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

Matthew Butler, Dimitar Kazakov
2011 2011 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr)  
This study investigates the characteristic of nonstationarity 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 nonstationarity 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
more » ... 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. 978-1-4244-9932-8/11/$26.00 ©2011 IEEE 978-1-4244-9934-2/11/$26.00 ©2011 IEEE
doi:10.1109/cifer.2011.5953557 dblp:conf/cifer/ButlerK11 fatcat:zt5mu76y55f5ffifcgj3nmbkq4