基于长短期记忆网络的黄金价格预测
Gold Price Prediction Based on Long Short-Term Memory Network
DOI: 10.12677/AAM.2020.96104, PDF,    科研立项经费支持
作者: 闫 铭*：太原理工大学数学学院，山西 晋中；李东喜：太原理工大学大数据学院，山西 晋中
关键词: 黄金价格；长短期记忆网络(LSTM)；短期预测；长期预测；Gold Price； Long Short-Term Memory Network (LSTM)； Short-Term Prediction； Long-Term Prediction
摘要: 精确的预测黄金价格，有助于投资者了解黄金市场的行情，并对他们做出正确的投资决策提供了科学有效的参考，因此，提高黄金价格的预测精度显得尤为重要。本文提出了一种基于长短期记忆网络(LSTM)模型的黄金价格预测方法。该方法结合黄金价格数据，利用长短期记忆网络生成训练模型，最终实现对黄金价格的预测。结果表明，本文的方法可行有效，较BP神经网络和SVR智能预测拥有更高的预测精度。
Abstract: Accurate prediction of gold price is helpful for investors to understand the gold market and provide scientific and effective reference for them to make correct investment decisions. Therefore, it is particularly important to improve the prediction accuracy of gold price. This paper presents a gold price forecasting method based on Long Short-term memory network (LSTM) model. This method combines the gold price data, uses LSTM model to generate training model, and finally realizes the prediction of gold price. The results show that this method is feasible and effective, and has higher prediction accuracy than BP neural network and SVR intelligent prediction.
文章引用：闫铭, 李东喜. 基于长短期记忆网络的黄金价格预测[J]. 应用数学进展, 2020, 9(6): 871-880. https://doi.org/10.12677/AAM.2020.96104

参考文献

[1] 谢睿航, 申慧涛, 段绪晨. 基于LSTM网络的地铁线路客流量预测[J/OL]. 中国战略新兴业: 1-2[2018-11-19].
[2] 曹博, 高茂庭. 基于LSTM的短时交通流预测研究[J]. 现代计算机(专业版), 2018(25): 3-7.
[3] 任君, 王建华, 王传美, 王建祥. 基于正则化LSTM模型的股票指数预测[J]. 计算机应用与软件, 2018, 35(4): 44-48+108.
[4] 凌晨, 张骅月. 基于BP神经网络的黄金价格预测分析[J]. 天津科技, 2014, 41(1): 68-73.
[5] 杨潇. 中国黄金期货价格的SVR智能预测研究[J]. 会计之友, 2017(17): 50-53.
[6] Hochreiter, S., Bengio, Y., Frasconi, P., et al. (2001) Gradient Flow in Recurrent Nets: The Difficulty of Learning Long-Term Dependencies. In: A Field Guide to Dynamical Recurrent Networks, Wiley-IEEE Press, Munchen, 237-243.
[7] Bengio, Y., Simard, P. and Frasconi, P. (1994) Learning Long-Term Dependencies with Gradient Descent Is Difficult. IEEE Transactions on Neural Networks, 5, 157-166. [Google Scholar] [CrossRef] [PubMed]
[8] 陈超学. 基于循环神经网络的声学车型识别研究[D]: [硕士学位论文]. 西安: 西安电子科技大学, 2015.
[9] 张磊. 基于深度学习的视频分析系统[D]: [硕士学位论文]. 南京: 南京邮电大学, 2017.
[10] Song, E., Soong, F.K. and Kang, H.G. (2017) Effective Spectral and Excitation Modeling Techniques for LSTM-RNN-Based Speech Synthesis Systems. IEEE/ACM Transactions on Audio, Speech and Language Processing, 25, 2152-2161. [Google Scholar] [CrossRef] 
[11] Cortez, B., Carrera, B., Kim, Y.-J. and Jung, J.-Y. (2018) An Architecture for Emergency Event Prediction Using LSTM Recurrent Neural Networks. Expert Systems with Applications, 97, 315-324. [Google Scholar] [CrossRef] 
[12] Li, Y.F. and Cao, H. (2018) Prediction for Tourism Flow Based on LSTM Neural Network. Procedia Computer Science, 129, 277-283. [Google Scholar] [CrossRef] 
[13] Li, Z.B., Peng, F., Niu, B.S., Li, G.Y., Wu, J. and Miao, Z. (2018) Water Quality Prediction Model Combining Sparse Auto-Encoder and LSTM Network. IFAC Papers Online, 51, 831-836. [Google Scholar] [CrossRef] 
[14] Sivakumar, S.C., Robertson, W. and Phillips, W.J. (1997) A Modified BPTT Algorithm for Trajectory Learning in Block-Diagonal Recurrent Neural Networks. IEEE 1997 Canadian Conference on Electrical and Computer Engineering Innovation: Voyage of Discovery, Saint Johns, 25-28 May 1997, 297-300. [Google Scholar] [CrossRef] 

为你推荐