本文選題：股價 + BP神經(jīng)網(wǎng)絡(luò)�。� 參考：《天津科技大學(xué)》2012年碩士論文

【摘要】：證券市場對國民經(jīng)濟的推動作用毋庸置疑,尤其是在經(jīng)濟全球化的形勢下,證券市場能否健康發(fā)展直接影響國家的經(jīng)濟競爭力。在我國資本市場中存在一種觀點,我國上市公司的股票業(yè)績與基本面無關(guān),價格失真。 股票市場是一個極其復(fù)雜的非線性系統(tǒng),然而神經(jīng)網(wǎng)絡(luò)具有很強的自學(xué)習(xí)、自適應(yīng)和非線性逼近能力等特性。遺傳算法根據(jù)適者生存的原理進行全局搜索,注重搜索未知區(qū)域,將遺傳算法和神經(jīng)網(wǎng)絡(luò)算法結(jié)合起來,可充分發(fā)揮他們的優(yōu)勢。為此,本文采取遺傳算法和神經(jīng)網(wǎng)絡(luò)技術(shù)對上市公司股票價格與基本面的關(guān)聯(lián)性進行實證研究。 本文詳細分析了影響我國股票價格的諸多因素,從宏觀經(jīng)濟走向、上市公司業(yè)績、其他因素這三個影響我國股票價格的主要因素中確立了神經(jīng)網(wǎng)絡(luò)模型的輸入?yún)?shù),分別是每股收益、凈資產(chǎn)收益率、流通股本、GDP (Gross Domestic Product)和CPI (Consumer Price Index);輸出參數(shù)為股票價格。 本文選擇BP (Back-Propagation)神經(jīng)網(wǎng)絡(luò)建模。通過實驗確定了模型的層數(shù)及神經(jīng)元個數(shù)和權(quán)值矩陣。使用Levenberg-Marquardt算法對BP神經(jīng)網(wǎng)絡(luò)進行了改進,減少了BP神經(jīng)網(wǎng)絡(luò)的訓(xùn)練時間,提高了BP神經(jīng)網(wǎng)絡(luò)的收斂精度。通過遺傳算法與神經(jīng)網(wǎng)絡(luò)結(jié)合,用遺傳算法對BP神經(jīng)網(wǎng)絡(luò)的初始權(quán)值和閾值進行優(yōu)化。構(gòu)建了上市公司股價與基本面因素研究的模型。 最后,使用MATLAB對模型進行仿真、訓(xùn)練、驗證。結(jié)果表明：雖然很長一段時間股價脫離基本面運行,但是隨著市場秩序的規(guī)范和股票市場的健康發(fā)展,上市公司的股價正逐步趨向價值回歸。
[Abstract]:There is no doubt about the promotion of the securities market to the national economy , especially in the situation of economic globalization , the healthy development of the securities market directly affects the economic competitiveness of the country . In the capital market of our country , there is a view that the stock performance of the listed company is independent of the fundamental plane and the price is distorted .

The stock market is an extremely complex nonlinear system , however , the neural network has strong self - learning , self - adaptation and nonlinear approximation ability . Genetic algorithm is based on the principle of the survival of the author . It focuses on searching unknown regions , combining genetic algorithm and neural network algorithm to give full play to their advantages . To this end , the paper adopts genetic algorithm and neural network technology to study the relationship between stock price and basic surface .

This paper analyzes the factors that affect the stock price of our country , and establishes the input parameters of the neural network model from the three main factors that affect the stock price of our country from the macro - economic trend , the company ' s performance and other factors . The input parameters of the neural network model are the earnings per share , the yield of net assets , the current share , gross domestic product and CPI ( Consumer Price Index ) , and the output parameters are stock price .

By using Levenberg - Marquardt algorithm , the BP neural network is improved , the training time of BP neural network is reduced , the convergence accuracy of BP neural network is improved , and the initial weight and threshold of BP neural network are optimized by genetic algorithm .

Finally , using MATLAB to simulate , train and validate the model , the results show that the stock price of the listed company is gradually returning to value with the regulation of the market order and the healthy development of the stock market .
【學(xué)位授予單位】：天津科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2012
【分類號】：TP183;F275;F832.51

【參考文獻】

相關(guān)期刊論文 前10條

1 韓力群;;神經(jīng)網(wǎng)絡(luò)研究趨勢展望[J];北京工商大學(xué)學(xué)報(自然科學(xué)版);2007年06期

2 張吉剛;;基于BP神經(jīng)網(wǎng)絡(luò)股價預(yù)測的一種改進方法[J];長江大學(xué)學(xué)報(自科版)理工卷;2007年03期

3 盧t澤;葉德謙;南敏;;基于遺傳算法和神經(jīng)網(wǎng)絡(luò)的股票價格預(yù)測[J];電腦開發(fā)與應(yīng)用;2010年02期

4 梁化樓，戴貴亮;人工神經(jīng)網(wǎng)絡(luò)與遺傳算法的結(jié)合：進展及展望[J];電子學(xué)報;1995年10期

5 侯木舟,韓旭里;基于MATLAB的神經(jīng)網(wǎng)絡(luò)在股市預(yù)測中的應(yīng)用[J];系統(tǒng)工程;2003年02期

6 智晶;張冬梅;姜鵬飛;;基于主成分的遺傳神經(jīng)網(wǎng)絡(luò)股票指數(shù)預(yù)測研究[J];計算機工程與應(yīng)用;2009年26期

7 王麗薇，洪勇，洪家榮;遺傳算法的收斂性研究[J];計算機學(xué)報;1996年10期

8 張靜;;BP神經(jīng)網(wǎng)絡(luò)改進算法的比較研究[J];科技信息(學(xué)術(shù)研究);2006年05期

9 席裕庚，柴天佑，，惲為民;遺傳算法綜述[J];控制理論與應(yīng)用;1996年06期

10 張鈴,ahu.edu.cn,張鈸;遺傳算法機理的研究[J];軟件學(xué)報;2000年07期

本文編號：1909026