Neural network time series forecasting of financial markets
Neural Network Time Series Forecasting of Financial Markets E. Michael Azoff The first comprehensive and practical introduction to using neural networks in financial time series forecasting. This practical working guide shows you how to understand, design and profitably use neural network techniques in financial market forecasting. It encompasses:
What people are saying - Write a review
We haven't found any reviews in the usual places.
a-stp ACE neuron altemative analysis applied artiﬁcial average backpropagation benchmark BFGS British pound calculated channel normalisation classiﬁcation commodity concem conjugate gradient convergence correlation cost function deﬁned deﬁnitions deviation bands elements epoch evaluated example ﬁeld ﬁgures ﬁltering ﬁnal ﬁnancial time series ﬁrst ﬁxed futures contract futures price Gaussian Henon map hidden layer inﬂuence input data input layer input node input variables input vectors input-space leaming coefﬁcient measure median forecast method multiconnectivity multilayer perceptron network output neural network nonlinear normalised RMS error open interest output layer neuron output neuron parameters performance period plotted prediction preprocessing price time series problem proﬁt provides quasi-Newton method random walk range retum risk sample selected series forecasting Shanno sigmoid solver standard deviation steepest descent steps sufﬁcient sunspot Table tanh target techniques test set train set training and test transfer function wavelet weight initialisations weight update zero