Advertisement

Forecasting

  • Michael Schulz
Chapter
Part of the Springer Tracts in Modern Physics book series (STMP, volume 184)

Abstract

Forecasting means the ability to extrapolate the future dynamics of a given system on the basis of its current state and its history. If we have a suitable model, the forecast may be extended to arbitrarily long times. Typical candi- dates for a nearly unlimited prognosis are the models of classical mechanics. Knowledge of the initial conditions allows the determination of any further development due to the deterministic equations of motion. Obviously, a pre- diction becomes better if we have a higher accuracy of the initial conditions or of the past and if we have precise equations of motion.

Keywords

Neural Network Stock Price Spin Glass Learning Procedure Training Pattern 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag New York, Inc. 2003

Authors and Affiliations

  • Michael Schulz
    • 1
  1. 1.Abteilung Theoretische PhysikUniversität UlmUlmGermany

Personalised recommendations