Systemic Risk

Dynamic Risk in the U.S. Banking System: An Analysis of Sentiment, Policy Shocks, and Spillover Effects ArXiv ID: 2601.01783 “View on arXiv” Authors: Haibo Wang, Jun Huang, Lutfu S Sua, Jaime Ortiz, Jinshyang Roan, Bahram Alidaee Abstract The 2023 U.S. banking crisis propagated not through direct financial linkages but through a high-frequency, information-based contagion channel. This paper moves beyond exploration analysis to test the “too-similar-to-fail” hypothesis, arguing that risk spillovers were driven by perceived similarities in bank business models under acute interest rate pressure. Employing a Time-Varying Parameter Vector Autoregression (TVP-VAR) model with 30-day rolling windows, a method uniquely suited for capturing the rapid network shifts inherent in a panic, we analyze daily stock returns for the four failed institutions and a systematically selected peer group of surviving banks vulnerable to the same risks from March 18, 2022, to March 15, 2023. Our results provide strong evidence for this contagion channel: total system connectedness surged dramatically during the crisis peak, and we identify SIVB, FRC, and WAL as primary net transmitters of risk while their perceived peers became significant net receivers, a key dynamic indicator of systemic vulnerability that cannot be captured by asset-by-asset analysis. We further demonstrate that these spillovers were significantly amplified by market sentiment (as measured by the VIX) and economic policy uncertainty (EPU). By providing a clear conceptual framework and robust empirical validation, our findings confirm the persistence of systemic risks within the banking network and highlight the importance of real-time monitoring in strengthening financial stability. ...

Investigating Conditional Restricted Boltzmann Machines in Regime Detection ArXiv ID: 2512.21823 “View on arXiv” Authors: Siddhartha Srinivas Rentala Abstract This study investigates the efficacy of Conditional Restricted Boltzmann Machines (CRBMs) for modeling high-dimensional financial time series and detecting systemic risk regimes. We extend the classical application of static Restricted Boltzmann Machines (RBMs) by incorporating autoregressive conditioning and utilizing Persistent Contrastive Divergence (PCD) to incorporate complex temporal dependency structures. Comparing a discrete Bernoulli-Bernoulli architecture against a continuous Gaussian-Bernoulli variant across a multi-asset dataset spanning 2013-2025, we observe a dichotomy between generative fidelity and regime detection. While the Gaussian CRBM successfully preserves static asset correlations, it exhibits limitations in generating long-range volatility clustering. Thus, we analyze the free energy as a relative negative log-likelihood (surprisal) under a fixed, trained model. We demonstrate that the model’s free energy serves as a robust, regime stability metric. By decomposing the free energy into quadratic (magnitude) and structural (correlation) components, we show that the model can distinguish between pure magnitude shocks and market regimes. Our findings suggest that the CRBM offers a valuable, interpretable diagnostic tool for monitoring systemic risk, providing a supplemental metric to implied volatility metrics like the VIX. ...

Modeling Bank Systemic Risk of Emerging Markets under Geopolitical Shocks: Empirical Evidence from BRICS Countries ArXiv ID: 2512.20515 “View on arXiv” Authors: Haibo Wang Abstract The growing economic influence of the BRICS nations requires risk models that capture complex, long-term dynamics. This paper introduces the Bank Risk Interlinkage with Dynamic Graph and Event Simulations (BRIDGES) framework, which analyzes systemic risk based on the level of information complexity (zero-order, first-order, and second-order). BRIDGES utilizes the Dynamic Time Warping (DTW) distance to construct a dynamic network for 551 BRICS banks based on their strategic similarity, using zero-order information such as annual balance sheet data from 2008 to 2024. It then employs first-order information, including trends in risk ratios, to detect shifts in banks’ behavior. A Temporal Graph Neural Network (TGNN), as the core of BRIDGES, is deployed to learn network evolutions and detect second-order information, such as anomalous changes in the structural relationships of the bank network. To measure the impact of anomalous changes on network stability, BRIDGES performs Agent-Based Model (ABM) simulations to assess the banking system’s resilience to internal financial failure and external geopolitical shocks at the individual country level and across BRICS nations. Simulation results show that the failure of the largest institutions causes more systemic damage than the failure of the financially vulnerable or dynamically anomalous ones, driven by powerful panic effects. Compared to this “too big to fail” scenario, a geopolitical shock with correlated country-wide propagation causes more destructive systemic damage, leading to a near-total systemic collapse. It suggests that the primary threats to BRICS financial stability are second-order panic and large-scale geopolitical shocks, which traditional risk analysis models might not detect. ...

