Using Evolutionary Neural Networks to Test the Influence of the Choice of Numeraire on Financial Time Series Modeling

Azzini A., Dragoni M., Tettamanzi A. G. B.

Conference on EvoApplications 2011: EvoCOMPLEX, EvoGAMES, EvoIASP, EvoINTELLIGENCE, EvoNUM, AND EvoSTOC, Torino, Italy, 27 - 29 April 2011, vol.6625, pp.81-90 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 6625
  • City: Torino
  • Country: Italy
  • Page Numbers: pp.81-90
  • Istanbul Technical University Affiliated: No

Abstract

This work presents an evolutionary solution that aims to test the influence of the choice of numeraire on financial time series modeling. In particular, the method used in such a problem is to apply a very powerful natural computing analysis tool, namely evolutionary neural networks, based on the joint evolution of the topology and the connection weights together with a novel similarity-based crossover, to a couple of very liquid financial time series expressed in their trading currency and several alternative numeraires like gold, silver, and a currency like the euro, which is intended to be stable 'by design', and compare the results.