🚀 go-pugleaf

Neural Networks in the Capital Markets
The following NNCM-96 pre-prints are now available on request. 
Please send your postal address to: boguntula@lbs.lon.ac.uk
===================================================
NEURAL MODEL IDENTIFICATION, VARIABLE SELECTION AND 
                                MODEL ADEQUACY

          A-P. N. REFENES, A. D. ZAPRANIS AND J. UTANS
                           Department of Decision Science
                                 London Business School
                      Regents Park, London, NW1 4SA, UK

In recent years an impressive array of publications have appeared
claiming considerable successes of neural networks in modeling
financial data but skeptical practitioners and statisticians are still
raising the question of whether neural networks really are "a major
breakthrough or just a passing fad". A major reason for this is the
lack of procedures for performing tests for mispecified models, and
tests of statistical significance for the various parameters that have
been estimated, which makes it difficult to assess the model's
significance and the possibility that any short term successes that
are reported might be due to "data mining". In this paper we describe
a methodology for neural model identification which facilitates
hypothesis testing at two levels: model adequacy and variable
significance. The methodology includes a model selection procedure
to produce consistent  estimators, a variable selection procedure 
based on variable significance testing and a model adequacy 
procedure based on residuals analysis.
================================================
SPECIFICATION TESTS FOR NEURAL NETWORKS:
 A CASE STUDY IN TACTICALASSET ALLOCATION

             A. D. ZAPRANIS, J. UTANS, A-P. N. REFENES
                         Department of Decision Science
                                London Business School
                        Regents Park, London, NW1 4SA, UK

A case study in tactical asset allocation is used to introduce a
methodology for neural model identification including model
specification and variable selection. Neural models are contrasted to
multiple linear regression on the basis of model identification. The
results indicate the presence of non-linear relationships between the
economic variables and asset class returns.
=============================================