|
on Risk Management |
| By: | Luis Enriquez Alvarez |
| Abstract: | Artificial intelligence risks are multidimensional in nature, as the same risk scenarios may have legal, operational, and financial risk dimensions. With the emergence of new AI regulations, the state of the art of artificial intelligence risk management seems to be highly immature due to upcoming AI regulations. Despite the appearance of several methodologies and generic criteria, it is rare to find guidelines with real implementation value, considering that the most important issue is customizing artificial intelligence risk metrics and risk models for specific AI risk scenarios. Furthermore, the financial departments, legal departments and Government Risk Compliance teams seem to remain unaware of many technical aspects of AI systems, in which data scientists and AI engineers emerge as the most appropriate implementers. It is crucial to decompose the problem of artificial intelligence risk in several dimensions: data protection, fairness, accuracy, robustness, and information security. Consequently, the main task is developing adequate metrics and risk models that manage to reduce uncertainty for decision-making in order to take informed decisions concerning the risk management of AI systems. The purpose of this paper is to orientate AI stakeholders about the depths of AI risk management. Although it is not extremely technical, it requires a basic knowledge of risk management, quantifying uncertainty, the FAIR model, machine learning, large language models and AI context engineering. The examples presented pretend to be very basic and understandable, providing simple ideas that can be developed regarding specific AI customized environments. There are many issues to solve in AI risk management, and this paper will present a holistic overview of the inter-dependencies of AI risks, and how to model them together, within risk scenarios. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.18394 |
| By: | Martin Aichele; Igor Cialenco; Damian Jelito; Marcin Pitera |
| Abstract: | We develop a statistical framework for risk estimation, inspired by the axiomatic theory of risk measures. Coherent risk estimators -- functionals of P&L samples inheriting the economic properties of risk measures -- are defined and characterized through robust representations linked to $L$-estimators. The framework provides a canonical methodology for constructing estimators with sound financial and statistical properties, unifying risk measure theory, principles for capital adequacy, and practical statistical challenges in market risk. A numerical study illustrates the approach, focusing on expected shortfall estimation under both i.i.d. and overlapping samples relevant for regulatory FRTB model applications. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.05809 |
| By: | Albert Di Wang; Ye Du |
| Abstract: | Risk management is a prominent issue in peer-to-peer lending. An investor may naturally reduce his risk exposure by diversifying instead of putting all his money on one loan. In that case, an investor may want to minimize the Value-at-Risk (VaR) or Conditional Value-at-Risk (CVaR) of his loan portfolio. We propose a low degree of freedom deep neural network model, DeNN, as well as a high degree of freedom model, DSNN, to tackle the problem. In particular, our models predict not only the default probability of a loan but also the time when it will default. The experiments demonstrate that both models can significantly reduce the portfolio VaRs at different confidence levels, compared to benchmarks. More interestingly, the low degree of freedom model, DeNN, outperforms DSNN in most scenarios. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.07444 |
| By: | Takaaki Koike |
| Abstract: | Dependence among multiple lifetimes is a key factor for pricing and evaluating the risk of joint life insurance products. The dependence structure can be exposed to model uncertainty when available data and information are limited. We address robust pricing and risk evaluation of joint life insurance products against dependence uncertainty among lifetimes. We first show that, for some class of standard contracts, the risk evaluation based on distortion risk measure is monotone with respect to the concordance order of the underlying copula. Based on this monotonicity, we then study the most conservative and anti-conservative risk evaluations for this class of contracts. We prove that the bounds for the mean, Value-at-Risk and Expected shortfall are computed by a combination of linear programs when the uncertainty set is defined by some norm-ball centered around a reference copula. Our numerical analysis reveals that the sensitivity of the risk evaluation against the choice of the copula differs depending on the risk measure and the type of the contract, and our proposed bounds can improve the existing bounds based on the available information. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.01971 |
| By: | Jinghui Chen; Edward Furman; Stephano Ricci; Judeto Shanthirajah |
