本文關(guān)鍵詞： BP神經(jīng)網(wǎng)絡(luò) 粒子群優(yōu)化算法 趨勢(shì)因子 股市預(yù)測(cè)　出處：《吉林財(cái)經(jīng)大學(xué)》2013年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：鑒于智能計(jì)算方法具有自適應(yīng)、自學(xué)習(xí)、并行性等優(yōu)點(diǎn)，本文以智能計(jì)算方法為基礎(chǔ)，，通過(guò)引入趨勢(shì)因子和群智能等方法，提出了改進(jìn)BP神經(jīng)網(wǎng)絡(luò)模型并將其應(yīng)用于股市預(yù)測(cè)領(lǐng)域中。具體內(nèi)容包括：（1）通過(guò)對(duì)BP神經(jīng)網(wǎng)絡(luò)的輸入層、隱層和輸出層節(jié)點(diǎn)數(shù)目的確定，建立基于BP神經(jīng)網(wǎng)絡(luò)的股市預(yù)測(cè)模型，并將其對(duì)深圳成分指數(shù)進(jìn)行仿真模擬預(yù)測(cè)。實(shí)驗(yàn)結(jié)果表明，BP神經(jīng)網(wǎng)絡(luò)用于股市預(yù)測(cè)領(lǐng)域是可行的，有效的，具有一定的優(yōu)越性。（2）鑒于趨勢(shì)因子具有糾正預(yù)測(cè)方向的特性，為進(jìn)一步提高BP神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)性能，本文將趨勢(shì)因子引入到BP神經(jīng)網(wǎng)絡(luò)中，提出了引入趨勢(shì)因子BP神經(jīng)網(wǎng)絡(luò)，即DF-BPNN網(wǎng)絡(luò)(BP Neural Network with Direction Factor)。實(shí)驗(yàn)結(jié)果表明，與基本BP神經(jīng)網(wǎng)絡(luò)相比，本文提出的DF-BPNN模型的預(yù)測(cè)性能優(yōu)于BP神經(jīng)網(wǎng)絡(luò)，其預(yù)測(cè)精度有進(jìn)一步的改善。（3）鑒于粒子群優(yōu)化算法具有較好的全局搜索能力和優(yōu)化性能，本文利用粒子群優(yōu)化算法對(duì)BP神經(jīng)網(wǎng)絡(luò)的權(quán)重和閾值進(jìn)行優(yōu)化，提出了一種基于群智能的PSO-BP混合神經(jīng)網(wǎng)絡(luò)模型即PSO-BP NN（PSO-BP NeuralNetwork）。另外，采用本文提出的PSO-BPNN模型對(duì)深圳成分指數(shù)股市進(jìn)行預(yù)測(cè)，得到了令人滿意的結(jié)果。（4）針對(duì)本文提出的引入趨勢(shì)因子BP神經(jīng)網(wǎng)絡(luò)和PSO-BP混合神經(jīng)網(wǎng)絡(luò)，與基本BP神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)性能進(jìn)行比較研究。通過(guò)實(shí)驗(yàn)獲得的仿真模擬圖與數(shù)值結(jié)果表明，本文提出的引入趨勢(shì)因子BP神經(jīng)網(wǎng)絡(luò)與PSO-BP混合神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)性能均優(yōu)于基本BP神經(jīng)網(wǎng)絡(luò)，但引入趨勢(shì)因子BP神經(jīng)網(wǎng)絡(luò)與PSO-BP混合神經(jīng)網(wǎng)絡(luò)相比，其預(yù)測(cè)性能差別較小。
[Abstract]:In view of the advantages of self-adaptive, self-learning and parallelism, the intelligent computing method is based on the introduction of trend factor and swarm intelligence. This paper proposes an improved BP neural network model and applies it to the field of stock market prediction. The content includes: 1) by determining the number of nodes in the input layer, hidden layer and output layer of BP neural network, the stock market forecasting model based on BP neural network is established. The experimental results show that the BP neural network is feasible, effective and has some advantages in the field of stock market forecasting. (2) since the trend factor has the characteristics of correcting the forecast direction, In order to further improve the prediction performance of BP neural network, the trend factor is introduced into BP neural network in this paper, and a BP neural network with trend factor is proposed. The experimental results show that the BP neural network is compared with the basic BP neural network. The prediction performance of the proposed DF-BPNN model is better than that of BP neural network, and its prediction accuracy is further improved. In this paper, particle swarm optimization algorithm is used to optimize the weight and threshold of BP neural network, and a PSO-BP hybrid neural network model based on swarm intelligence is proposed, I. E. PSO-BP NN(PSO-BP neural network. The PSO-BPNN model proposed in this paper is used to predict the Shenzhen component index stock market, and a satisfactory result is obtained. The BP neural network and the PSO-BP hybrid neural network are introduced in this paper, and the trend factor BP neural network and the PSO-BP hybrid neural network are introduced in this paper. The prediction performance of BP neural network is compared with that of basic BP neural network. The simulation and numerical results obtained from experiments show that, The prediction performance of BP neural network and PSO-BP hybrid neural network proposed in this paper is better than that of basic BP neural network, but the difference of prediction performance between BP neural network and PSO-BP hybrid neural network is smaller.
【學(xué)位授予單位】：吉林財(cái)經(jīng)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類(lèi)號(hào)】：F224;F832.5

