Key Borrowers Detected by the Intensities of Their Short-Range Interactions

Abstract

The issue of systemic importance has received particular attention since the recent financial crisis when it came to the fore that an individual financial institution can disturb the whole financial system. Interconnectedness is considered as one of the key drivers of systemic importance. Several measures have been proposed in the literature in order to estimate the interconnectedness of financial institutions and systems. However, most of them lack an important dimension of this characteristic: intensities of agent interaction. This paper proposes a novel method that solves this issue. A distinctive feature of our approach is that it takes into consideration not just the interconnectedness of agents but also their interaction intensities. The approach is based on the power index and centrality analysis and is employed to find a key borrower in a loan market. To illustrate the feasibility of our methodology we apply it at the European Union level and find key countries-borrowers. JEL Classification: C7, G2.

A Hybrid Network Analysis and Machine Learning Model for Enhanced Financial Distress Prediction

“…Assessing interconnectedness in financial institutions has been identified as an early warning indicator for distress in financial [45]. Several methodologies have been suggested in scholarly works to gauge the level of interconnection across financial institutions and systems [46].…”