Combining Neural Network Forecasts on Wavelet-Transformed Time Series

Abstract

We discuss a simple strategy aimed at improving neural network prediction accuracy, based on the combination of predictions at varying resolution levels of the domain under investigation (here: time series). First, a wavelet transform is used to decompose the time series into varying scales of temporal resolution. The latter provide a sensible decomposition of the data so that the underlying temporal structures of the original time series become more tractable. Then, a Dynamical Recurrent Neural Network (DRNN) is trained on each resolution scale with the temporal-recurrent backpropagation (TRBP) algorithm. By virtue of its internal dynamic, this general class of dynamic connectionist network approximates the underlying law governing each resolution level by a system of nonlinear difference equations. The individual wavelet scale forecasts are afterwards recombined to form the current estimate. The predictive ability of this strategy is assessed with the sunspot series.