| Abstract: | The limitations of the traditional mean-variance (MV) efficient frontier, as introduced by Markowitz (1952), have been extensively documented in the literature. Specifically, the assumptions of normally distributed returns or quadratic investor preferences are often unrealistic in practice. Moreover, variance is not always an appropriate risk measure, particularly for heavy-tailed and highly volatile distributions, such as those observed in insurance claims and cryptocurrency markets, which may exhibit infinite variance. To address these issues, Shalit and Yitzhaki (2005) proposed a mean-Gini (MG) framework for portfolio selection, which requires only finite first moments and accommodates non-normal return distributions. However, downside risk measures - such as tail variance - are generally considered more appropriate for capturing risk managers' risk preference than symmetric measures like variance or Gini. In response, we introduce a novel portfolio optimization framework based on a downside risk metric: the tail Gini. In the first part of the paper, we develop the mean-tail Gini (MTG) efficient frontier. Under the assumption of left-tail exchangeability, we derive closed-form solutions for the optimal portfolio weights corresponding to given expected returns. In the second part, we conduct an empirical study of the mean-tail variance (MTV) and MTG frontiers using data from equity and cryptocurrency markets. By fitting the empirical data to a generalized Pareto distribution, the estimated tail indices provide evidence of infinite-variance distributions in the cryptocurrency market. Additionally, the MTG approach demonstrates superior performance over MTV strategy by mitigating the amplification distortions induced by $\mathrm{L}^2$-norm risk measures. The MTG framework helps avoid overly aggressive investment strategies, thereby reducing exposure to unforeseen losses. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.17225 |
| By: | Kairan Hong; Jinling Gan; Qiushi Tian; Yanglinxuan Guo; Rui Guo; Runnan Li |
| Abstract: | Cryptocurrency markets present unique prediction challenges due to their extreme volatility, 24/7 operation, and hypersensitivity to news events, with existing approaches suffering from key information extraction and poor sideways market detection critical for risk management. We introduce a theoretically-grounded multi-agent cryptocurrency trend prediction framework that advances the state-of-the-art through three key innovations: (1) an information-preserving news analysis system with formal theoretical guarantees that systematically quantifies market impact, regulatory implications, volume dynamics, risk assessment, technical correlation, and temporal effects using large language models; (2) an adaptive volatility-conditional fusion mechanism with proven optimal properties that dynamically combines news sentiment and technical indicators based on market regime detection; (3) a distributed multi-agent coordination architecture with low communication complexity enabling real-time processing of heterogeneous data streams. Comprehensive experimental evaluation on Bitcoin across three prediction horizons demonstrates statistically significant improvements over state-of-the-art natural language processing baseline, establishing a new paradigm for financial machine learning with broad implications for quantitative trading and risk management systems. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.08268 |
| By: | Giovanni Bonaccolto (Department of Economics and Law, ``Kore" University of Enna, Italy); Sayar Karmakar (Department of Statistics, University of Florida, USA); Elie Bouri (Adnan Kassar School of Business, Lebanese American University, Lebanon); Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa) |
| Abstract: | Previous studies examine spillover effects across the volatility of several cryptocurrencies in the mean or across quantiles without addressing the issue of high dimensionality. Using a large dataset of 50 cryptocurrencies, we employ a LASSO-regularized Quantile VAR framework and show that spillover effects differ across low, medium, and high volatility regimes, especially when evaluated dynamically over time, with sharp increases around tail events such as the war in Ukraine. Importantly, we demonstrate that the LASSO-QVAR model delivers statistically significant forecasting improvements over its univariate counterpart, underscoring the role of interconnectedness in enhancing volatility prediction across cryptocurrencies. |
| Keywords: | Cryptocurrencies, Volatility, LASSO Quantile VAR, Spillovers; Forecasting |
| JEL: | C32 C53 G10 G17 |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:pre:wpaper:202538 |
| By: | Sergio Bianchi; Daniele Angelini |
| Abstract: | Volatility is the canonical measure of financial risk, a role largely inherited from Modern Portfolio Theory. Yet, its universality rests on restrictive efficiency assumptions that render volatility, at best, an incomplete proxy for true risk. This paper identifies three fundamental inconsistencies: (i) volatility is path-independent and blind to temporal dependence and non-stationarity; (ii) its relevance collapses in derivative-intensive strategies, where volatility often represents opportunity rather than risk; and (iii) it lacks an absolute benchmark, providing no guidance on what level of volatility is economically ``fair'' in efficient markets. To address these limitations, we propose a new paradigm that reconceptualizes risk in terms of predictability rather than variability. Building on a general class of stochastic processes, we derive an analytical link between volatility and the Hurst-Holder exponent within the Multifractional Process with Random Exponent (MPRE) framework. This relationship yields a formal definition of ``fair volatility'', namely the volatility implied under market efficiency, where prices follow semi-martingale dynamics. Extensive empirical analysis on global equity indices supports this framework, showing that deviations from fair volatility provide a tractable measure of market inefficiency, distinguishing between momentum-driven and mean-reverting regimes. Our results advance both the theoretical foundations and empirical assessment of financial risk, offering a definition of volatility that is efficiency-consistent and economically interpretable. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.18837 |
| By: | Arthur Charpentier; Philipp Ratz |
