|
on Risk Management |
| By: | Fabio Anobile (LUM University); Francesco Frangiamore (University of Palermo); Marco Maria Matarrese (University of Palermo); Jamel Saadaoui (University Paris 8) |
| Abstract: | This paper shows that geopolitical risk is an important predictor of tail risks in the investment growth distribution. Using the growth-at-risk framework, we document that higher geopolitical risk predicts lower left tails, while having no impact on the other parts of the distribution. We document higher uncertainty during periods of heightened geopolitical risks, when also the distribution becomes more left-skewed, leading extremely negative outcomes to become more likely. Additional structural analysis based on local projections shows that GPR shocks have larger dynamic effects on the left tail of the distribution, affecting particularly and significantly downside risk. |
| Keywords: | Geopolitical risk, investment, quantile regressions, local projections |
| JEL: | E M |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:inf:wpaper:2025.19 |
| By: | Peng Liu; Yang Liu; Houhan Teng |
| Abstract: | In this paper, we provide extended convolution bounds for the Fr\'{e}chet problem and discuss related implications in quantitative risk management. First, we establish a new form of inequality for the Range-Value-at-Risk (RVaR). Based on this inequality, we obtain bounds for robust risk aggregation with dependence uncertainty for (i) RVaR, (ii) inter-RVaR difference and (iii) inter-quantile difference, and provide sharpness conditions. These bounds are called extended convolution bounds, which not only complement the results in the literature (convolution bounds in Blanchet et al. (2025)) but also offer results for some variability measures. Next, applying the above inequality, we study the risk sharing for the averaged quantiles (corresponding to risk sharing for distortion risk measures with special inverse S-shaped distortion functions), which is a non-convex optimization problem. We obtain the expression of the minimal value of the risk sharing and the explicit expression for the corresponding optimal allocation, which is comonotonic risk sharing for large losses and counter-comonotonic risk sharing for small losses or large gains. Finally, we explore the dependence structure for the optimal allocations, showing that the optimal allocation does not exist if the risk is not bounded from above. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.21929 |
| By: | Turner, Dylan; Tsiboe, Francis; Baldwin, Katherine L.; Dong, Fengxia |
| Keywords: | Agricultural and Food Policy, Risk and Uncertainty, Farm Management |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:ags:aaea24:343841 |
| By: | Haoying Dai |
| Abstract: | We develop a theoretical framework that aims to link micro-level option hedging and stock-specific factor exposure with macro-level market turbulence and explain endogenous volatility amplification during gamma-squeeze events. By explicitly modeling market-maker delta-neutral hedging and incorporating beta-dependent volatility normalization, we derive a stability condition that characterizes the onset of a gamma-squeeze event. The model captures a nonlinear recursive feedback loop between market-maker hedging and price movements and the resulting self-reinforcing dynamics. From a complex-systems perspective, the dynamics represent a bounded nonlinear response in which effective gain depends jointly on beta-normalized shock perception and gamma-scaled sensitivity. Our analysis highlights that low-beta stocks exhibit disproportionately strong feedback even for modest absolute price movements. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.22766 |
| By: | Chunxiao Lu (University of Canterbury); Linxiang Ma; Yuyang Zhang |
| Abstract: | This paper investigates whether institutional investors incorporate firm-level environmental regulatory risk into their portfolio decisions. We document substantial heterogeneity across investor types in their responses to changes in firm-level environmental regulatory risk. Long-horizon investors, such as banks, insurance companies, and pension funds, tend to tilt their portfolios toward stocks with higher environmental regulatory risk. In contrast, short-horizon investors, including investment advisors and mutual funds, reduce their holdings of these firms. These opposing portfolio adjustments offset each other, attenuating the aggregate impact on stock returns. We further find that these risk-induced demand shifts vary systematically around federal elections. Following Democratic victories, the resolution of regulatory uncertainty induces long-horizon investors to decrease their exposure to environmentally risky firms, while short-horizon investors increase their holdings. By comparison, portfolio adjustments are substantially less pronounced after Republican victories. Overall, our findings highlight the role of investment horizons and heterogeneous environmental preferences in driving institutional portfolio allocation. |
