Neural Network Modelling with Applications to Euro Exchange Rates

Neural networks have shown considerable success when used to model financial data series. However, a major weakness of this class of models is the lack of established procedures for misspecification testing and tests of statistical significance for the various estimated parameters. These issues are particularly important in the case of financial engineering where data generating processes are very complex and dominantly stochastic. After a brief review of neural network models, an input selection algorithm is proposed and discussed. It is based on a multistep multiple testing procedure calibrated by using subsampling. The simulation results show that the proposed testing procedure is an effective criterion for selecting a proper set of relevant inputs for the network. When applied to Euro exchange rates, the selected network models show that information contained in past percentage changes can be relevant to the prediction of future percentage changes of certain time series. The apparent predictability for some countries which we analysed does not seem to be an artifact of data snooping. Rather, it is the result of a testing procedure constructed to keep the family wise error rate under control. The results also remain stable while changing the subseries length.

[1]  Marcos Álvarez-Díaz,et al.  Forecasting exchange rates using an evolutionary neural network , 2007 .

[2]  Ramazan Gençay,et al.  Linear, non-linear and essential foreign exchange rate prediction with simple technical trading rules , 1999 .

[3]  Stefan M. Rüger,et al.  An analysis of the metric structure of the weight space of feedforward networks and its application to time series modeling and prediction , 1996, ESANN.

[4]  Terrence L. Fine,et al.  Feedforward Neural Nets , 1999 .

[5]  Halbert White,et al.  Bootstrapping Confidence Intervals for Clinical Input Variable Effects in a Network Trained to Identify the Presence of Acute Myocardial Infarction , 1995, Neural Computation.

[6]  H. Tong.  Non-linear time series. A dynamical system approach , 1990 .

[7]  Michael P. Clements,et al.  Forecasting economic and financial time-series with non-linear models , 2004 .

[8]  Jeffrey S. Racine,et al.  Statistical inference, the bootstrap, and neural-network modeling with application to foreign exchange rates , 2001, IEEE Trans. Neural Networks.

[9]  Halbert White,et al.  Tests of Conditional Predictive Ability , 2003 .

[10]  Halbert White,et al.  Learning in Artificial Neural Networks: A Statistical Perspective , 1989, Neural Computation.

[11]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[12]  David West,et al.  Neural network ensemble strategies for financial decision applications , 2005, Comput. Oper. Res..

[13]  Philip Hans Franses,et al.  Forecasting Exchange Rates Using Neural Networks for Technical Trading Rules , 1998 .

[14]  S. Holm.  A Simple Sequentially Rejective Multiple Test Procedure , 1979 .

[15]  David Enke,et al.  The adaptive selection of financial and economic variables for use with artificial neural networks , 2004, Neurocomputing.

[16]  H. White,et al.  A Reality Check for Data Snooping , 2000 .

[17]  Chris Brooks,et al.  Linear and Non-linear (Non-)Forecastability of High-frequency Exchange Rates , 1997 .

[18]  A. Neil Burgess,et al.  Neural networks in financial engineering: a study in methodology , 1997, IEEE Trans. Neural Networks.

[19]  Chung-Ming Kuan,et al.  Forecasting exchange rates using feedforward and recurrent neural networks , 1992 .

[20]  Michael Wolf,et al.  Centre De Referència En Economia Analítica Barcelona Economics Working Paper Series Working Paper Nº 17 Stewise Multiple Testing as Formalized Data Snooping Stepwise Multiple Testing as Formalized Data Snooping , 2022 .

[21]  Kurt Hornik,et al.  Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives , 1994, Neural Computation.

[22]  Kenneth S. Rogoff,et al.  Exchange rate models of the seventies. Do they fit out of sample , 1983 .

[23]  Min Qi,et al.  18 Financial applications of Artificial Neural Networks , 1996 .

[24]  Kenneth Rogoff,et al.  Do they fit out of sample , 1983 .

[25]  Min Wu,et al.  Technical Trading-Rule Profitability, Data Snooping, and Reality Check: Evidence from the Foreign Exchange Market , 2005 .

[26]  Terrence L. Fine,et al.  Feedforward Neural Network Methodology , 1999, Information Science and Statistics.

[27]  Joseph P. Romano,et al.  Exact and Approximate Stepdown Methods for Multiple Hypothesis Testing , 2003 .

[28]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[29]  Ruey S. Tsay,et al.  Analysis of Financial Time Series , 2005 .

[30]  Chris Brooks.  Testing for non-linearity in daily sterling exchange rates , 1996 .

[31]  Monica Lam,et al.  Neural network techniques for financial performance prediction: integrating fundamental and technical analysis , 2004, Decis. Support Syst..

[32]  Francesco Giordano,et al.  The hidden layer size in feed-forward neural networks: a statistical point of view. , 1999 .

[33]  James M. Nason,et al.  Nonparametric exchange rate prediction , 1990 .

[34]  Nikola Gradojevic,et al.  Non-linear, hybrid exchange rate modeling and trading profitability in the foreign exchange market , 2007 .

[35]  Michele La Rocca,et al.  Variable selection in neural network regression models with dependent data: a subsampling approach , 2005, Comput. Stat. Data Anal..

[36]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[37]  Timo Teräsvirta,et al.  POWER OF THE NEURAL NETWORK LINEARITY TEST , 1993 .

[38]  Amit Mitra,et al.  Forecasting daily foreign exchange rates using genetically optimized neural networks , 2002 .

[39]  Apostolos-Paul N. Refenes,et al.  Neural model identification, variable selection and model adequacy , 1999 .

[40]  Francesco Giordano,et al.  Bootstrap Variables Selection in Neural Network Regression Models , 2004 .

[41]  Halbert White,et al.  Artificial neural networks: an econometric perspective ∗ , 1994 .

[42]  Michele La Rocca,et al.  Neural Network Modeling by Subsampling , 2005, IWANN.

[43]  Piotr Kokoszka,et al.  Subsampling the Mean of Heavy-Tailed Dependent Observations , 2004 .