| Abstract: | Over the past decade alternatives to traditional insurance and banking have grown in popularity. The desire to encourage local participation has lead products such as peer-to-peer insurance, reciprocal contracts, and decentralized finance platforms to increasingly rely on network structures to redistribute risk among participants. In this paper, we develop a comprehensive framework for linear risk sharing (LRS), where random losses are reallocated through nonnegative linear operators which can accommodate a wide range of networks. Building on the theory of stochastic and doubly stochastic matrices, we establish conditions under which constraints such as budget balance, fairness, and diversification are guaranteed. The convex order framework allows us to compare different allocations rigorously, highlighting variance reduction and majorization as natural consequences of doubly stochastic mixing. We then extend the analysis to network-based sharing, showing how their topology shapes risk outcomes in complete, star, ring, random, and scale-free graphs. A second layer of randomness, where the sharing matrix itself is random, is introduced via Erd\H{o}s--R\'enyi and preferential-attachment networks, connecting risk-sharing properties to degree distributions. Finally, we study convex combinations of identity and network-induced operators, capturing the trade-off between self-retention and diversification. Our results provide design principles for fair and efficient peer-to-peer insurance and network-based risk pooling, combining mathematical soundness with economic interpretability. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.21411 |
| By: | Yanran Wu; Xinlei Zhang; Quanyi Xu; Qianxin Yang; Chao Zhang |
| Abstract: | We build a 167-indicator comprehensive credit risk indicator set, integrating macro, corporate financial, bond-specific indicators, and for the first time, 30 large-scale corporate non-financial indicators. We use seven machine learning models to construct a bond credit spread prediction model, test their spread predictive power and economic mechanisms, and verify their credit rating prediction effectiveness. Results show these models outperform Chinese credit rating agencies in explaining credit spreads. Specially, adding non-financial indicators more than doubles their out-of-sample performance vs. traditional feature-driven models. Mechanism analysis finds non-financial indicators far more important than traditional ones (macro-level, financial, bond features)-seven of the top 10 are non-financial (e.g., corporate governance, property rights nature, information disclosure evaluation), the most stable predictors. Models identify high-risk traits (deteriorating operations, short-term debt, higher financing constraints) via these indicators for spread prediction and risk identification. Finally, we pioneer a credit rating model using predicted spreads (predicted implied rating model), with full/sub-industry models achieving over 75% accuracy, recall, F1. This paper provides valuable guidance for bond default early warning, credit rating, and financial stability. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.19042 |
| By: | Oliver Slumbers; Benjamin Patrick Evans; Sumitra Ganesh; Leo Ardon |
| Abstract: | Game theory has traditionally had a relatively limited view of risk based on how a player's expected reward is impacted by the uncertainty of the actions of other players. Recently, a new game-theoretic approach provides a more holistic view of risk also considering the reward-variance. However, these variance-based approaches measure variance of the reward on both the upside and downside. In many domains, such as finance, downside risk only is of key importance, as this represents the potential losses associated with a decision. In contrast, large upside "risk" (e.g. profits) are not an issue. To address this restrictive view of risk, we propose a novel solution concept, downside risk aware equilibria (DRAE) based on lower partial moments. DRAE restricts downside risk, while placing no restrictions on upside risk, and additionally, models higher-order risk preferences. We demonstrate the applicability of DRAE on several games, successfully finding equilibria which balance downside risk with expected reward, and prove the existence and optimality of this equilibria. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.03446 |
| By: | Leonardo N. Ferreira; Haroon Mumtaz; Ana Skoblar |
| Abstract: | This paper introduces a Bayesian vector autoregression (BVAR) with stochastic volatility-in-mean and time-varying skewness. Unlike previous approaches, the proposed model allows both volatility and skewness to directly affect macroeconomic variables. We provide a Gibbs sampling algorithm for posterior inference and apply the model to quarterly data for the US and the UK. Empirical results show that skewness shocks have economically significant effects on output, inflation and spreads, often exceeding the impact of volatility shocks. In a pseudo-real-time forecasting exercise, the proposed model outperforms existing alternatives in many cases. Moreover, the model produces sharper measures of tail risk, revealing that standard stochastic volatility models tend to overstate uncertainty. These findings highlight the importance of incorporating time-varying skewness for capturing macro-financial risks and improving forecast performance. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.08415 |
| By: | Emiel Sanders; Rudi Vander Vennet (-) |