| Keywords: | Environmental regulatory risk, Institutional investors, Asset demand, Investor horizon, Environmental commitment |
| JEL: | G11 G12 G20 G28 Q50 |
| Date: | 2025–12–01 |
| URL: | https://d.repec.org/n?u=RePEc:cbt:econwp:25/14 |
| By: | Wahdat, Ahmad Z.; Bryant, Elijah H.; Hubbell, Caitlinn B.; Balagtas, Joseph V. |
| Keywords: | Food Consumption/Nutrition/Food Safety, Demand and Price Analysis, Risk and Uncertainty |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:ags:aaea24:343899 |
| By: | Ponte Marques, Aurea; Juselius, Mikael; Tarashev, Nikola |
| Abstract: | We employ 68 quarters of data – including from non-public supervisory sources – to study how 17 US and 17 euro-area banks balance the risk of breaching regulatory requirements against the cost of maintaining and speedily restoring “management” buffers. We find that steady-state management buffer targets systematically declined and regulatory risk tolerance (RRT) rose following the Great Financial Crisis, especially at banks experiencing a stronger increase in capital requirements. As a sign that RRT is a conscious choice, banks facing more volatile management buffer shocks set higher management buffer targets. High-RRT banks tend to respond to a depletion of their management buffers by cutting lending, whereas low-RRT banks reduce the riskiness but not the volume of their assets — thus highlighting real-economy effects of capital management strategies. JEL Classification: G21, G28, E51, G31 |
| Keywords: | bank regulation, capital management, management buffer target, speed of reversion |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:ecb:ecbwps:20253161 |
| By: | Eden Gross; Ryan Kruger; Francois Toerien |
| Abstract: | This study introduces a dynamic Bayesian network (DBN) framework for forecasting value at risk (VaR) and stressed VaR (SVaR) and compares its performance to several commonly applied models. Using daily S&P 500 index returns from 1991 to 2020, we produce 10-day 99% VaR and SVaR forecasts using a rolling period and historical returns for the traditional models, while three DBNs use both historical and forecasted returns. We evaluate the models' forecasting accuracy using standard backtests and forecasting error measures. Results show that autoregressive models deliver the most accurate VaR forecasts, while the DBNs achieve comparable performance to the historical simulation model, despite incorporating forward-looking return forecasts. For SVaR, all models produce highly conservative forecasts, with minimal breaches and limited differentiation in accuracy. While DBNs do not outperform traditional models, they demonstrate feasibility as a forward-looking approach to provide a foundation for future research on integrating causal inference into financial risk forecasting. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.05661 |
| By: | Aviv Alpern; Svetlozar Rachev |
| Abstract: | We introduce a simple portfolio optimization strategy using ESG data with the Black-Litterman allocation framework. ESG scores are used as a bias for Stein shrinkage estimation of equilibrium risk premiums used in assigning Black-Litterman asset weights. Assets are modeled as multivariate affine normal-inverse Gaussian variables using CVaR as a risk measure. This strategy, though very simple, when employed with a soft turnover constraint is exceptionally successful. Portfolios are reallocated daily over a 4.7 year period, each with a different set of hyperparameters used for optimization. The most successful strategies have returns of approximately 40-45% annually. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.21850 |
| By: | Yang Zhou (Graduate School of Economics, Nagoya City University, JAPAN); Shigeto Kitano (Research Institute for Economics and Business Administration, Kobe University, JAPAN) |
| Abstract: | Do geopolitical risks affect the occurrence of "extreme capital flow episodes"? Using a panel of 57 economies from 1986Q1 to 2023Q4, we examine the effects of both global and country-specific geopolitical risks on the occurrence of the four types of extreme capital episodes ("surge", "stop", "flight", and "retrenchment"). We find no association between global geopolitical risks and the occurrence of extreme capital flow episodes for advanced economies and only a weak association for emerging economies. In contrast, country-specific geopolitical risks show no significant association for advanced economies but a significant association for emerging economies. Our results suggest that when country-specific geopolitical risk is high, an emerging economy is more likely to experience stop, flight, and retrenchment episodes and less likely to experience surge episodes, reflecting heightened risk perceptions among both domestic and foreign investors. For each episode, we further identify its key underlying flow type: banking flows for flight, direct investment flows for stop, and banking, debt, and equity flows for retrenchment. We also find that country specific geopolitical risks became a more important driver of these episodes after the global financial crisis. These findings are robust to incorporating additional economic uncertainty indices, to excluding or adding certain control variables, to removing periods of dramatic global geopolitical risk fluctuations, and to employing alternative econometric methodologies. |
