Abstract
Real-world time series data are complex and a single forecasting model may not able to capture data patterns well. This paper presents a novel method for time series forecasting and its application in predicting foreign exchange rates. The proposed method uses a hybrid of finite impulse response (FIR) neural networks and autoregressive integrated moving average (ARIMA) model using time-variable parameters to forecast time series variables, and uses principal component analysis (PCA) to combine results of variables to get better final result. Experimental results show that the proposal obtains higher prediction performance than other methods for mid-term and long-term forecasting.
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
References
Damodar, N.: Basic Econometrics. The Mc-Graw Hill, London (2004)
Michael, K.: Evans Practical Business Forecasting. Blackwell Publishers Ltd., a Blackwell Publishing company, Bodmin, Cornwall (2002)
Zhang, G., Patuwo, B.E., Hu, M.Y.: Forecasting with artificial neural networks: the state of the art. Int. J. Forecast. 14, 35–62 (1998)
Wan, E.A.: Temporal backpropagation for FIR neural networks. In: IJCNN International Joint Conference on Neural Networks, IEEE (1990)
Wan, E.A.: Finite impulse response neural networks for autoregressive time series prediction. In: Proceedings of the NATO Advanced Workshop on Time Series Prediction and Analysis, Sante Fe, NM (2003)
Kim, H.J.: Time series prediction using an interval arithmetic FIR network. Neural Inf. Process. Lett. Rev. 8(3), 39–47 (2005)
Mehdi, K., Bijari, M.: A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Appl. Soft Comput. 11(2), 2664–2675 (2011)
Faruk, D.Ö.: A hybrid neural network and ARIMA model for water quality time Series prediction. Eng. Appl. Artif. Intell. 23(4), 586–594 (2010)
Khandelwal, I., Adhikari, R., Verma, G.: Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition. Procedia Comput. Sci. 48, 173–179 (2015)
Aburto, L., Weber, R.: Demand Forecast in a Supermarket using a Hybrid Intelligent System. Department of Industrial Engineering, University of Chile, pp 143–151 (2012)
Qin, M., Li, Z., Du, Z.: Red tide time series forecasting by combining ARIMA and deep belief network. Knowl.-Based Syst. 125, 39–52 (2017)
Barak, S., Sadegh, S.S.: Forecasting energy consumption using ensemble ARIMA–ANFIS hybrid algorithm. Int. J. Electr. Power Energy Syst. 82, 92–104 (2016)
Thành, N.C., Sơn, H.G.: A combination of FIR neural networks and ARIMA model with time-variable parameters to improve time series forecasting performance. J. Mil. Sci. Technol. 170–179 (2017)
Khashei, M., Bijari, M.: Which methodology is better for combining linear and nonlinear models for time series forecasting? J. Ind. Syst. Eng. 4(4), 265–285 (2011)
Zhang, G.P.: Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50, 159–175 (2003)
Barak, S., Sadegh, S.S.: Forecasting energy consumption using ensemble ARIMA–ANFIS hybrid algorithm. Int. J. Electr. Power Energy Syst. 82, 92–104 (2016)
Sơn, H.G.: A forecasting method for mutual dependant multivariate time series using FIR neural networks. J. Mil. Sci. Technol. 49 (2017)
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
Sơn, H.G. (2020). A Combination of Finite Impulse Response Neural Networks, ARIMA and Principal Component Analysis for Forex Market Prediction. In: Sattler, KU., Nguyen, D., Vu, N., Tien Long, B., Puta, H. (eds) Advances in Engineering Research and Application. ICERA 2019. Lecture Notes in Networks and Systems, vol 104. Springer, Cham. https://doi.org/10.1007/978-3-030-37497-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-37497-6_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37496-9
Online ISBN: 978-3-030-37497-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)