Stochastic Nonlinear Time Series Forecasting Using Time-Delay Reservoir Computers: Performance and Universality
Neural Networks, 55C, 59-71 (2014)
24 Pages Posted: 6 Nov 2013 Last revised: 13 May 2014
Date Written: November 5, 2013
Reservoir computing is a recently introduced machine learning paradigm that has already shown excellent performances in the processing of empirical data. We study a particular kind of reservoir computers called time-delay reservoirs that are constructed out of the sampling of the solution of a time-delay differential equation and show their good performance in the forecasting of the conditional covariances associated to multivariate discrete-time nonlinear stochastic processes of VEC-GARCH type as well as in the prediction of factual daily market realized volatilities computed with intraday quotes, using as training input daily log-return series of moderate size. We tackle some problems associated to the lack of task-universality for individually operating reservoirs and propose a solution based on the use of parallel arrays of time-delay reservoirs.
Keywords: Reservoir computing, echo state networks, neural computing, time-delay reservoir, time series forecasting, universality, VEC-GARCH model, volatility forecasting, realized volatility, parallel reservoir computing
JEL Classification: C45, C53, C63
Suggested Citation: Suggested Citation