| Keywords: | Global geopolitical risk; Country-specific geopolitical Risk; Extreme capital flow episodes; Emerging economies; Flight-to-safety; Flighthome effects |
| JEL: | E44 F32 F51 G28 G32 |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:kob:dpaper:dp2025-32 |
| By: | Frederik Rech (School of Economics, Beijing Institute of Technology, Beijing, China); Fanchen Meng (Faculty of Economics, Shenzhen MSU-BIT University, Shenzhen, China); Hussam Musa (Faculty of Economics, Matej Bel University, Bansk\'a Bystrica, Slovakia); Martin \v{S}ebe\v{n}a (Faculty of Arts and Social Sciences, Hong Kong Baptist University, Hong Kong, China); Siele Jean Tuo (Business School, Liaoning University, Shenyang, China) |
| Abstract: | This study investigates whether firm-level artificial intelligence (AI) adoption improves the out-of-sample prediction of corporate financial distress models beyond traditional financial ratios. Using a sample of Chinese listed firms (2008-2023), we address sparse AI data with a novel pruned training window method, testing multiple machine learning models. We find that AI adoption consistently increases predictive accuracy, with the largest gains in recall rates for identifying distressed firms. Tree-based models and AI density metrics proved most effective. Crucially, models using longer histories outperformed those relying solely on recent "AI-rich" data. The analysis also identifies divergent adoption patterns, with healthy firms exhibiting earlier and higher AI uptake than distressed peers. These findings, while based on Chinese data, provide a framework for early-warning signals and demonstrate the broader potential of AI metrics as a stable, complementary risk indicator distinct from traditional accounting measures. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.02510 |
| By: | Micha{\l} Sikorski |
| Abstract: | Volatility clustering is one of the most robust stylized facts of financial markets, yet it is typically detected using moment-based diagnostics or parametric models such as GARCH. This paper shows that clustered volatility also leaves a clear imprint on the time-reversal symmetry of horizontal visibility graphs (HVGs) constructed on absolute returns in physical time. For each time point, we compute the maximal forward and backward visibility distances, $L^{+}(t)$ and $L^{-}(t)$, and use their empirical distributions to build a visibility-asymmetry fingerprint comprising the Kolmogorov--Smirnov distance, variance difference, entropy difference, and a ratio of extreme visibility spans. In a Monte Carlo study, these HVG asymmetry features sharply separate volatility-clustered GARCH(1, 1) dynamics from i.i.d.\ Gaussian noise and from randomly shuffled GARCH series that preserve the marginal distribution but destroy temporal dependence; a simple linear classifier based on the fingerprint achieves about 90\% in-sample accuracy. Applying the method to daily S\&P500 data reveals a pronounced forward--backward imbalance, including a variance difference $\Delta\mathrm{Var}$ that exceeds the simulated GARCH values by two orders of magnitude and vanishes after shuffling. Overall, the visibility-graph asymmetry fingerprint emerges as a simple, model-free, and geometrically interpretable indicator of volatility clustering and time irreversibility in financial time series. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.02352 |
| By: | Paolo Bartesaghi; Rosanna Grassi; Pierpaolo Uberti |
| Abstract: | The global balance is a well-known indicator of the behavior of a signed network. Recent literature has introduced the concept of local balance as a measure of the contribution of a single node to the overall balance of the network. In the present research, we investigate the potential of using deviations of local balance from global balance as a criterion for selecting outperforming assets. The underlying idea is that, during financial crises, most assets in the investment universe behave similarly: losses are severe and widespread, and the global balance of the correlation-based signed network reaches its maximum value. Under such circumstances, standard diversification (mainly related to portfolio size) is unable to reduce risk or limit losses. Therefore, it may be useful to concentrate portfolio exposures on the few assets - if such assets exist-that behave differently from the rest of the market. We argue that these assets are those for which the local balance strongly departs from the global balance of the underlying signed network. The paper supports this hypothesis through an application using real financial data. The results, in both descriptive and predictive contexts, confirm the proposed intuition. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.10606 |
