Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 6, Issue 5, 2022

Research on Stock Price Prediction Based on Orthogonal Gaussian Basis Function Expansion and Pearson Correlation Coefficient Weighted LSTM Neural Network

Download as PDF

DOI: 10.23977/acss.2022.060504 | Downloads: 19 | Views: 615

Author(s)

Shun Lin 1, Yuan Feng 2

Affiliation(s)

1 School of Fiance, Hunan University of Technology and Bussiness, Changsha, 410205, China
2 School of Economics, Central South University of Forestry and Technology, Changsha, 410004, China

Corresponding Author

Shun Lin

ABSTRACT

For stock price prediction in quantitative finance, deep learning techniques such as LSTM neural network do not need the stationarity assumption of traditional time series models (such as ARIMA and GARCH) and can forecast medium and long-term time series, so they have attracted much attention. This paper proposes an improved LSTM neural network based on orthogonal Gaussian basis function expansion and Pearson correlation coefficient weighting. The proposed method uses the functional features of intra-day prices to fit the residual series predicted by the LSTM neural network. Considering that the underlying model structure between each component of the function eigenvector and the residual series is unknown, we use the Bagging method to capture and trade off the variance and bias of the prediction model. In addition, since the dimension of the predictive variable of the LSTM neural network is a parameter to be estimated, we use the model averaging method based on Pearson correlation coefficient weighting for tuning. The results of actual data analysis show that the proposed method can significantly improve the prediction accuracy of the original LSTM neural network and has certain robustness. Finally, the proposed method can be further applied to consumer price index (CPI) prediction, daily average temperature prediction, and real-time monitoring of environmental trace elements.

KEYWORDS

Stock price prediction, model averaging, orthogonal Gaussian basis function, Bagging

CITE THIS PAPER

Shun Lin, Yuan Feng, Research on Stock Price Prediction Based on Orthogonal Gaussian Basis Function Expansion and Pearson Correlation Coefficient Weighted LSTM Neural Network. Advances in Computer, Signals and Systems (2022) Vol. 6: 23-30. DOI: http://dx.doi.org/10.23977/acss.2022.060504.

REFERENCES

[1] Rahimi, Z. H., & Khashei, M. A Least Squares-based Parallel Hybridization of Statistical and Intelligent Models for Time Series Forecasting [J]. Computers & Industrial Engineering, 2018, 118(2): 21-23.
[2] WAN Rui; Institute of Mathematics and Statistics, Changchun University of Technology;. Stock Price Volatility Forecast Based on GARCH Model [J]. Science & Technology Information, 2022, 20(6): 129-132.
[3] Xiong Jinghua; Ru Jing; School of Economics and Finance, South China University of Technology; School of Water Resources and Hydropower Engineering, Wuhan University;. Research on Exchange Rate Forecasting Integrated Model Based on Random Forest and Fuzzy Information Granulation [J]. The Journal of Quantitative & Technical Economics, 2021, 38(1): 135-156.
[4] Sun Shaoyan; SUN Wenxuan; China State-owned Economy Research Center, Jilin University, Jilin University; School of Economics, Jilin University, Jilin University. Research on the Fluctuation Law of RMB Exchange Rate after Joining SDR [J]. On Economic Problems, 2019(2): 42-47.
[5] Zheng Hong, Duan Zhongdong, Wang Zhen, Li Hongwei; School of Civil and Environment Engineering, Harbin Institute of Technology; Ninbo Shangong Intelligent Security Technology Co., Ltd.;. Structural Damage Detection Based on Autoregressive Model and Kernel Principal Component Analysis [J]. Intelligent Building & Smart City, 2020(5): 15-19.
[6] Bao Yueyan. Covariance matrix prediction model based on LSTM using high frequency data [J]. Journal of Chongqing Technology and Business University (Natural Science Edition), 2022(4): 1-7.
[7] Zeng Lifang, Li Liping. The Bank of China Stock Price Forecast Empirical Analysis Based on BP Neural Network and GARCH Model [D]. Yunnan: Chinese Master's Theses Full-text Database, 2020.
[8] Yang Guijun, Du Feia, Ji Xiaolei, School of Statistics, Tianjin University of Finance and Economics; China Center for Economic Statistics Research, Tianjin University of Finance and Economics;. Financial Early Warning Model of BP Neural Network Based on the First and the Last Quality Factors [J]. Statistics & Decision, 2022, 38(3): 166-171.
[9] Zhang, G. Time Series Forecasting Using a Hybrid Arima and Neural Network Model [J]. Neurocomputing, 2003, 50(0): 5-7.
[10] Anna, M., Aurelia, R., Artur, D., & Joachim, P. Forecasting of Natural Gas Consumption in Poland Based on Arima-lstm Hybrid Model [J]. Energies, 2021, 14(24): 12-13.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 19418
Visits: 296844

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.