Uncovering Sparse Financial Networks with Information Criteria

2026-01-07

AI Summary

This study addresses the limitation of conventional financial connectedness measures based on forecast error variance decomposition (FEVD), which often yield dense networks that obscure genuine systemic risk transmission channels. The authors reformulate FEVD-based connectedness estimation as a regression model selection problem and, for the first time, introduce information criteria to construct a sparse network identification framework. They extend this approach to generalized FEVD to accommodate correlated shocks and heavy-tailed errors, and employ pseudo out-of-sample forecasting to automatically tune the penalty parameter. The proposed method consistently recovers active spillover channels and demonstrates finite-sample effectiveness and robustness in Monte Carlo simulations. Empirical applications to global equity markets, S&P 500 sector indices, and commodity futures reveal an intrinsically sparse structure underlying financial networks.

Technology Category

Reasoning under Uncertainty: Relational Probabilistic ModelsCognitive Modeling & Cognitive Systems: Neural Spike CodingMachine Learning: Feature Construction/Reformulation

Application Category

Social Networks and Social Media: Social media analysis through the lenses of networksEconomics, Online Markets and Human Computation: Social networks and social learningGraph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Empirical measures of financial connectedness based on Forecast Error Variance Decompositions (FEVDs) often yield dense network structures that obscure true transmission channels and complicate the identification of systemic risk. This paper proposes a novel information-criterion-based approach to uncover sparse, economically meaningful financial networks. By reformulating FEVD-based connectedness as a regression problem, we develop a model selection framework that consistently recovers the active set of spillover channels. We extend this method to generalized FEVDs to accommodate correlated shocks and introduce a data-driven procedure for tuning the penalty parameter using pseudo-out-of-sample forecast performance. Monte Carlo simulations demonstrate the approach's effectiveness with finite samples and its robustness to approximately sparse networks and heavy-tailed errors. Applications to global stock markets, S&P 500 sectoral indices, and commodity futures highlight the prevalence of sparse networks in empirical settings.

Problem

• financial connectedness
• sparse networks
• forecast error variance decomposition
• systemic risk
• information criteria

Innovation

• sparse financial networks
• information criteria
• forecast error variance decomposition
• model selection
• systemic risk