Institutional Backing and Crypto Volatility: A Hybrid Framework for DeFi Stabilization ArXiv ID: 2512.19251 “View on arXiv” Authors: Ihlas Sovbetov Abstract Decentralized finance (DeFi) lacks centralized oversight, often resulting in heightened volatility. In contrast, centralized finance (CeFi) offers a more stable environment with institutional safeguards. Institutional backing can play a stabilizing role in a hybrid structure (HyFi), enhancing transparency, governance, and market discipline. This study investigates whether HyFi-like cryptocurrencies, those backed by institutions, exhibit lower price risk than fully decentralized counterparts. Using daily data for 18 major cryptocurrencies from January 2020 to November 2024, we estimate panel EGLS models with fixed, random, and dynamic specifications. Results show that HyFi-like assets consistently experience lower price risk, with this effect intensifying during periods of elevated market volatility. The negative interaction between HyFi status and market-wide volatility confirms their stabilizing role. Conversely, greater decentralization is strongly associated with increased volatility, particularly during periods of market stress. Robustness checks using quantile regressions and pre-/post-Terra Luna subsamples reinforce these findings, with stronger effects observed in high-volatility quantiles and post-crisis conditions. These results highlight the importance of institutional architecture in enhancing the resilience of digital asset markets. ...

Deep Learning and Elicitability for McKean-Vlasov FBSDEs With Common Noise ArXiv ID: 2512.14967 “View on arXiv” Authors: Felipe J. P. Antunes, Yuri F. Saporito, Sebastian Jaimungal Abstract We present a novel numerical method for solving McKean-Vlasov forward-backward stochastic differential equations (MV-FBSDEs) with common noise, combining Picard iterations, elicitability and deep learning. The key innovation involves elicitability to derive a path-wise loss function, enabling efficient training of neural networks to approximate both the backward process and the conditional expectations arising from common noise - without requiring computationally expensive nested Monte Carlo simulations. The mean-field interaction term is parameterized via a recurrent neural network trained to minimize an elicitable score, while the backward process is approximated through a feedforward network representing the decoupling field. We validate the algorithm on a systemic risk inter-bank borrowing and lending model, where analytical solutions exist, demonstrating accurate recovery of the true solution. We further extend the model to quantile-mediated interactions, showcasing the flexibility of the elicitability framework beyond conditional means or moments. Finally, we apply the method to a non-stationary Aiyagari–Bewley–Huggett economic growth model with endogenous interest rates, illustrating its applicability to complex mean-field games without closed-form solutions. ...

Universal Dynamics of Financial Bubbles in Isolated Markets: Evidence from the Iranian Stock Market ArXiv ID: 2512.12054 “View on arXiv” Authors: Ali Hosseinzadeh Abstract Speculative bubbles exhibit common statistical signatures across many financial markets, suggesting the presence of universal underlying mechanisms. We test this hypothesis in the Iranian stock market, an economy that is highly isolated, subject to capital controls, and largely inaccessible to foreign investors. Using the Log-Periodic Power Law Singularity (LPPLS) model, we analyze two major bubble episodes in 2020 and 2023. The estimated critical exponents beta around 0.46 and 0.20 fall within the empirical ranges documented for canonical historical bubbles such as the 1929 DJIA crash and the 2000 Nasdaq episode. The Tehran Stock Exchange displays clear LPPLS hallmarks, including faster-than-exponential price acceleration, log-periodic corrections, and stable estimates of the critical time horizon. These results indicate that endogenous herding, imitation, and positive-feedback dynamics, rather than exogenous shocks, play a dominant role even in politically and economically isolated markets. By showing that an emerging and semi-closed financial system conforms to the same dynamical patterns observed in global markets, this paper provides new empirical support for the universality of bubble dynamics. To the best of our knowledge, it also presents the first systematic LPPLS analysis of bubbles in the Tehran Stock Exchange. The findings highlight the usefulness of LPPLS-based diagnostic tools for monitoring systemic risk in emerging or restricted economies. ...

