Neural Networks to Predict Financial Time Series in a Minority Game
Transcript
Neural Networks to Predict Financial Time Series in a Minority Game
Dipartimento di Scienze Economiche, Matematiche e Statistiche Università degli Studi di Foggia ____________________________________________________________________ Neural Networks to Predict Financial Time Series in a Minority Game Context Luca Grilli e Angelo Sfrecola Quaderno n. 14/2005 “Esemplare fuori commercio per il deposito legale agli effetti della legge 15 aprile 2004 n. 106” Quaderno riprodotto al Dipartimento di Scienze Economiche, Matematiche e Statistiche nel mese di giugno 2005 e depositato ai sensi di legge Authors only are responsible for the content of this preprint. _______________________________________________________________________________ Dipartimento di Scienze Economiche, Matematiche e Statistiche, Largo Papa Giovanni Paolo II, 1, 71100 Foggia (Italy), Phone +39 0881-75.37.30, Fax +39 0881-77.56.16 Neural Networks to Predict Financial Time Series in a Minority Game Context∗ Luca Grilli† Angelo Sfrecola‡ Abstract In this paper we consider financial time series from U.S. Fixed Income Market, S&P500, Exchange Market and Oil Market. It is well known that financial time series reveal some anomalies as regards the Efficient Market Hypotesis and some scaling behavior is evident such as fat tails and clustered volatility. This suggests to consider financial time serie as “pseudo”-random time series. For this kind of time series the power of prediction of neural networks has been shown to be appreciable. We first consider the financial time serie from the Minority Game point of view and than we apply a neural network with learning algorithm in order to analyze its prediction power. We show that Fixed Income Market presents many differences from other markets in terms of predictability as a measure of market efficiency. Keywords: Minority Game, Learning Algorithms, Neural Networks, Financial Time Series, Efficient Market Hypotesis. Subject Classification: 91A80, 91A26, 92B20, 62M45. JEL Classification: C45, C70, C22, G14. References [1] Arthur W. B., Inductive reasoning and bounded rationality, Am. Econ. Assoc. Papers and Proc, Krugman ed., 1994, pp.88-406 [2] l. Bachelier, Théorie de la spécilation, Paris, 1900 (Reprinted MIT Press, Cambridge, 1964) [3] M. Bernaschi, L. Grilli, D. Vergni, Statistical analysis of fixed income market, Physica A: Statistical Mechanics and its application, 308 (1-4), 2002, pp. 381-390 ∗ Research supported by Local Project 2004 (EX 40%) Università di Foggia author) Dipartimento di Scienze Economiche, Matematiche e Statistiche, Università degli Studi di Foggia, Via IV Novembre 1, I-71100 Foggia, Italy e-mail: [email protected] ‡ Research financially supported by Dipartimento di Scienze Economiche, Matematiche e Statistiche, Università degli Studi di Foggia † (Corresponding [4] A. Cavagna, Irrelevance of memory in the minority game, Phys. Rev. E, 59:R3783, 1999 [5] D. Challet, A. Chessa, M. Marsili and Y.-C. Zhang, From Minority Games to real markets, cond-mat/0011042, 2000 [6] D. Challet, Inter-pattern speculation: beyond minority, majority and $-games, cond-mat/0502140, 2005 [7] A.C.C. Coolen, Generating funcional analysis of Minority Games with real market histories, cond-mat/0410335, 2004 [8] M. Hart, P. Jefferies, N. F. Johnson and P. M. Hui, Crowd-anticrowd model of the Minority Game, cond-mat/0003486, 2000 [9] L. Grilli, Long-term fixed income market structure, Physica A: Statistical Mechanics and its application, 332, 2004, pp. 441-447 [10] L. Grilli and A. Sfrecola A Neural Networks approach to Minority Game, Quaderno DSEMS n. 13/2005, University of Foggia [11] W. Kinzel and I. Kanter, Dynamics of interacting neural networks, J. Phys. A, 33:L141-L147, 2000 [12] R. Metzler, W. Kinzel and I. Kanter, Interacting neural networks, Phys. Rev. E, 62(2):2555, 2000 [13] H. Simon, Models of Bounded Rationality, MIT Press, Cambridge, 1997 2