| By: | Ceglar, Andrej; Jwaideh, Mark; Danieli, Francesca; Pasqua, Carlo; Hutchinson, John; Ranger, Nicola; Heemskerk, Irene; O’Donnell, Emma; Cimini, Francesco; Sabuco, Juan; Alvarez, Jimena |
| Abstract: | Degraded ecosystems undermine productivity, disrupt supply chains and heighten vulnerability to shocks, creating risks for the real economy and the financial sector. Biodiversity loss and ecosystem degradation also pose a growing risk to price stability, with increasing evidence that ecosystem shocks contribute to inflationary pressures in the euro area. This paper moves from dependency mapping to a risk-based assessment of the euro area economy and banks, applying the nature value-at-risk (NVaR) framework, which links biophysical shocks to ecosystem services with sectoral-production functions1. Water-related risks, including flood protection, surface water and groundwater scarcity, and water quality, emerge as the most material for the euro area economy. Surface-water scarcity alone could expose up to 24% of euro area output to risk under a drought event with a 100-year return period. A complementary endogenous-risk analysis that was conducted, quantified the extent to which euro area firms and banks may contribute to the very ecosystem degradation on which their activities depend, creating feedback loops that could amplify financial risks over time. The results showed material feedback loops between ecosystem degradation and banks’ own portfolios, with water-related risks being the dominant transmission channel. Overall, this study takes a first step towards the identification of risk hotspots and provides a more robust assessment of nature-related risks than prior studies. It also discusses the remaining data gaps and methodological constraints, and outlines the next steps to be taken, as a priority, to address this. JEL Classification: Q51, Q54, E31 |
| Keywords: | ecosystem degradation, endogenous risk, nature-related financial risks, price stability, sectoral output at risk, water scarcity and quality |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:ecb:ecbops:2025380 |
| By: | Weikang Zhang; Alison Watts |
| Abstract: | Crypto enthusiasts claim that buying and holding crypto assets yields high returns, often citing Bitcoin's past performance to promote other tokens and fuel fear of missing out. However, understanding the real risk-return trade-off and what factors affect future crypto returns is crucial as crypto becomes increasingly accessible to retail investors through major brokerages. We examine the HODL strategy through two independent analyses. First, we implement 480 million Monte Carlo simulations across 378 non-stablecoin crypto assets, net of trading fees and the opportunity cost of 1-month Treasury bills, and find strong evidence of survivorship bias and extreme downside concentration. At the 2-3 year horizon, the median excess return is -28.4 percent, the 1 percent conditional value at risk indicates that tail scenarios wipe out principal after all costs, and only the top quartile achieves very large gains, with a mean excess return of 1, 326.7 percent. These results challenge the HODL narrative: across a broad set of assets, simple buy-and-hold loads extreme downside risk onto most investors, and the miracles mostly belong to the luckiest quarter. Second, using a Bayesian multi-horizon local projection framework, we find that endogenous predictors based on realized risk-return metrics have economically negligible and unstable effects, while macro-finance factors, especially the 24-week exponential moving average of the Fear and Greed Index, display persistent long-horizon impacts and high cross-basket stability. Where significant, a one-standard-deviation sentiment shock reduces forward top-quartile mean excess returns by 15-22 percentage points and median returns by 6-10 percentage points over 1-3 year horizons, suggesting that macro-sentiment conditions, rather than realized return histories, are the dominant indicators for future outcomes. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.02029 |
| By: | Omar Abdelrahman; Josef Schroth |
| Abstract: | When a bank holds a lot of safe assets, it is well situated to deal with funding stress. But when all banks hold a lot of safe assets, a pecuniary externality implies that their (wholesale) funding costs increase. This reduces banks’ ability to hold capital buffers and thus, paradoxically, increases the frequency of funding stress. |
