Finance has all the time been about connections, but traditional models often oversimplify them. The 2008 global financial crisis and the COVID-19 market shock demonstrated how misleading these assumptions will be. The collapse of Lehman Brothers and the near-bankruptcy of AIG demonstrated how distress spreads through connections that traditional approaches couldn’t capture. What was missing was a framework to map and measure these interdependencies.
This chapter highlights how network theory, long utilized in data science, will be applied to practical investment problems. Traditional tools equivalent to clustering and centrality remain essential, while machine learning (ML) techniques, including graphical neural networks (GNNs), provide additional opportunities to uncover hidden clusters, track contagions, and test scenarios across markets.
By combining established networking tools with newer ML methods, practitioners can see how assets, institutions, and data flows are connected. This perspective helps them move beyond simplistic assumptions and uncover patterns that influence diversification, systemic risk and market forecasts.
