Network Structure and Market Risk in the European Equity Market

This paper proposes a methodology to anticipate market risk using qualitative and quantitative variables that capture communicative and financial activity within equity networks. During periods of crisis as market risk increases, companies tend to behave alike, and the number of news and common topics among companies increases. A corporate news network is built where the nodes are top European companies, and the edges are the number of news items on the same topic by every pair of companies identified by the topic model methodology. A longitudinal analysis was conducted using a time series of static social networks to generate a dynamic social network and proposed the component causality index as a leading indicator of market risk. This research finds out that the component causality index, based on centrality indicators, anticipates, or moves together with value-at-risk during the period 2005-2011.