| Keywords: | Business fluctuations and cycles; Credit and credit aggregates |
| JEL: | E4 E44 E6 G2 G21 G28 |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:bca:bocsan:25-28 |
| By: | John Beirne (Asian Development Bank); Nuobu Renzhi (Capital University of Economics and Business in Beijing) |
| Abstract: | This paper examines the effects of country-specific geopolitical risk on capital flow volatility and asset markets across 29 emerging and advanced economies over the period 2000–2023. Using panel regressions and a panel structural vector autoregression framework, the results show that geopolitical risk raises bond yields and leads to exchange rate depreciation, with stronger and more persistent effects in emerging economies. Asset markets for advanced economies are affected mainly through lower equity prices. The impact on capital flow volatility is slightly higher on average for advanced economies but remains more persistent for emerging economies. Greater financial development, higher central bank independence, and lower public debt mitigate the adverse effects of geopolitical risk on both capital flows and asset markets. These findings highlight the importance of strong macroeconomic fundamentals and institutional frameworks in building resilience against geopolitical shocks. |
| Keywords: | geopolitical risk;capital flow volatility;financial markets |
| JEL: | G15 G41 |
| Date: | 2025–11–21 |
| URL: | https://d.repec.org/n?u=RePEc:ris:adbewp:021786 |
| By: | Josef Schroth |
| Abstract: | Time-varying capital buffer requirements are a powerful tool that allow bank regulators to avoid severe financial stress without the cost of imposing very high levels of capital. However, this tool is only effective if banks understand how it is used. I present a model that banks and financial market participants can use to anticipate how time-varying capital buffer requirements change over time. |
| Keywords: | Business fluctuations and cycles; Credit and credit aggregates |
| JEL: | E E1 E13 E3 E32 E4 E44 |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:bca:bocsan:25-27 |
| By: | Thi Thanh Ha DOAN; Asei ITO; Changyuan LUO; Hongyong ZHANG |
| Abstract: | Utilizing comprehensive parent-affiliate matched data on Japanese multinational firms, this study investigates how geopolitical risks affect global supply chain configurations, with a focus on East and Southeast Asia during the period 2009–2022. We construct firm-level exposure to geopolitical risk in China using data on trade and foreign direct investment. First, Japanese multinational firms tend to respond to geopolitical shocks by diversifying their supply chains away from China and toward the Association of Southeast Asian Nations’ (ASEAN) economies. This response is particularly pronounced among firms that depend heavily on imported inputs from China or maintain substantial production operations there. Second, such diversification typically does not entail drastic within-firm relocation (“friend-shoring†) of supply chains. Third, Japanese multinational firms tend to increase their capital investment in Japan while maintaining their existing production bases in China. These results suggest that firms favor a strategy of supply chain diversification—rather than outright relocation / reshoring or abrupt decoupling—as a means of mitigating geopolitical risks. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:eti:dpaper:25112 |
| By: | Ziyao Wang; A. Alexandre Trindade; Svetlozar T. Rachev |
| Abstract: | This paper develops a three-dimensional decomposition of volatility memory into orthogonal components of level, shape, and tempo. The framework unifies regime-switching, fractional-integration, and business-time approaches within a single canonical representation that identifies how each dimension governs persistence strength, long-memory form, and temporal speed. We establish conditions for existence, uniqueness, and ergodicity of this decomposition and show that all GARCH-type processes arise as special cases. Empirically, applications to SPY and EURUSD (2005--2024) reveal that volatility memory is state-dependent: regime and tempo gates dominate in equities, while fractional-memory gates prevail in foreign exchange. The unified tri-gate model jointly captures these effects. By formalizing volatility dynamics through a level--shape--tempo structure, the paper provides a coherent link between information flow, market activity, and the evolving memory of financial volatility. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.02166 |
| By: | Hansjoerg Albrecher; Jan Beirlant |