| Abstract: | How does geopolitical risk affect banks and their lending behavior? Using the attack of Russia on Ukraine in February 2022 as an unanticipated geopolitical risk event and exploiting the syndicated loan exposures of European banks, we document that Russia-exposed banks experience a more pronounced increase of their cost of equity compared to banks with limited Russian lending exposure. In a difference-in-differences setup, we find that Russia-exposed banks significantly curtail their syndicated lending and that this contraction is most pronounced for lending to new borrowers and unsecured loans. We find no relationship between (changes in) the cost of equity of banks and their credit supply. We conclude that geopolitical risk shocks affect banks’ risk profiles and may cause a contraction in lending. Hence, geopolitical risk is a relevant concern for bank supervisors. |
| Keywords: | Geopolitical risk; cost of equity; syndicated lending |
| JEL: | E51 G21 |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:rug:rugwps:25/1122 |
| By: | Ava C. Blake; Nivika A. Gandhi; Anurag R. Jakkula |
| Abstract: | Accurate prediction of financial market volatility is critical for risk management, derivatives pricing, and investment strategy. In this study, we propose a multitude of regime-switching methods to improve the prediction of S&P 500 volatility by capturing structural changes in the market across time. We use eleven years of SPX data, from May 1st, 2014 to May 27th, 2025, to compute daily realized volatility (RV) from 5-minute intraday log returns, adjusted for irregular trading days. To enhance forecast accuracy, we engineered features to capture both historical dynamics and forward-looking market sentiment across regimes. The regime-switching methods include a soft Markov switching algorithm to estimate soft-regime probabilities, a distributional spectral clustering method that uses XGBoost to assign clusters at prediction time, and a coefficient-based soft regime algorithm that extracts HAR coefficients from time segments segmented through the Mood test and clusters through Bayesian GMM for soft regime weights, using XGBoost to predict regime probabilities. Models were evaluated across three time periods--before, during, and after the COVID-19 pandemic. The coefficient-based clustering algorithm outperformed all other models, including the baseline autoregressive model, during all time periods. Additionally, each model was evaluated on its recursive forecasting performance for 5- and 10-day horizons during each time period. The findings of this study demonstrate the value of regime-aware modeling frameworks and soft clustering approaches in improving volatility forecasting, especially during periods of heightened uncertainty and structural change. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.03236 |
| By: | Natalia Fischl-Lanzoni; Martin Hiti; Asani Sarkar |
| Abstract: | The bank run that started in March 2023 in the U.S. occurred at an unusually rapid pace, suggesting that depositors were surprised by these events. Given that public data revealed bank vulnerabilities as early as 2022:Q1, were other market participants also surprised? In this post, based on a recent paper, we develop a new, high-frequency measure of bank balance sheet risk to examine how stock market investors’ risk sensitivity evolved around the run. We find that stock market investors only became attentive to bank risk after the run and only to the risk of a limited number (less than one-third) of publicly traded banks. Surprisingly, investors seem to have mostly focused on media exposure and not fundamentals when evaluating bank risk. In a companion post, we examine how the Federal Reserve’s liquidity support affected investor risk perceptions. |
| Keywords: | bank runs; bank balance sheets; investor attention; bank liquidity; emergency lending |
| JEL: | E50 G11 G21 |
| Date: | 2025–09–30 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fednls:101878 |
| By: | Yousef Adeli Sadabad; Mohammad Reza Hesamzadeh; Gyorgy Dan; Matin Bagherpour; Darryl R. Biggar |
| Abstract: | The System Price (SP) of the Nordic electricity market serves as a key reference for financial hedge contracts such as Electricity Price Area Differentials (EPADs) and other risk management instruments. Therefore, the identification of drivers and the accurate forecasting of SP are essential for market participants to design effective hedging strategies. This paper develops a systematic framework that combines interpretable drivers analysis with robust forecasting methods. It proposes an interpretable feature engineering algorithm to identify the main drivers of the Nordic SP based on a novel combination of K-means clustering, Multiple Seasonal-Trend Decomposition (MSTD), and Seasonal Autoregressive Integrated Moving Average (SARIMA) model. Then, it applies principal component analysis (PCA) to the identified data matrix, which is adapted to the downstream task of price forecasting to mitigate the issue of imperfect multicollinearity in the data. Finally, we propose a multi-forecast selection-shrinkage algorithm for Nordic SP forecasting, which selects a subset of complementary forecast models based on their bias-variance tradeoff at the ensemble level and then computes the optimal weights for the retained forecast models to minimize the error variance of the combined forecast. Using historical data from the Nordic electricity market, we demonstrate that the proposed approach outperforms individual input models uniformly, robustly, and significantly, while maintaining a comparable computational cost. Notably, our systematic framework produces superior results using simple input models, outperforming the state-of-the-art Temporal Fusion Transformer (TFT). Furthermore, we show that our approach also exceeds the performance of several well-established practical forecast combination methods. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.18887 |
| By: | Chiara Mio (Venice School of Management, Università Ca' Foscari Venice); Nicolas Canestraro (Venice School of Management, Università Ca' Foscari Venice); Antonio Costantini (Venice School of Management, Università Ca' Foscari Venice) |