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王宜峰;王燕鳴;張顏江;;條件CAPM與橫截面定價(jià)檢驗(yàn):基于中國(guó)股市的經(jīng)驗(yàn)分析[J];管理工程學(xué)報(bào);2012年04期

2 郭琨;周煒星;成思危;;中國(guó)股市的經(jīng)濟(jì)晴雨表作用——基于熱最優(yōu)路徑法的動(dòng)態(tài)分析[J];管理科學(xué)學(xué)報(bào);2012年01期

3 李明;韓旭明;;引入懲罰收益因素OIF Elman神經(jīng)網(wǎng)絡(luò)及其應(yīng)用[J];計(jì)算機(jī)應(yīng)用研究;2007年06期

4 覃家琦;邵新建;趙映雪;;雙重上市、IPO抑價(jià)與大規(guī)模融資行為——來(lái)自中國(guó)公司IPO的證據(jù)[J];金融研究;2012年03期

5 田丁石;肖俊超;;異質(zhì)風(fēng)險(xiǎn)、市場(chǎng)有效性與CAPM異象研究——基于滬深股市橫截面收益分析[J];南開(kāi)經(jīng)濟(jì)研究;2012年05期

6 羅玫;宋云玲;;中國(guó)股市的業(yè)績(jī)預(yù)告可信嗎?[J];金融研究;2012年09期

7 張戡;李婷;李凌飛;;基于聚類(lèi)分析與協(xié)整檢驗(yàn)的A股市場(chǎng)統(tǒng)計(jì)套利策略[J];統(tǒng)計(jì)與決策;2012年15期

8 王治政;吳衛(wèi)星;;中美股市波動(dòng)特征比較研究:基于ARCH類(lèi)模型的實(shí)證分析[J];上海金融;2012年09期

9 林黎;任若恩;;泡沫隨機(jī)臨界時(shí)點(diǎn)超指數(shù)膨脹模型:中國(guó)股市泡沫的檢測(cè)與識(shí)別[J];系統(tǒng)工程理論與實(shí)踐;2012年04期

10 王德明;王莉;張廣明;;基于遺傳BP神經(jīng)網(wǎng)絡(luò)的短期風(fēng)速預(yù)測(cè)模型[J];浙江大學(xué)學(xué)報(bào)(工學(xué)版);2012年05期

相關(guān)博士學(xué)位論文 前2條

1 許相莉;基于智能計(jì)算的圖像檢索算法研究[D];吉林大學(xué);2011年

2 王麗敏;計(jì)算智能改進(jìn)方法及其在金融與環(huán)境領(lǐng)域中的應(yīng)用[D];吉林大學(xué);2007年

本文編號(hào)：1555340