Bayesian Regularization Neural Network Model for Stock Time Series Prediction

doi:10.23940/ijpe.19.12.p19.32713278

Abstract

Abstract: With strong nonlinear characterization ability, a BP neural network can effectively describe the characteristics of nonlinear time series. However, there are still some limitations, such as the ease of falling into a local optimum. Aiming at this problem, the Bayesian regularization optimization algorithm was used to improve the BP neural network. Under the premise of minimizing the objective function, the algorithm adjusts the weight update function through the conditional probability density and the prior probability of the historical data. Thus, the generalization capability of BP neural network will be enhanced. After an empirical study on stock time series prediction, we found that the improved network could prominently increase the prediction ability, while the ability of volatility prediction was better than that of other traditional algorithms.

Key words: bayesian regulation, neural network, time series prediction

Yue Hou, Bin Xie, and Heng Liu. Bayesian Regularization Neural Network Model for Stock Time Series Prediction [J]. Int J Performability Eng, 2019, 15(12): 3271-3278.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

[1] H. Darryll and B. Hirtle, “Bank Capital Requirements for Market Risk: The Internal Models Approach,” Social Science Electronic Publishing, Vol. 3, No. 4, pp. 1-12, December 1997
[2] Y. T. Wan, Z. G. Zhang, L. T. Zhao,D. M. Ai, “An Improved Historical Simulation Method to Estimate the Amount of Refined Oil Retail Value at Risk VaR,”Advanced Materials Research, Vol. 734, pp. 1711-1718, 2013
[3] J. Schaumburg, “Predicting Extreme Value at Risk: Nonparametric Quantile Regression with Refinements from Extreme Value Theory,” Computational Statistics & Data Analysis, Vol. 56, No. 12, pp. 4081-4096, 2012
[4] C. S. Chen, M. A. Golberg,Y. C. Hon, “The Method of Fundamental Solutions and Quasi‐Monte‐Carlo Method for Diffusion Equations,” International Journal for Numerical Methods in Engineering, Vol. 43, No. 8, pp. 1421-1435, 1998
[5] A. Suharsono, A. Aziza,W. Pramesti, “Comparison of Vector Autoregressive (VAR) andVector Error Correction Models (VECM) for Index of ASEAN Stock Price,” in Proceedings of AIP Conference, Vol.1913, No. 1, pp. 020032, 2017
[6] Yen, Gili and C. F. Lee, “Efficient Market Hypothesis (EMH): Past, Present and Future,” Review of Pacific Basin Financial Markets and Policies, Vol. 11, No. 12, pp. 305-329, 2008
[7] A. Varfis and C. Versino, “Univariate Economic Time Series Forecasting by Connectionist Methods,”Proc. of INNC, Vol. 56, pp. 342-345, 1990
[8] S. O.Olatunji and M. S. Al-Ahmadi, “Saudi Arabia Stock Prices Forecasting using Artificial Neural Networks,”Applications of Digital Information and Web Technologies(ICADIWT), pp. 81-86, Wisconsin, USA, August 2011
[9] K. J.Kim and I. Han, “Genetic Algorithms Approach to Feature Discretization in Artificial Neural Networks for the Prediction of Stock Price Index,” Expert Systems with Applications, Vol. 19, No. 12, pp. 125-132, August 2000
[10] W. M. Ma, Y. Y Wang,N. F. Dong, “Study on Stock Price Prediction based on BP Neural Network,”Emergency Management and Management Sciences (ICEMMS), pp. 57-60, Beijing, China, August 2010
[11] Q. Sun, W. G. Che,H. L. Wang, “Bayesian Regularization BP Neural Network Model for the Stock Price Prediction,”Advances in Intelligent Systems and Computing, pp. 521-531, November 2013
[12] A. V. D.Vaart, “Bayesian Regularization,” Hindustan Book Agency, New Delhi, 2010
[13] J. S.Chou and T. K. Nguyen, “Forward Forecast of Stock Price using Sliding-Window Metaheuristic-Optimized Machine-Learning Regression,” IEEE Transactions on Industrial Informatics, Vol. 14, No. 7, pp. 3132-3142, July 2018
[14] Z. Q. Guo, H. Q. Wang, J. Yang,D. J. Miller, “A Stock Market Forecasting Model Combining Two-Directional Two-Dimensional Principal Component Analysis and Radial Basis Function Neural Network,” PLOS ONE, Vol. 10, No. 4, pp. e0122385, April 2015
[15] L. Mao, D. Y. Qi,X. X. Li, “Improved GA Combined with GDBP Algorithm for Forecasting Releasing Behaviors of Drug Carrier,”Progress in Informatics and Computing (PIC), pp. 35-39, Shanghai, China, December 2010
[16] Q. Xue, F. Yun, C. W. Zheng,Y. H. Liu, “Improved LMBP Algorithm in the Analysis and Application of Simulation Data,”Computer Application and System Modeling (ICCASM), pp. V6-545-V6-547, Taiyuan, China, October 2010
[17] Ticknor and L. Jonathan, “A Bayesian Regularized Artificial Neural Network for Stock Market Forecasting,” Expert Systems with Applications, Vol. 40, No. 14, pp. 5501-5506, October 2013
[18] Q. Sun, W. G. Che,H. L. Wang, “Bayesian Regularization BP Neural Network Model for the Stock Price Prediction,”Foundations and Applications of Intelligent Systems, pp. 521-531, 2014