Next Article in Journal
Desirable Portfolios in Fixed Income Markets: Application to Credit Risk Premiums
Previous Article in Journal
Multivariate Birnbaum-Saunders Distributions: Modelling and Applications
Open AccessArticle

Multiple Time Series Forecasting Using Quasi-Randomized Functional Link Neural Networks

1
ISFA, Laboratoire SAF, Université Claude Bernard Lyon I, 69100 Villeurbanne, France
2
Laboratoire IRMA, Université de Strasbourg, 67081 Strasbourg, France
*
Author to whom correspondence should be addressed.
Risks 2018, 6(1), 22; https://doi.org/10.3390/risks6010022
Received: 3 January 2018 / Revised: 16 February 2018 / Accepted: 26 February 2018 / Published: 12 March 2018
We are interested in obtaining forecasts for multiple time series, by taking into account the potential nonlinear relationships between their observations. For this purpose, we use a specific type of regression model on an augmented dataset of lagged time series. Our model is inspired by dynamic regression models (Pankratz 2012), with the response variable’s lags included as predictors, and is known as Random Vector Functional Link (RVFL) neural networks. The RVFL neural networks have been successfully applied in the past, to solving regression and classification problems. The novelty of our approach is to apply an RVFL model to multivariate time series, under two separate regularization constraints on the regression parameters. View Full-Text
Keywords: forecasting; multivariate time series; dynamic regression; neural networks forecasting; multivariate time series; dynamic regression; neural networks
Show Figures

Figure 1

MDPI and ACS Style

Moudiki, T.; Planchet, F.; Cousin, A. Multiple Time Series Forecasting Using Quasi-Randomized Functional Link Neural Networks. Risks 2018, 6, 22.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop