Granger Causality Detection in High-Dimensional Systems Using Feedforward Neural Networks

62 Pages Posted: 19 Mar 2020

See all articles by Hector F. Calvo-Pardo

Hector F. Calvo-Pardo

University of Southampton

Tullio Mancini

University of Southampton

Jose Olmo

Universidad de Zaragoza; University of Southampton

Date Written: February 24, 2020

Abstract

This paper proposes a novel methodology to detect Granger causality in mean in vector autoregressive settings using feedforward neural networks. The approach accommodates unknown dependence structures between the elements of highly-dimensional multivariate time series with weak and strong persistence. To do this, we propose a two-stage procedure. First, we fit a neural network given by an optimal number of nodes in the intermediate hidden layers. This is done by maximising the transfer of information between input and output variables in the network. Second, we apply a novel sparse double group lasso penalty function to identify the variables that have predictive ability and, hence, Granger cause the others. The penalty function inducing sparsity is applied to the weights characterizing the nodes of the neural network. We show the correct identification of these weights for increasing sample sizes. A comprehensive simulation study shows the strong performance of our method for Granger causality detection in terms of size and power, and the consistency of the method for model selection for increasing sample sizes. An application to the recently created Tobalaba network of renewable energy companies shows the increase in connectivity between companies after the creation of the network using Granger-causality measures to map the connections.

Keywords: Granger-causality, lasso penalty function, mutual information, neural networks, sparsity

JEL Classification: G11

Suggested Citation

Calvo-Pardo, Hector F. and Mancini, Tullio and Olmo, Jose, Granger Causality Detection in High-Dimensional Systems Using Feedforward Neural Networks (February 24, 2020). Available at SSRN: https://ssrn.com/abstract=3543687 or http://dx.doi.org/10.2139/ssrn.3543687

Hector F. Calvo-Pardo

University of Southampton ( email )

University Rd.
Southampton SO17 1BJ, Hampshire SO17 1LP
United Kingdom

Tullio Mancini

University of Southampton ( email )

University Rd.
Southampton SO17 1BJ, Hampshire SO17 1LP
United Kingdom

Jose Olmo (Contact Author)

Universidad de Zaragoza ( email )

Gran Via, 2
50005 Zaragoza, Zaragoza 50005
Spain

University of Southampton ( email )

Southampton
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
88
Abstract Views
530
Rank
437,024
PlumX Metrics