The Financial Connectome: A Brain-Inspired Framework for Modeling Latent Market Dynamics ArXiv ID: 2508.02012 “View on arXiv” Authors: Yuda Bi, Vince D Calhoun Abstract We propose the Financial Connectome, a new scientific discipline that models financial markets through the lens of brain functional architecture. Inspired by the foundational work of group independent component analysis (groupICA) in neuroscience, we reimagine markets not as collections of assets, but as high-dimensional dynamic systems composed of latent market modules. Treating stocks as functional nodes and their co-fluctuations as expressions of collective cognition, we introduce dynamic Market Network Connectivity (dMNC), the financial analogue of dynamic functional connectivity (dFNC). This biologically inspired framework reveals structurally persistent market subnetworks, captures regime shifts, and uncovers systemic early warning signals all without reliance on predictive labels. Our results suggest that markets, like brains, exhibit modular, self-organizing, and temporally evolving architectures. This work inaugurates the field of financial connectomics, a principled synthesis of systems neuroscience and quantitative finance aimed at uncovering the hidden logic of complex economies. ...

Mapping Crisis-Driven Market Dynamics: A Transfer Entropy and Kramers-Moyal Approach to Financial Networks ArXiv ID: 2507.09554 “View on arXiv” Authors: Pouriya Khalilian, Amirhossein N. Golestani, Mohammad Eslamifar, Mostafa T. Firouzjaee, Javad T. Firouzjaee Abstract Financial markets are dynamic, interconnected systems where local shocks can trigger widespread instability, challenging portfolio managers and policymakers. Traditional correlation analysis often miss the directionality and temporal dynamics of information flow. To address this, we present a unified framework integrating Transfer Entropy (TE) and the N-dimensional Kramers-Moyal (KM) expansion to map static and time-resolved coupling among four major indices: Nasdaq Composite (^IXIC), WTI crude oil (WTI), gold (GC=F), and the US Dollar Index (DX-Y.NYB). TE captures directional information flow. KM models non-linear stochastic dynamics, revealing interactions often overlooked by linear methods. Using daily data from August 11, 2014, to September 8, 2024, we compute returns, confirm non-stationary using a conduct sliding-window TE and KM analyses. We find that during the COVID-19 pandemic (March-June 2020) and the Russia-Ukraine crisis (Feb-Apr 2022), average TE increases by 35% and 28%, respectively, indicating heightened directional flow. Drift coefficients highlight gold-dollar interactions as a persistent safe-haven channel, while oil-equity linkages show regime shifts, weakening under stress and rebounding quickly. Our results expose the shortcomings of linear measures and underscore the value of combining information-theoretic and stochastic drift methods. This approach offers actionable insights for adaptive hedging and informs macro-prudential policy by revealing the evolving architecture of systemic risk. ...

Systemic Risk in the European Insurance Sector ArXiv ID: 2505.02635 “View on arXiv” Authors: Giovanni Bonaccolto, Nicola Borri, Andrea Consiglio, Giorgio Di Giorgio Abstract This paper investigates the dynamic interdependencies between the European insurance sector and key financial markets-equity, bond, and banking-by extending the Generalized Forecast Error Variance Decomposition framework to a broad set of performance and risk indicators. Our empirical analysis, based on a comprehensive dataset spanning January 2000 to October 2024, shows that the insurance market is not a passive receiver of external shocks but an active contributor in the propagation of systemic risk, particularly during periods of financial stress such as the subprime crisis, the European sovereign debt crisis, and the COVID-19 pandemic. Significant heterogeneity is observed across subsectors, with diversified multiline insurers and reinsurance playing key roles in shock transmission. Moreover, our granular company-level analysis reveals clusters of systemically central insurance companies, underscoring the presence of a core group that consistently exhibits high interconnectivity and influence in risk propagation. ...

Systemic Risk Management via Maximum Independent Set in Extremal Dependence Networks ArXiv ID: 2503.15534 “View on arXiv” Authors: Unknown Abstract The failure of key financial institutions may accelerate risk contagion due to their interconnections within the system. In this paper, we propose a robust portfolio strategy to mitigate systemic risks during extreme events. We use the stock returns of key financial institutions as an indicator of their performance, apply extreme value theory to assess the extremal dependence among stocks of financial institutions, and construct a network model based on a threshold approach that captures extremal dependence. Our analysis reveals different dependence structures in the Chinese and U.S. financial systems. By applying the maximum independent set (MIS) from graph theory, we identify a subset of institutions with minimal extremal dependence, facilitating the construction of diversified portfolios resilient to risk contagion. We also compare the performance of our proposed portfolios with that of the market portfolios in the two economies. ...