Filippo Castiglione
Published 2000-06-30Version 1
Financial forecasting is a difficult task due to the intrinsic complexity of the financial system. In the present paper we relate our experience using neural nets as financial time series forecast method. In particular we show that a neural net able to forecast the sign of the price increments with a success rate slightly above 50 percent can be found.
Comments: 12 pages, 5 figures (to be published in Advances in Complex Systems, as the Proceeding of the WE-Heraeus Workshop on "Economic Dynamics from the Physics Point of View", Bad Honnef, Germany, March 27-30, 2000
Artificial neural network as a universal model of nonlinear dynamical systems
On the problem of neural network decomposition into some subnets
Mutual Information, Neural Networks and the Renormalization Group