| Abstract: | This article reviews the academic literature on corporate risk disclosure, focusing on nonfinancial risks in the European regulatory context, particularly considering the Non-Financial Reporting Directive (NFRD) and Corporate Sustainability Reporting Directive (CSRD). Through a systematic review of 140 scientific papers, this study pinpoints key drivers and trends in corporate risk disclosure, such as regulatory compliance, stakeholder pressure, and emerging technologies. Our literature review suggests that while the NFRD has engendered an improvement in the quality and quantity of non- financial risk reporting, firms still tend to focus on past and present risks, with limited forward-looking or negative risk information. Furthermore, this article underscores gaps in current literature, such as the lack of focus on developing countries, financial-sector companies, and the infrequent use of qualitative research methodologies. The paper concludes by recommending a multitheoretical framework and further investigation into the usefulness of non-financial risk disclosures for investors and other stakeholders. |
| Keywords: | risk disclosure, risk reporting, non-financial risks, Non-Financial Reporting Directive, Corporate Sustainability Reporting Directive |
| JEL: | M49 |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:vnm:wpdman:216 |
| By: | Moawia Alghalith (UWI, St Augustine); Wing-Keung Wong (Department of Finance, Fintech Center, and Big Data Research Center, Asia University; Department of Medical Research, China Medical University Hospital, Taiwan; Business, Economic and Public Policy Research Centre, Hong Kong Shue Yan University; The Economic Growth Centre, Nanyang Technological University) |
| Abstract: | We provide an accurate, simple formula for pricing multidimensional European options. The formula is as simple as the Black-Scholes formula. Therefore, the (costly) computational methods are needless. Moreover, our method allows the calculation of the implied volatility of the underlying asset of a multidimensional option. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:nan:wpaper:2505 |
| By: | José Fique; Xisong Jin |
| Abstract: | We develop a structural framework for system-wide financial stress testing with multiple interacting contagion and amplification effects acting through a dual channel of liquidity and solvency risk. The framework allows us to identify vulnerabilities arising from the increasingly intricate and complex financial system of banks and investment funds in Luxembourg. Based on exogenous shocks stemming from hypothetical adverse scenarios, several important findings are documented for banks and three types of investment funds (Bond Funds, Equity Funds and Mixed Funds) during 2020-2023. First, the simulated shocks have significant first-round and higher-order effects on investment funds, in particular on Equity Funds. Moreover, Bond Funds display a stronger amplification factor than other types of investment funds. Second, the impact on Luxembourg banks is substantially muted. The overall bank capital depletion, measured by the total risk exposure amount, is low even in view of the tail risk metrics, which reflects the strong resilience of the Luxembourg banking sector as a whole. Third, for both investment funds and banks, their vulnerabilities still reflect the procyclicality of the financial system. Overall, the joint modelling of banks and non-banks delivers clear benefits to the analytical capabilities of central banks and informs policymakers in developing the non-bank macroprudential toolkit of the future. |
| Keywords: | Financial stability, systemic risk, macro-prudential policy, fire sales, banking business model, stress testing, ; liquidity, macro-financial linkages. |
| JEL: | D85 G01 G21 G23 L14 |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:bcl:bclwop:bclwp199 |
| By: | Hwang, Joon; Alam, Nurul; Shenk, Mary K (The Pennsylvania State University) |
| Abstract: | Throughout human evolutionary history, individuals have faced two fundamental challenges under uncertainty: deciding whether to take risks and managing risks through cooperation. While both risk-taking and social risk management have been widely studied, less attention has been given to how these two processes are linked—specifically, how risk-taking itself may be shaped by social networks. We test the "social capital buffer" hypothesis, which posits that greater social connectedness promotes risk-taking by buffering against negative outcomes. Analyzing social networks and risk preferences among 140 individuals in rural Bangladesh whose livelihoods range from farming to wage labor and small-scale trade, we identify distinct pathways through which social capital influences risk preference. Highly clustered individuals in financial support networks exhibit greater risk preference, suggesting that clustering facilitates risk-taking by ensuring resource circulation within a tight-knit group. In contrast, individuals with more support-receiving ties in material support networks are more risk-averse, indicating that material support functions as informal social insurance reducing reliance on risky decisions. Finally, reciprocity in material support networks promotes risk-taking only among wealthier individuals, highlighting how individual economic resources interact with social capital to shape risk-taking. These findings reveal that social capital does not uniformly promote or constrain risk-taking but serves distinct adaptive functions based on network structure, economic conditions, and resource types, balancing risk-taking and risk-avoidance to help individuals successfully navigate uncertainty. |
