Abstract
Motivated by recurrent neural networks, this paper proposes a recurrent support vector regression (SVR) procedure to forecast nonlinear ARMA model based simulated data and real data of financial returns. The forecasting ability of the recurrent SVR based ARMA model is compared with five competing models (random walk, threshold ARMA model, MLE based ARMA model, recurrent artificial neural network based ARMA model and feed-forward SVR based ARMA model) by using two forecasting accuracy evaluation metrics (NSME and sign) and robust Diebold–Mariano test. The results reveal that for one-step-ahead forecasting, the recurrent SVR model is consistently better than the benchmark models in forecasting both the magnitude and turning points, and statistically improves the forecasting performance as opposed to the usual feed-forward SVR.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
For MLE, maximizing the joint probability density function amounts to minimizing the sum of residual squares, i.e., minimizing the empirical risk, which is equivalent to the OLS approach.
References
Adya M, Collopy F (1998) How effective are neural networks at forecasting and prediction? A review and evaluation. J Forecast 17:481–495
Andrews DWK (1991) Heteroskedasticity and autocorrelation consistent covariance matrix estimation. Econometrica 59:817–858
Ashok KN, Mitra A (2002) Forecasting daily foreign exchange rates using genetically optimized neural networks. J Forecast 21:501–511
Box GEP, Jenkins GM, Reinsel GC (1994) Time series analysis: forecasting and control. Prentice Hall, Englewood Cliffs
Cao L, Tay F (2001) Financial forecasting using support vector machines. Neural Comput Appl 10:184–192
Database of Exchange Rates: http://pacific.commerce.ubc.ca/xr Policy Analysis Computing and Information Facility in Commerce (PACIFIC) at University of British Columbia
Database of NYSE stock index: http://www.nyse.com/marketinfo/datalib/the Market Information section of the NYSE\(^{\rm TM}\) web page
Deng NY, Tian YJ (2004) New methods in data mining: support vector machine. Science Press, Beijing
Diebold FX, Mariano RS (1995) Comparing predictive accuracy. J Bus Econ Stat 13:253–265
Espinoza M, Suykens JAK, De Moor B (2006) LS-SVM regression with autocorrelated errors. In: Proceedings of the 14th IFAC symposium on system identification (SYSID), Newcastle, Australia, pp 582–587
Evgeniou T, Poggio T, Pontil M, Verri A (2002) Regularization and statistical learning theory for data analysis. Comput Stat Data Anal 38(4):421–432
Gaudart J, Giusiano B, Huiart L (2004) Comparison of the performance of multi-layer perceptron and linear regression for epidemiological data. Comput Stat Data Anal 44(4):547–570
Hamilton JD (1997) Time series analysis. princeton University Press, Princeton
Härdle WK, Moro RA, Schäfer D (2005) Predicting bankruptcy with support vector machines. In: Statistical tools for finance and insurance. Springer, Berlin
Härdle WK, Moro RA, Schäfer D (2006) Graphical data representation in bankruptcy analysis. In: Handbook for data visualization. Springer, Berlin
Haykin S (1999) Neural networks: a comprehensive foundations. Prentice Hall, New Jersey
Hong Wei-Chiang (2011) Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artificial bee colony algorithm. Energy 36(9):5568–5578
Jordan MI (1987) Attractor dynamics and parallelism in a connectionist sequential machine. In: Proceeding of 8th annual conference of the cognitive science society, Hillsdale, pp 531–546
Kamruzzaman J, Sarker R (2004) ANN-based forecasting of foreign currency exchange rate. Neural Inf Process Lett Rev 3(2):49–58
Kanas A (2003) Non-linear forecasts of stock returns. J Forecast 22(4):299–315
Kuan C-M (1995) A recurrent Newton algorithm and its convergence properties. IEEE Trans Neural Netw 6:779–783
Kuan C-M, Hornik K, White H (1994) A convergence result for learning in recurrent neural networks. Neural Comput 6:420–440
Kuan C-M, Liu T (1995) Forecasting exchange rates using feedforward and recurrent neural networks. J Appl Economet 10:347–364
Lee TS, Chiu CC, Chou YC, Lu CJ (2006) Mining the customer credit using classification and regression tree and multivariate adaptive regression splines. Comput Stat Data Anal 50(4):1113–1130
Lisi F, Schiavo RA (1999) A comparison between neural networks and chaotic models for exchange rate prediction. Comput Stat Data Anal 30(1):87–102
Lorenz EN (1963) Deterministic non-periodic flow. J Atmos Sci 20:130–141
Moosa I (2000) Exchange rate forecasting: techniques and applications. Macmillan Press LTD, Lonton
Newey WK, West KD (1987) A simple positive, semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix. Econometrica 55(3):703–708
Niemira MP, Klein PA (1994) Forecasting financial and economic cycles. Wiley, New York
Pesaran M, Timmerman A (1990) The statistical and economic significance of the predictability of excess returns on common stocks. Department of Applied Economics, University of Cambridge, working paper no. 9022
Priestley MB (1988) Nonlinear and non-stationary time series analysis. Academic Press, London
Scholkopf B, Smola A (2001) Learning with kernels. MIT Press, Cambridge
Suykens JAK, Vandewalle J (2000) Recurrent least squares support vector machines. IEEE Trans Circuits Syst I 47(7):1109–1114
Suykens JAK, Van Gestel T, De Brabanter J, De Moor B, Vandewalle J (2002) Least squares support vector machines. World Scientific, Singapore
Tian J, Juhola M, Grönfors T (1997) AR parameter estimation by a feedback neural network. Comput Stat Data Anal 25(1):17–24
Trafalis T, Ince H (2000) Support vector machine for regression and applications to financial forecasting. In: International joint conference on neural networks, pp 348–353
Van Gestel T, Suykens J, Baestaens D, Lambrechts A, Lanckriet G, Vandaele B, De Moor B, Vandewalle J (2001) Financial time series prediction using least squares support vector machines within the evidence framework. IEEE Trans Neural Netw 12(4):809–821
Vapnik VN (1995) The nature of statistical learning theory. Springer, New York
Vapnik VN (1997) Statistical learning theory. Wiley, New York
Wu B (1995) Model-free forecasting for nonlinear time series (with application to exchange rates). Comput Stat Data Anal 19(4):433–459
Yang H, Chan L, King I (2002) Support vector machine regression for volatile stock market prediction. In: Proceedings of the third international conference on intelligent data engineering and automated learning, pp 391–396
Acknowledgments
The authors thank the editor, Stefan Trueck, and three anonymous referees for their constructive comments. Kiho Jeong’s research was supported by Kyungpook National University Research Fund, 2011. Shiyi Chen appreciates the supports from Shanghai Leading Talent Project, Fudan Zhuo-Shi Talent Plan and Fudan 985 Project. The work was also sponsored by Deutsche Forschungsgemeinschaft through SFB 649 “Economic Risk”.
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Chen, S., Jeong, K. & Härdle, W.K. Recurrent support vector regression for a non-linear ARMA model with applications to forecasting financial returns. Comput Stat 30, 821–843 (2015). https://doi.org/10.1007/s00180-014-0543-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-014-0543-9