Abstract
Compared with the traditional time series prediction model, neural network has obvious advantages for the analysis of nonlinear time series data. However, the topology structure and the training algorithm of neural network have a great influence on the prediction accuracy. Taking stock data as an instance, this paper analyzes the impacts factors of prediction ability of neural network such as topology structure, training algorithm and dataset. The experimental results show that the training algorithm and the size of dataset have significant influence on the performance of neural network.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Akaike H (1969) Fitting autoregressive models for prediction. Ann Inst Stat Math 21(1):243–247
Box GEP, Jenkins GM, Reinsel GC et al (2015) Time Series Analysis: Forecasting and Control. Wiley, Hoboken
Granger CWJ, Joyeux R (1980) An introduction to long-memory time series models and fractional differencing. J Time Ser Anal 1(1):15–29
Varfis A, Versino C (1990) Univariate economic time series forecasting by connectionist methods. In: Proceedings of INNC, vol 90, pp 342–345
Liu X (2016) Research on the mothed of forecasting stock price based on the BP neural network: taking military industry as an example. Beijing Jiaotong university, Beijing
Xiao Q (2017) The research and application of artificial neural networks in stock price forecasting. South China University of Technology, Guangzhou
Chen YY, Zhang ZX, Li WB (2014) Neural network based stock price prediction model. Comput Appl Softw 31(5):89–92
Han L (2016) Research on the stock prediction based on LM-BP neural networks. Northeast Agricultural University, Harbin
Liu XY (2018) Time series prediction and its application. Financ Theory Teach 1:010
Guo JF, Li Y, An D (2017) Prediction for short-term sock price based on LM-GA-BP neural network. Comput Technol Dev 27(01):152–155+15
Yang H, Ma JH (2017) Research on method of regularization parameter solution. Comput Measure Control 25(8):226–229
Jiao RQ (2017) Regularization parameters selection of Bayesian penalized regression. Southwest Jiaotong University, Chengdu
Wang L, Peng L, Xia D, Zeng Y (2015) BP neural network incorporating self-adaptive differential evolution algorithm for time series forecasting. Comput Eng Sci 37(12):2270–2275
Chou JS, Nguyen TK (2018) Forward forecast of stock price using sliding-window metaheuristic-optimized machine learning regression. IEEE Trans Ind Inf PP(99):1
Cai RH, Cui YX, Xue P (2017) Research on the methods of determining the number of hidden nodes in three layer BP neural network. Comput Inf Technol 25(5):29–33
Nielsen MA (2015) Neural Networks and Deep Learning. Determination press, USA
Acknowledgements
This paper is supported by Gansu Provincial Department of Education Project (2016B-027).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Hou, Y., Liu, H., Xie, B., Ding, F. (2020). The Impact Factors of Neural Network Based Time Series Prediction: Taking Stock Price as an Example. In: Xu, Z., Choo, KK., Dehghantanha, A., Parizi, R., Hammoudeh, M. (eds) Cyber Security Intelligence and Analytics. CSIA 2019. Advances in Intelligent Systems and Computing, vol 928. Springer, Cham. https://doi.org/10.1007/978-3-030-15235-2_134
Download citation
DOI: https://doi.org/10.1007/978-3-030-15235-2_134
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-15234-5
Online ISBN: 978-3-030-15235-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)