| Date: | 2025–09–27 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:bxt8g_v1 |
| By: | Evan Heus; Rick Bookstaber; Dhruv Sharma |
| Abstract: | Large Language Models (LLMs) struggle with the complex, multi-modal, and network-native data underlying financial risk. Standard Retrieval-Augmented Generation (RAG) oversimplifies relationships, while specialist models are costly and static. We address this gap with an LLM-centric agent framework for supply chain risk analysis. Our core contribution is to exploit the inherent duality between networks and knowledge graphs (KG). We treat the supply chain network as a KG, allowing us to use structural network science principles for retrieval. A graph traverser, guided by network centrality scores, efficiently extracts the most economically salient risk paths. An agentic architecture orchestrates this graph retrieval alongside data from numerical factor tables and news streams. Crucially, it employs novel ``context shells'' -- descriptive templates that embed raw figures in natural language -- to make quantitative data fully intelligible to the LLM. This lightweight approach enables the model to generate concise, explainable, and context-rich risk narratives in real-time without costly fine-tuning or a dedicated graph database. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.01115 |
| By: | Ivan Guo; Jan Ob\l\'oj |
| Abstract: | We consider the robust pricing and hedging of American options in a continuous time setting. We assume asset prices are continuous semimartingales, but we allow for general model uncertainty specification via adapted closed convex constraints on the volatility. We prove the robust pricing-hedging duality. When European options with given prices are available for static trading, we show that duality holds against richer models where these options are traded dynamically. Our proofs rely on probabilistic treatment of randomised stopping times and suitable measure decoupling, and on optimal transport duality. In addition, similarly to the approach of Aksamit et al. (2019) in discrete time, we identify American options with European options on an enlarged space. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.05463 |
| By: | Jinho Cha; Long Pham; Thi Le Hoa Vo; Jaeyoung Cho; Jaejin Lee |
| Abstract: | This study develops an inverse portfolio optimization framework for recovering latent investor preferences including risk aversion, transaction cost sensitivity, and ESG orientation from observed portfolio allocations. Using controlled synthetic data, we assess the estimator's statistical properties such as consistency, coverage, and dynamic regret. The model integrates robust optimization and regret-based inference to quantify welfare losses under preference misspecification and market shocks. Simulation experiments demonstrate accurate recovery of transaction cost parameters, partial identifiability of ESG penalties, and sublinear regret even under stochastic volatility and liquidity shocks. A real-data illustration using ETFs confirms that transaction-cost shocks dominate volatility shocks in welfare impact. The framework thus provides a statistically rigorous and economically interpretable tool for robust preference inference and portfolio design under uncertainty. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.06986 |
| By: | Kosuke Aoki (BANCO DE ESPAÑA); Enric Martorell (BANCO DE ESPAÑA); Kalin Nikolov (BANCO DE ESPAÑA) |
| Abstract: | We examine the interplay between monetary policy, bank risk-taking, and financial stability in a quantitative macroeconomic model with endogenous risk-taking by banks and systemic crises. Banks’ access to leverage depends on their charter value, which is itself affected by movements in the real interest rate. We find that permanent shifts in the long-term real interest rate have a significant impact on banks’ leverage and on their investments in systemically risky assets, while transitory movements have a more limited impact. We show that in the presence of systemic risk-taking, the systemic component of monetary policy faces a trade-off between price stability and financial stability. A moderate reaction to inflation deviations from the target is optimal, as it sustains banks’ equity value after financial crises. Seeking price stability reduces inflation volatility but leads to increased systemic risk-taking and more severe financial recessions. The optimal central bank policy combination involves an increase in regulatory bank capital requirements coupled with a moderate reaction of monetary policy to inflation. |
| Keywords: | financial intermediation, monetary policy, systemic risk, macroprudential policy |
| JEL: | E44 E52 E58 G21 |
| Date: | 2025–03 |
| URL: | https://d.repec.org/n?u=RePEc:bde:wpaper:2517 |
| By: | Samuel N. Cohen; Cephas Svosve |
| Abstract: | We explore a link between stochastic volatility (SV) and path-dependent volatility (PDV) models. Using assumed density filtering, we map a given SV model into a corresponding PDV representation. The resulting specification is lightweight, improves in-sample fit, and delivers robust out-of-sample forecasts. We also introduce a calibration procedure for both SV and PDV models that produces standard errors for parameter estimates and supports joint calibration of SPX/VIX smile. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.02024 |
| By: | Jinho Cha; Long Pham; Thi Le Hoa Vo; Jaeyoung Cho; Jaejin Lee |
