Matkovskyy, Roman (2012): Forecasting the Index of Financial Safety (IFS) of South Africa using neural networks.

PDF
MPRA_paper_42153.pdf Download (1MB)  Preview 
Abstract
This paper investigates neural network tools, especially the nonlinear autoregressive model with exogenous input (NARX), to forecast the future conditions of the Index of Financial Safety (IFS) of South Africa. Based on the time series that was used to construct the IFS for South Africa (Matkovskyy, 2012), the NARX model was built to forecast the future values of this index and the results are benchmarked against that of Bayesian VectorAutoregressive Models. The results show that the NARX model applied to IFS of South Africa and trained by the LevenbergMarquardt algorithm may ensure a forecast of adequate quality with less computation expanses, compared to BVAR models with different priors.
Item Type:  MPRA Paper 

Original Title:  Forecasting the Index of Financial Safety (IFS) of South Africa using neural networks 
English Title:  Forecasting the Index of Financial Safety (IFS) of South Africa using neural networks 
Language:  English 
Keywords:  Index of Financial Safety (IFS); neural networks; nonlinear dynamic network (NDN); nonlinear autoregressive model with exogenous input (NARX); forecast 
Subjects:  C  Mathematical and Quantitative Methods > C4  Econometric and Statistical Methods: Special Topics > C45  Neural Networks and Related Topics E  Macroeconomics and Monetary Economics > E4  Money and Interest Rates > E44  Financial Markets and the Macroeconomy G  Financial Economics > G0  General > G01  Financial Crises 
Item ID:  42153 
Depositing User:  Roman Matkovskyy 
Date Deposited:  23. Oct 2012 19:22 
Last Modified:  13. Feb 2013 12:46 
References:  ABIAD, A., G. (2003). Early Warning Systems: A Survey and a RegimeSwitching Approach. IMF Working Paper No. 03/32. AKAIKE, H. (1970). Statistical predictor identification, Annals of the Institute for Statistical Mathematics 22, 203217. AMARI, S. (1995). Learning and statistical inference, in M. A. Arbib, ed., ‘The Handbook of Brain Theory and Neural Networks’, MIT Press, Cambridge, Massachusetts, 522526. BACHA, H. & MEYER, W. (1992). Neural Network architecture for Load Forecasting, Proceedings of International Joint Conference on Neural Networks, IEEE Publisher, 442447. BARTLETT, P. (1993). VapnikChervonenkis dimension bounds for twoand threelayer networks, Neural Computation 5(3), 371373. COHN, D. and TESAURO, G. (1992). How tight are the VapnikChervonenkis bounds?, Neural Computation 4(2), 249269. ELISSEEFF, A., and PAUGAMMOISY, H. (1997). Size of multilayer networks for exact learning: analytic approach". Advances in Neural Information Processing Systems 9, Cambridge, MA: The MIT Press, 162168. FAHLMAN, S. E. and LEBIERE, C. (1991). The CascadeCorrelation Learning Architecture, Available at http://www.cs.iastate.edu/~honavar/fahlman.pdf [Accessed 07 February 2012]. FORESEE, F.D. and HAGAN, M.T. (1997). GaussNewton approximation to Bayesian regularization, Proceedings of the 1997 International Joint Conference on Neural Networks, pp. 19305. FRASER, A. M., SWINNEY, H. L. (1986). Independent coordinates for strange attractors from mutual information, Physical Review, A 33, 113440. GIRGUIS, S., AHMED, K. M., El MAKKY, N. M., & HAFEZ, A. M. (2006). Mining the Future: Predicting Itemsets' Support of Association Rules Mining. Retrieved January 28, 2007, Available at: http://www.cs.pitt.edu/~shenoda/files/miningthefuturefdm06.pdf [Accessed 07 February 2012]. HAYKIN, S. (1999). Neural Networks, A Comprehensive Foundation, 2nd Edition, Prentice Hall. HSU, HWEI P. (1995). Signals and Systems. McGrawHill. p.18. KAISER, H. F. (1958). The varimax criterion for analytic rotation in factor analysis. Psychometrika, 23(3): 187200. KELLEY, C.T. (1999). Iterative Methods for Optimization. SIAM Press, Philadelphia. KOOPMAN, S. J., LUCAS, A. and SCHWAAB, B. (2010). Macro, frailty, and contagion effects in defaults: Lessons from the 2008 credit crisis. Tinbergen Institute Discussion Paper 2010004/2, 1–40. LAWRENCE, S., GILES, C.L., and TSOI, A.C. (1996). What size neural network gives optimal generalization? Convergence properties of backpropagation. Technical Report UMIACSTR9622 and CSTR3617, Institute for Advanced Computer Studies, University of Maryland, College Park. LEONTARITIS, I. L., BILLINGS, S.A. (1985). Inputoutput parametric model for nonlinear systems – Part II: stochastic nonlinear systems, Int.J.Control, 41(2): 329344. LEVENBERG, K. (1944). A Method for the Solution of Certain Nonlinear Problems in Least Squares. Quarterly of Applied Mathematics, 2(2): 164168. LIN, TSUNGNAN, HORNE, BILL G., TINO, PETER & LEE, G., C. (2000). Learning long term dependencies in NARX recurrent neural networks, Recurrent neural networks design and applications, CRC Press, 133146. MAASS, W. (1995). VapnikChervonenkis dimension of neural networks, in M. A. Arbib, ed., The Handbook of Brain Theory and Neural Networks, MIT Press, Cambridge, Massachusetts, 522526. MACKAY, D.J.C. (1992). Bayesian Interpolation, Neural Computation, 4(3): 415447. MARQUARDT, D.W. (1963). An Algorithm for the LeastSquares Estimation of Nonlinear Parameters. SIAM Journal of Applied Mathematics, 11(2): 431441. MATKOVSKYY, R. (2012). The Index of the Financial Safety (IFS) of South Africa and Bayesian estimates for IFS VectorAutoregressive Model. Forthcoming. MENEZES, Jose M.P. & BARRETO, G. A. (2006). A new look at nonlinear time series prediction with NARX recurrent neural network, Proceedings of Ninth Brazilian Symposium on Neural Networks, pp.160165, 2327 Oct. 2006. MOODY, J. (1992). The effective number of parameters: An analysis of generalization and regularization in nonlinear learning systems, in J. Moody, S. J. Hanson and R. P. Lippmann, eds, Advances in Neural Information Processing Systems, Vol. 4, Morgan Kaufmann, San Mateo, CA, 847854. NIELSEN, H.B. (1999). Damping Parameter in Marquardt’s Method. Technical Report IMMREP199905, Technical University of Denmark, 1999. Available at http://www.imm.dtu.dk/˜hbn. NOCEDAL, J. and WRIGHT, S.J. (1999). Numerical Optimization. Springer, New York. RIPLEY, B. (1995). Statistical ideas for selecting network architectures, Invited Presentation, Neural Information Processing Systems 8. SIEGELMANN, HAVA T., HORNE G. & LEE G.C. (1997). Computational capabilities of recurrent NARX neural network” IEEE Transactions on Systems, Man and Cybernetics, Part B, 27(2): 208215. OPPENHEIM, A. V., WILLSKY, A. S., & NAWAB, S. H. (1997). Signals & Systems. Prentice Hall. 
URI:  http://mpra.ub.unimuenchen.de/id/eprint/42153 