[1]邓烜堃,万 良,马彦勤.深度稀疏修正神经网络在股票预测中的应用[J].计算机技术与发展,2018,28(09):199-204.[doi:10.3969/ j. issn.1673-629X.2018.09.041]
　DENG Xuan-kun,WAN Liang,MA Yan-qin.Application of Deep Sparse Modified Neural Network in Stock Forecasting[J].,2018,28(09):199-204.[doi:10.3969/ j. issn.1673-629X.2018.09.041]
点击复制

深度稀疏修正神经网络在股票预测中的应用()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年09期
页码:
199-204
栏目:
应用开发研究
出版日期:
2018-09-10

文章信息/Info

Title:
Application of Deep Sparse Modified Neural Network in Stock Forecasting
文章编号:
1673-629X(2018)09-0199-06
作者:
邓烜堃 1; 2; 万 良 1; 2; 马彦勤1
1. 贵州大学 计算机科学与技术学院,贵州 贵阳 550025; 2. 贵州大学 计算机软件与理论研究所,贵州 贵阳 550025
Author(s):
DENG Xuan-kun 1; 2; WAN Liang 1; 2; MA Yan-qin1
1. School of Computer Science &Technology,Guizhou University,Guiyang 550025,China; 2. Institute of Computer Software and Theory,Guizhou University,Guiyang 550025,China
关键词:
深度神经网络; 股票预测; 主成分分析; 激活函数; 权值初始化
Keywords:
deep neural network; stock forecasting; principal component analysis; activation function; weight initialization
分类号:
TP183
DOI:
10.3969/ j. issn.1673-629X.2018.09.041
文献标志码:
A
摘要:
传统的股票预测基于统计学的方法,虽然在股票的趋势预测中有效,但是价格预测的准确度不够令人满意。因此,文中利用神经网络研究股票价格的预测问题。 神经网络具有很强的非线性拟合能力,适用于股票等非线性系统建模。文中采集了股票交易的历史数据作为数据集,对数据使用了归一化和主成分分析方法进行预处理,降低了数据维度,有利于简化模型和降低计算复杂度。 针对模型的构建,设计了一种深度稀疏修正神经网络模型(deep sparse rectifier neural networks,DSRNN)。 DSRNN 具有多层网络结构,基于带动量项的 BP 学习算法训练参数,利用了激活函数 ReLU(rectified linear units)和提出的权值初始化方法。 并将其与其他三种基于传统方法建立的模型进行了比较,结果表明 DSRNN 在健壮性、精确度方面都有更好的表现。
Abstract:
The traditional stock forecasting is based on statistics,which is effective in forecasting stock trends but not satisfactory in the accuracy of price forecasting. Therefore,we apply the neural network for study on the forecast of stock prices. Neural network has a strong nonlinear fitting,suitable for non-linear system modeling like stock. In this paper,we collect the historical data of stock trading as the data sets,using the normalization and principal component analysis to preprocess them,which are advantageous to model simplification and computational complexity reduction. For the model construction,we design a deep sparse correction neural network model (DSRNN)which has a multi-layer network structure,training parameters based on the BP learning algorithm with momentum,using the ReLU (reactive function units) and weight initialization method proposed. Comparing with the other three models based on traditional methods,it shows that DSRNN performs better in terms of robustness and accuracy.

相似文献/References:

[1]刘利 何先平 袁文亮.股票趋势预测中Wrapper方法的研究与应用[J].计算机技术与发展,2010,(01):209.
　LIU Li,HE Xian-ping,YUAN Wen-liang.Research and Application of Wrapper Approach to Stock Trend Prediction[J].,2010,(09):209.
[2]林舒都,邵曦.基于i-vector和深度学习的说话人识别[J].计算机技术与发展,2017,27(06):66.
　LIN Shu-du,SHAO Xi. Speaker Recognition with i-vector and Deep Learning[J].,2017,27(09):66.
[3]秦牧轩,荆晓远,吴 飞.基于公共空间嵌入的端到端深度零样本学习[J].计算机技术与发展,2018,28(11):44.[doi:10.3969/ j. issn.1673-629X.2018.11.010]
　QIN Mu-xuan,JING Xiao-yuan,WU Fei.End-to-end Deep Zero-shot Learning Based on Co-space Embedding[J].,2018,28(09):44.[doi:10.3969/ j. issn.1673-629X.2018.11.010]
[4]郎 波,樊一娜.基于深度神经网络的个性化学习行为评价方法[J].计算机技术与发展,2019,29(07):6.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 002]
　LANG Bo,FAN Yi-na.Personalized Learning Behavior Evaluation Method Based on Deep Neural Network[J].,2019,29(09):6.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 002]
[5]马文斌,夏国恩.基于深度神经网络的客户流失预测模型[J].计算机技术与发展,2019,29(09):76.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 015]
　MA Wen-bin,XIA Guo-en.Customer Churn Prediction Model Based on Deep Neural Network[J].,2019,29(09):76.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 015]
[6]陈可心,黄 刚.CStock:一种结合新闻与股价的股票走势预测模型[J].计算机技术与发展,2020,30(09):18.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 004]
　CHEN Ke-xin,HUANG Gang.Cstock:A Stock Trend Forecasting Model Combining News and Stock Price[J].,2020,30(09):18.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 004]
[7]贾欣齐,李 睿,张志成,等.DenseNet-GRU:直肠癌 CT 影像分类的深度神经网络模型[J].计算机技术与发展,2021,31(03):111.[doi:10. 3969 / j. issn. 1673-629X. 2021. 03. 019]
　JIA Xin-qi,LI Rui,ZHANG Zhi-cheng,et al.DenseNet-GRU:A Deep Neural Network Model for CT Image Classification of Rectal Cancer[J].,2021,31(09):111.[doi:10. 3969 / j. issn. 1673-629X. 2021. 03. 019]
[8]利向晴,夏国恩,张显全,等.基于深度神经网络权重集成的客户流失预测[J].计算机技术与发展,2021,31(10):18.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 004]
　LI Xiang-qing,XIA Guo-en,ZHANG Xian-quan,et al.Customer Churn Prediction Based on Deep Neural Network Weight Ensemble[J].,2021,31(09):18.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 004]
[9]王 闯,沈苏彬.一种基于多智能体的分布式深度神经网络算法[J].计算机技术与发展,2021,31(12):45.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 008]
　WANG Chuang,SHEN Su-bin.A Distributed Deep Neural Network Algorithm Based on Multi-agent[J].,2021,31(09):45.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 008]
[10]盛良睿,程 旗,李 捷,等.基于稀疏裁剪和深度可分离的轻量化方法[J].计算机技术与发展,2022,32(S1):36.[doi:10. 3969 / j. issn. 1673-629X. 2022. S1. 008]
　SHENG Liang-rui,CHENG Qi,LI Jie,et al.Lightweight Method Based on Sparse Clipping and Depth Separability[J].,2022,32(09):36.[doi:10. 3969 / j. issn. 1673-629X. 2022. S1. 008]

更新日期/Last Update: 2018-09-10