| Abstract: | We provide a survey of how techniques developed for the modelling of extremes naturally matter in insurance, and how they need to and can be adapted for the insurance applications. Topics covered include truncation, tempering, censoring and regression techniques. The discussed techniques are illustrated on concrete data sets. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.22272 |
| By: | Kundan Mukhia; Buddha Nath Sharma; Salam Rabindrajit Luwang; Md. Nurujjaman; Chittaranjan Hens; Suman Saha; Tanujit Chakraborty |
| Abstract: | We study how the 2024 U.S. presidential election, viewed as a major political risk event, affected cryptocurrency markets by distinguishing human-driven peer-to-peer stablecoin transactions from automated algorithmic activity. Using structural break analysis, we find that human-driven Ethereum Request for Comment 20 (ERC-20) transactions shifted on November 3, two days before the election, while exchange trading volumes reacted only on Election Day. Automated smart-contract activity adjusted much later, with structural breaks appearing in January 2025. We validate these shifts using surrogate-based robustness tests. Complementary energy-spectrum analysis of Bitcoin and Ethereum identifies pronounced post-election turbulence, and a structural vector autoregression confirms a regime shift in stablecoin dynamics. Overall, human-driven stablecoin flows act as early-warning indicators of political stress, preceding both exchange behavior and algorithmic responses. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.00893 |
| By: | Tatsuro Senga (KEIO UNIVERSITY AND QUEEN MARY UNIVERSITY OF LONDON); Iacopo Varotto (BANCO DE ESPAÑA) |
| Abstract: | Does micro-level investment irreversibility amplify or dampen business cycles? We show this depends on the source of aggregate risk. Investment irreversibility reduces fluctuations in both aggregate output and investment when firm-level idiosyncratic shocks aggregate up to economy-wide effects. This contrasts with models driven by aggregate productivity shocks, where irreversibility has little effect on volatility. The key is whether idiosyncratic shocks are suffi ciently volatile to cause the irreversibility constraint to bind cyclically for a significant mass of firms. If so, investment irreversibility hampers productivity-enhancing capital reallocation and reduces business cycle volatility. Moreover, household consumption smoothing is impeded when firms cannot adjust capital optimally, increasing real wage volatility. This labor market effect, combined with capital misallocation, reduces aggregate output volatility by 22 percent and investment volatility by 60 percent. These results highlight the importance of considering the source of economic volatility when assessing investment frictions. We provide empirical support for these predictions using firm-level investment data from Compustat. |
| Keywords: | investment irreversibility, business cycles, idiosyncratic shocks, capital misallocation |
| JEL: | D25 E22 E23 E32 |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:bde:wpaper:2546 |
| By: | Wenbin Wu; Kejiang Qian; Alexis Lui; Christopher Jack; Yue Wu; Peter McBurney; Fengxiang He; Bryan Zhang |
| Abstract: | We curate the DeXposure dataset, the first large-scale dataset for inter-protocol credit exposure in decentralized financial networks, covering global markets of 43.7 million entries across 4.3 thousand protocols, 602 blockchains, and 24.3 thousand tokens, from 2020 to 2025. A new measure, value-linked credit exposure between protocols, is defined as the inferred financial dependency relationships derived from changes in Total Value Locked (TVL). We develop a token-to-protocol model using DefiLlama metadata to infer inter-protocol credit exposure from the token's stock dynamics, as reported by the protocols. Based on the curated dataset, we develop three benchmarks for machine learning research with financial applications: (1) graph clustering for global network measurement, tracking the structural evolution of credit exposure networks, (2) vector autoregression for sector-level credit exposure dynamics during major shocks (Terra and FTX), and (3) temporal graph neural networks for dynamic link prediction on temporal graphs. From the analysis, we observe (1) a rapid growth of network volume, (2) a trend of concentration to key protocols, (3) a decline of network density (the ratio of actual connections to possible connections), and (4) distinct shock propagation across sectors, such as lending platforms, trading exchanges, and asset management protocols. The DeXposure dataset and code have been released publicly. We envision they will help with research and practice in machine learning as well as financial risk monitoring, policy analysis, DeFi market modeling, amongst others. The dataset also contributes to machine learning research by offering benchmarks for graph clustering, vector autoregression, and temporal graph analysis. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.22314 |