Extraction of Information Content Exchange in Financial Markets by an Entropy Analysis

Recently, there has been an explosive interest in the literature about modeling and forecasting volatility in financial markets. Many researches have focused on energy markets and oil volatility index (OVX). In this paper, we aim first at evidencing if there is an exchange of information between two stock time series, and then at evaluating which is the direction of this information flow. In particular, we propose an entropy-based approach that exploits two objective metrics, namely Mutual Information (MI) and Transfer Entropy (TE), non requiring a parametric model and being directly applicable on the data. The experimental outcomes, applied on Brent and WTI crude oil prices and their volatility index for the period from May 10, 2007 till July 03, 2018 demonstrate the effectiveness of the proposed method.