Abstract
An Artificial Neural Network (ANN) algorithms have been widely used in machine learning for pattern recognition, classifications and time series forecasting today; especially in financial applications with nonlinear and nonparametric modeling’s. The objective of this study is an attempt to develop a new hybrid forecasting approach based on back propagation neural network (BPN) and Geometric Brownian Motion (GBM) to handle random walk data patterns under the high volatility. The proposed methodology is successfully implemented in the Colombo Stock Exchange (CSE) Sri Lanka, the daily demands of the All Share Price Index (ASPI) price index from April 2009 to March 2017. The performances of the model are evaluated based on the best two forecast horizons of 75% and 85% training samples. According to the empirical results, 85% training samples have given highly accurate in their testing process. Furthermore, the results confirmed that the proposed hybrid methodology always gives the best performances under the high volatility forecasting compared to the separate traditional time series models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Mishra, T., Kapoor, V.: Financial trends prediction using the back propagation neural network and YQL. Int. J. Comput. Appl. 144(10), 20–26 (2016)
Willmot, P.: Introduces Quabtitative Finance 2. Wiley, New York (2007)
Dmouj, A.: Stock Price Modelling: Theory and Practice. Vrije Universiteit, Amsterdam (2006)
Omar, A., Jaffar, M.M.: Forecasting share price of small size companies in Bursa Malaysia using geometric brownian motion. J. Int. Appl. Math. Inf. Sci. 8, 107–112 (2014)
Brewer, K.D., Feng, Y., Kwan, C.C.Y.: Geometric Brownian motion, option pricing, and simulation: some spread sheet-based exercises in financial modelling. Spread Sheets Educ. 7(2), 1–28 (2012)
Kim, K.-j.: Artificial neural networks with evolutionary instance selection for financial forecasting. Expert Syst. Appl. 12(1), 202–220 (2006)
Kryzanowski, L., Galler, M., Wright, D.W.: Using artificial neural networks to pick stocks. Financ. Anal. J. 3(2), 40–333 (1993)
Huang, M., Chen, M., Lee, S.: Integrating data mining with case-based reasoning for chronic diseases prognosis and diagnosis. Expert Syst. Appl. 32(3), 856–867 (2007)
Morgan, D.P., Scofield, C.L.: Neural Networks and Speech Processing. Kluwer Academic Publishers, Dordrecht (1991)
Postali, F.A.S., Picchetti, P.: Geometric brownian motion and structural breaks in oil prices: a quantitative analysis. Energy Econ. 28, 506–522 (2006)
Qi, M.: Handbook of Statistics. Elsevier B.V., Amsterdam (1996)
Rathnayaka, R.M.K.T., Seneviratna, D.M.K.N, Jianguo, W.: A hybrid statistical approach for stock market forecasting based on artificial neural network and ARIMA time series models. In: International Conference on Behavioral, Economic and Socio-cultural Computing (BESC), Nanjing, China, pp. 33–38 (2015)
Rathnayaka, R.M.K.T., Jianguo, W., Seneviratna, D.M.K.N.: Geometric brownian motion with Ito’s lemma approach to evaluate market fluctuations: a case study on Colombo stock exchange. In: International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC2014), Shanghai, China, pp. 25–29 (2014)
Rathnayaka, R.M.K.T., Seneviratna, D.M.K.N., Jianguo, W.: An unbiased GM(1,1)-based new hybrid approach for time series forecasting. Grey Syst. Theory Appl. 6(3), 322–340 (2016)
Reddy, K., Clinton, V.: Simulating stock prices using geometric Brownian motion: evidence from Australian companies. Aust. Account. Bus. Finance J. 10(3), 23–47 (2016)
Roman, J., Jameel, A.: Back propagation and recurrent neural networks in financial analysis of multiple stock market returns. In: 29th Annual Hawaii International Conference on System Sciences (1996)
Seneviratna, D.M.K.N., Rathnayaka, R.M.K.T.: Rainfall data forecasting by SARIMA and BPNN model. IOSR J. Math. 6(3), 57–63 (2017)
Seneviratna, D., Chen, D.: Using feed forward BPNN for forecasting all share price index. J. Data Anal. Inf. Process. 2, 87–94 (2014)
Seneviratna, D., Shuhua, M.: Forecasting the twelve month treasury bill rates in Sri Lanka. IOSR J. Econ. Finance 1(1), 42–47 (2013)
Zhang, G., Patuwo, B.E., Hu, M.Y.: Forecasting with artificial neural networks. Int. J. Forecast. 14, 35–62 (1998)
Yuan, Y.: Study on Financial Market Investment Portfolio Selection Based on Genuine Correlation Matrix. In: Qu, X., Yang, Y. (eds.) IBI 2011. CCIS, vol. 268, pp. 329–334. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-29087-9_51
Wang, J., Deng, S.: Fluctuations of interface statistical physics models applied to a stock market model. Nonlinear Anal. Real World Appl. 9, 718–723 (2008)
Nasseri, M., Asgahari, K., Abedini, M.: Optimized scenariofor rainfall forecasting using genetic algorithm coupled with artificial neural network. Expert Syst. Appl. 35(3), 1415–1421 (2008)
Acknowledgments
This work was supported by the Research Grant (SUSL/RE/2017/04), Sabaragamuwa University of Sri Lanka, Belihuoya, Sri Lanka.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Codes and Mat Lab Program for Proposed Hybrid Methodology
Codes and Mat Lab Program for Proposed Hybrid Methodology
The new hybrid methodology is more appropriate to handle incomplete, noise and non-linear random time sequences with limited data samples. The proposed algorithm is as follows.
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kapila Tharanga Rathnayaka, R.M., Seneviratna, D.M.K.N. (2019). A Novel Hybrid Back Propagation Neural Network Approach for Time Series Forecasting Under the Volatility. In: Hemanth, J., Silva, T., Karunananda, A. (eds) Artificial Intelligence. SLAAI-ICAI 2018. Communications in Computer and Information Science, vol 890. Springer, Singapore. https://doi.org/10.1007/978-981-13-9129-3_6
Download citation
DOI: https://doi.org/10.1007/978-981-13-9129-3_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9128-6
Online ISBN: 978-981-13-9129-3
eBook Packages: Computer ScienceComputer Science (R0)