Evaluating the performance of a EuroDivisia index using artificial intelligence techniques

This paper compares two methods to predict inflation rates in Europe. One method uses a standard back propagation neural network and the other uses an evolutionary approach, where the network weights and the network architecture are evolved. Results indicate that back propagation produces superior results. However, the evolving network still produces reasonable results with the advantage that the experimental set-up is minimal. Also of interest is the fact that the Divisia measure of money is superior as a predictive tool over simple sum.

[1]  Livio Stracca.  Does Liquidity Matter? Properties of a Divisia Monetary Aggregate in the Euro Area , 2004 .

[2]  The outcome of the ECB’s evaluation of its monetary policy strategy , 2007 .

[3]  D. Schunk,et al.  The Relative Forecasting Performance of the Divisia and Simple Sum Monetary Aggregates , 2001 .

[4]  Bin-Tzong Chie,et al.  Financial Innovation and Divisia Money in Taiwan: Comparative Evidence from Neural Network and Vector Error-Correction Forecasting Models , 2004 .

[5]  Jonathan A. Tepper,et al.  TOOLS FOR NON-LINEAR TIME SERIES FORECASTING IN ECONOMICS – AN EMPIRICAL COMPARISON OF REGIME SWITCHING VECTOR AUTOREGRESSIVE MODELS AND RECURRENT NEURAL NETWORKS , 2004 .

[6]  A. Mullineux,et al.  One Divisia money for Europe , 1997 .

[7]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[8]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[9]  Livio Stracca.  Does Liquidity Matter? Properties of the Synthetic Divisia Monetary Aggregate in the Euro Area , 2001, SSRN Electronic Journal.

[10]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[11]  David D. VanHoose,et al.  Recent developments in understanding the demand for money , 2004 .

[12]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[13]  William A. Barnett,et al.  Economic monetary aggregates an application of index number and aggregation theory , 1980 .

[14]  Michael T. Belongia.  Measurement Matters: Recent Results from Monetary Economics Reexamined , 1996, Journal of Political Economy.

[15]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation (3rd Edition) , 2007 .

[16]  William A. Barnett,et al.  Consumer Theory and the Demand for Money , 2000 .

[17]  H. Lütkepohl,et al.  A money demand system for German M3 , 1998 .

[18]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[19]  D. M. Titterington,et al.  Neural Networks: A Review from a Statistical Perspective , 1994 .

[20]  James L. Swofford,et al.  THE COMPOSITION AND CONSTRUCTION OF MONETARY AGGREGATES , 1991 .

[21]  Saeed Moshiri,et al.  Static, Dynamic, and Hybrid Neural Networks in Forecasting Inflation , 1998 .

[22]  William A. Barnett,et al.  The user cost of money , 1978 .

[23]  G. Kendall,et al.  Co-evolution vs. Neural Networks; An Evaluation of UK Risky Money , 2004 .