| Abstract: | This study develops and analyzes an optimization model of smart contract adoption under bounded risk, linking structural theory with simulation and real-world validation. We examine how adoption intensity alpha is structurally pinned at a boundary solution, invariant to variance and heterogeneity, while profitability and service outcomes are variance-fragile, eroding under volatility and heavy-tailed demand. A sharp threshold in the fixed cost parameter A3 triggers discontinuous adoption collapse (H1), variance shocks reduce profits monotonically but not adoption (H2), and additional results on readiness heterogeneity (H3), profit-service co-benefits (H4), and distributional robustness (H5) confirm the duality between stable adoption and fragile payoffs. External validity checks further establish convergence of sample average approximation at the canonical O(1/sqrt(N)) rate (H6). Empirical validation using S&P 500 returns and the MovieLens100K dataset corroborates the theoretical structure: bounded and heavy-tailed distributions fit better than Gaussian models, and profits diverge across volatility regimes even as adoption remains stable. Taken together, the results demonstrate that adoption choices are robust to uncertainty, but their financial consequences are highly fragile. For operations and finance, this duality underscores the need for risk-adjusted performance evaluation, option-theoretic modeling, and distributional stress testing in strategic investment and supply chain design. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.07006 |
| By: | Jian'an Zhang |
| Abstract: | We introduce Tail-Safe, a deployability-oriented framework for derivatives hedging that unifies distributional, risk-sensitive reinforcement learning with a white-box control-barrier-function (CBF) quadratic-program (QP) safety layer tailored to financial constraints. The learning component combines an IQN-based distributional critic with a CVaR objective (IQN--CVaR--PPO) and a Tail-Coverage Controller that regulates quantile sampling through temperature tilting and tail boosting to stabilize small-$\alpha$ estimation. The safety component enforces discrete-time CBF inequalities together with domain-specific constraints -- ellipsoidal no-trade bands, box and rate limits, and a sign-consistency gate -- solved as a convex QP whose telemetry (active sets, tightness, rate utilization, gate scores, slack, and solver status) forms an auditable trail for governance. We provide guarantees of robust forward invariance of the safe set under bounded model mismatch, a minimal-deviation projection interpretation of the QP, a KL-to-DRO upper bound linking per-state KL regularization to worst-case CVaR, concentration and sample-complexity results for the temperature-tilted CVaR estimator, and a CVaR trust-region improvement inequality under KL limits, together with feasibility persistence under expiry-aware tightening. Empirically, in arbitrage-free, microstructure-aware synthetic markets (SSVI $\to$ Dupire $\to$ VIX with ABIDES/MockLOB execution), Tail-Safe improves left-tail risk without degrading central performance and yields zero hard-constraint violations whenever the QP is feasible with zero slack. Telemetry is mapped to governance dashboards and incident workflows to support explainability and auditability. Limitations include reliance on synthetic data and simplified execution to isolate methodological contributions. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.04555 |
| By: | An Pham Ngoc Nguyen; Marija Bezbradica; Martin Crane |
| Abstract: | As global financial markets become increasingly interconnected, financial contagion has developed into a major influencer of asset price dynamics. Motivated by this context, our study explores financial contagion both within and between asset communities. We contribute to the literature by examining the contagion phenomenon at the community level rather than among individual assets. Our experiments rely on high-frequency data comprising cryptocurrencies, stocks and US ETFs over the 4-year period from April 2019 to May 2023. Using the Louvain community detection algorithm, Vector Autoregression contagion detection model and Tracy-Widom random matrix theory for noise removal from financial assets, we present three main findings. Firstly, while the magnitude of contagion remains relatively stable over time, contagion density (the percentage of asset pairs exhibiting contagion within a financial system) increases. This suggests that market uncertainty is better characterized by the transmission of shocks more broadly than by the strength of any single spillover. Secondly, there is no significant difference between intra- and inter-community contagion, indicating that contagion is a system-wide phenomenon rather than being confined to specific asset groups. Lastly, certain communities themselves, especially those dominated by Information Technology assets, consistently appear to act as major contagion transmitters in the financial network over the examined period, spreading shocks with high densities to many other communities. Our findings suggest that traditional risk management strategies such as portfolio diversification through investing in low-correlated assets or different types of investment vehicle might be insufficient due to widespread contagion. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.15232 |
| By: | Agnes Tomini (Aix-Marseille Univ., CNRS, AMSE, Marseille, France) |
| Abstract: | This paper extends the standard two-period prevention model by incorporating anticipatory emotions. We introduce an additional cost, referred as the emotional load, which is endogenously determined by future risk but can be mitigated by current preventive effort. We show that a more intense emotional load incentivizes the emotional agent to increase investment in either self-insurance or self-protection. By contrast, greater uncertainty sensitivity has an ambiguous effect: It depends on the curvature of the emotional load function and wealth. When savings are substitutes, the effect of these parameters may diverge, whereas they align when savings are complements to risk prevention. Finally contrasting our setting with a setting without uncertainty or emotions, we show that, under prudence, the introduction of a zero-mean risk leads to a higher optimal level of self-insurance. Anxiety amplifies the incentive to reduce risk by lowering present well-being. |
