Authors: Jonas Krampe, Luca Margaritella

Published on: February 04, 2024

Impact Score: 8.45

Arxiv code: Arxiv:2402.02482

Summary

• What is new: A new approach to estimate high-dimensional global bank network connectedness, differentiating between system-wide connectedness due to common components (banking market) and idiosyncratic shocks (single banks).
• Why this is important: Current methods risk underestimating systemic risk by oversimplifying high-dimensional datasets and failing to distinguish between market-wide and bank-specific influences.
• What the research proposes: A dynamic factor model with sparse VAR idiosyncratic components that isolates the effects of common component shocks and idiosyncratic shocks on system-wide connectedness.
• Results: The new method demonstrates that in normal times, idiosyncratic variation drives 60-80% of system-wide connectedness, but during crises like 2008 and Covid19, the market dynamic plays a significantly larger role.

Technical Details

Technological frameworks used: nan

Models used: Dynamic Factor Model with Sparse VAR Idiosyncratic Components

Data used: Daily data from 2003-2013 and a more recent dataset from 2014-2023

Potential Impact

This research impacts global banking, risk assessment, and financial crisis management sectors, offering improved tools for predicting and understanding systemic risk.

Want to implement this idea in a business?

We have generated a startup concept here: FinSight Analytics.