Nonlinear time-series analysis of the Greek exchange-rate market

Using concepts from the theory of chaos and nonlinear dynamical systems, a time-series analysis is performed on four major currencies against the Cree k Drachma. The R/S analysis provided evidence for fractality due to noisy c haos in only two of the data series, while the BDS test showed that all fou r systems exhibit nonlinearity. Correlation dimension and related tests, as well as Lyapunov exponents, gave consistent results, which did not rule ou t the possibility of deterministic chaos for the two possibly fractal serie s, rejecting though the occurrence of a simple low-dimensional attractor, w hile the other two series seemed to have followed a behavior close to that of a random signal. SVD analysis, used to filter away noise, strongly suppo rted the above findings and provided reliable evidence for the existence of an underlying system with a limited number of degrees-of-freedom only for those series found to exhibit fractality, while it revealed a noise dominat ion over the remaining two. These results were further confirmed through a forecasting attempt using artificial neural networks.