Pino, R.; de la Fuente, D.; Parreño, J.; Priore, P. The application of artificial neural networks to forecasting non-stationary or non-invertible time series. (Spanish. Abridged English version) Zbl 1055.37070 Qüestiió (2) 26, No. 3, 461-482 (2002). Summary: Recently increased interest in the application of artificial neural networks to forecasting times series, and attempts to exploit the undoubted advantages of these tools are noticeable. This paper deals with nonstationary or noninvertible times series that are problematic if forecasting uses the Box-Jenkins’ ARIMA methodology. The advantages of applying neural networks can be appreciated more clearly in the case of multivariate nonstationary system forecasting. MSC: 37M10 Time series analysis of dynamical systems 62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH) 62M45 Neural nets and related approaches to inference from stochastic processes 62M20 Inference from stochastic processes and prediction Keywords:time series; forecasting; artificial neural networks PDFBibTeX XMLCite \textit{R. Pino} et al., Qüestiió (2) 26, No. 3, 461--482 (2002; Zbl 1055.37070) Full Text: EuDML