The effects of variable stationarity in a financial time-series on Artificial Neural Networks

M. Butler, D. Kazakov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This study investigates the characteristic of non-stationarity in a financial time-series and its effect on the learning process for Artificial Neural Networks (ANN). It is motivated by previous work where it was shown that non-stationarity is not static within a financial time series but quite variable in nature. Initially unit-root tests were performed to isolate segments that were stationary or non-stationary at a pre-determined significance level and then various tests were conducted based on forecasting accuracy. The hypothesis of this research is that when using the de-trended/original observations from the time series the trend/level stationary segments should produce lower error measures and when the series are differenced the difference stationary (non-stationary) segments should have lower error. The results to date reveal that the effects of variable stationarity on learning with ANNs are a function of forecasting time-horizon, strength of the linear-time trend, sample size and persistence of the stationary process.
Original languageEnglish
Title of host publication2011 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr)
Place of PublicationParis
PublisherIEEE
Pages1 -8
Number of pages8
ISBN (Print)978-1-4244-9933-5
DOIs
Publication statusPublished - 1 Apr 2011

Keywords

  • artificial neural network
  • detrended original observation
  • difference stationary segments
  • financial time series
  • learning process
  • time horizon forecasting
  • trend level stationary segments
  • unit root tests
  • finance
  • learning (artificial intelligence)
  • neural nets
  • time series

Cite this