì)上海交易所上證指數(shù)進(jìn)行預(yù)測(cè)。 最后通過實(shí)驗(yàn)分析證明了BP神經(jīng)網(wǎng)絡(luò)不僅能夠?qū)W習(xí)訓(xùn)練集的例子,且能從訓(xùn)練集中提煉出某種一般性原理、規(guī)律,具有較強(qiáng)的非線性函數(shù)擬合特性,因此對(duì)于預(yù)測(cè)短周期內(nèi)股指波動(dòng)有較強(qiáng)的適用性。
[Abstract]:Securities is a highly complex nonlinear dynamic system, its change law has its own tendency, and is influenced by many factors such as politics, economy, psychology and so on. The high risk and high yield of the securities market has been paid much attention by investors. In order to obtain rich income, how to establish a prediction theory and model with high success rate has become a hot issue in academic circles. The existing research work is based on technical analysis, psychological analysis and mathematical statistics. However, it faces many difficulties in the research of stock market, and it is difficult to obtain satisfactory results. With the gradual establishment of chaos and fractal theory in securities market, people begin to use neural network to predict the change of securities market. Neural network has the characteristics of self-organization, self-adaptation and strong learning nonlinear mapping. It can automatically extract knowledge about economic activities from historical data. It is very suitable for information processing and analysis of time series in the economic field. For solving some problems in the field of stock forecasting, the BP back propagation network is a widely used neural network, the core of which is BP algorithm. It is a strict and effective method for computing large scale systems composed of many basic subsystems. This paper first analyzes the demand of stock forecasting, and introduces the basic principle and method of neural network. Combined with the practical problems in the stock market, a stock forecasting model based on BP artificial neural network is proposed, and a three-layer BP network is implemented to predict the Shanghai Stock Exchange index. Finally, it is proved that BP neural network can not only learn the example of training set, but also extract some general principles and rules from the training set, and has strong nonlinear function fitting characteristic. Therefore, it has strong applicability to predict the volatility of stock index in short period.
【學(xué)位授予單位】：大連海事大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：F830.91;TP183

【相似文獻(xiàn)】

中國期刊全文數(shù)據(jù)庫 前10條

1 戚杰,周敬宣,陳云峰,李艷萍;區(qū)域環(huán)境-經(jīng)濟(jì)系統(tǒng)的動(dòng)態(tài)仿真——以南水北調(diào)后的湖北省襄樊市為例[J];系統(tǒng)工程理論與實(shí)踐;2004年03期

2 楊楠;趨勢(shì)外推法在房價(jià)指數(shù)預(yù)測(cè)中的應(yīng)用[J];統(tǒng)計(jì)與預(yù)測(cè);2004年01期

3 張神勇;從商品零售物價(jià)指數(shù)預(yù)測(cè)看保值補(bǔ)貼率的變化趨勢(shì)[J];上海統(tǒng)計(jì);1996年04期

4 徐靜芳;1999年上海物價(jià)指數(shù)預(yù)測(cè)與調(diào)控[J];上海綜合經(jīng)濟(jì);1999年01期

5 王悅;人工神經(jīng)網(wǎng)絡(luò)在經(jīng)濟(jì)預(yù)測(cè)中的應(yīng)用[J];北京廣播電視大學(xué)學(xué)報(bào);2002年01期

6 王渡;;基于改進(jìn)的BP網(wǎng)絡(luò)的循環(huán)流化床鍋爐建模[J];科技創(chuàng)新導(dǎo)報(bào);2009年12期

7 劉丹;;基于一種改進(jìn)的BP神經(jīng)網(wǎng)絡(luò)的飛機(jī)目標(biāo)識(shí)別[J];中國高新技術(shù)企業(yè);2011年16期

8 馮居易;;神經(jīng)網(wǎng)絡(luò)在股票價(jià)格預(yù)測(cè)中的建模及應(yīng)用[J];福建電腦;2009年01期

9 賀艷輝;袁永明;張紅燕;龔，

本文編號(hào)：1846048