| Keywords: | Self-insurance, Self-protection, Anticipatory emotions, uncertainty |
| JEL: | D15 D81 D91 G22 |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:aim:wpaimx:2514 |
| By: | Jian'an Zhang |
| Abstract: | We formulate option market making as a constrained, risk-sensitive control problem that unifies execution, hedging, and arbitrage-free implied-volatility surfaces inside a single learning loop. A fully differentiable eSSVI layer enforces static no-arbitrage conditions (butterfly and calendar) while the policy controls half-spreads, hedge intensity, and structured surface deformations (state-dependent rho-shift and psi-scale). Executions are intensity-driven and respond monotonically to spreads and relative mispricing; tail risk is shaped with a differentiable CVaR objective via the Rockafellar--Uryasev program. We provide theory for (i) grid-consistency and rates for butterfly/calendar surrogates, (ii) a primal--dual grounding of a learnable dual action acting as a state-dependent Lagrange multiplier, (iii) differentiable CVaR estimators with mixed pathwise and likelihood-ratio gradients and epi-convergence to the nonsmooth objective, (iv) an eSSVI wing-growth bound aligned with Lee's moment constraints, and (v) policy-gradient validity under smooth surrogates. In simulation (Heston fallback; ABIDES-ready), the agent attains positive adjusted P\&L on most intraday segments while keeping calendar violations at numerical zero and butterfly violations at the numerical floor; ex-post tails remain realistic and can be tuned through the CVaR weight. The five control heads admit clear economic semantics and analytic sensitivities, yielding a white-box learner that unifies pricing consistency and execution control in a reproducible pipeline. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.04569 |
| By: | Thomas T. Yang |
| Abstract: | We revisit tail-index regressions. For linear specifications, we find that the usual full-rank condition can fail because conditioning on extreme outcomes causes regressors to degenerate to constants. More generally, the conditional distribution of the covariates in the tails concentrates on the values at which the tail index is minimized. Away from those points, the conditional density tends to zero. For local nonparametric tail index regression, the convergence rate can be very slow. We conclude with practical suggestions for applied work. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.01535 |
| By: | Antonio Penta; Larbi Alaoui |
| Abstract: | We revisit the long-lasting debate about the meaning of the utility function used in the standard Expected Utility (EU) model. Despite the common view that EU forces risk aversion and diminishing marginal utility of wealth to be pegged to one another, here we show that this is not the case. Marginal utility for money is an input into risk attitude, but it is not its sole determinant. The attitude towards ‘pure risk’ is also a contributing factor, and it is independent from the former. We discuss several theoretical implications of this result, for the following topics: (i) non-neutral risk attitudes for profit maximizing firms; (ii) risk-aversion over time lotteries in the presence of discounting; (iii) the equity premium puzzle. We also discuss matters of identification: (i) for firms; (ii) via proxies ; (iii) via standard MLE-methods under parametric restrictions; and (iv) cross-context elicitation in multi-dimensional settings, and its relationship with the methods and results from the psychology literature. |
| Keywords: | utility function, risk-aversion, marginal utility |
| JEL: | C72 C91 C92 D80 D91 |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:upf:upfgen:1909 |
| By: | Thomas Michael Pugh; Saarah Sheikh; Taylor Webley |
| Abstract: | Household savings in Canada have increased significantly since 2019, especially among homeowners without a mortgage. We assess how savings buffers can mitigate households’ financial risk in relation to asset repricing, mortgage payment renewal and unemployment. |
| Keywords: | Credit and credit aggregates; Financial stability; Housing; Recent economic and financial developments |
| JEL: | D3 D31 E2 E21 G5 G51 |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:bca:bocsan:25-23 |
| By: | Wing-Keung Wong (Department of Finance, Fintech Center, and Big Data Research Center, Asia University; Department of Medical Research, China Medical University Hospital, Taiwan; Business, Economic and Public Policy Research Centre, Hong Kong Shue Yan University; The Economic Growth Centre, Nanyang Technological University); Chenghu Ma (Fudan University); Zhuo Qiao (Faculty of Business Administration, University of Macau); Udo Broll (Dresden University of Technology); Joao Paulo Vieito (Polytechnic Institute of Viana do Castelo) |
| Abstract: | In this paper, we first state some well-known problems including the Friedman-Savage paradox raised by Friedman and Savage (1948) who wonder why individuals would like to buy insurance as well as buy lottery tickets. To provide solutions to the problems, we first use the idea from Fishburn and Kochenberger (1979), Thon and Thorlund-Petersen (1988), and Chew and Tan (2005) to use two-way stochastic dominance to define the j-order risk-averse and risk-seeking utility that consists of both risk-averse and risk-seeking components and we call the utility AD utility and call investors with AD utility AD investors. Thereafter, we develop a new stochastic dominance theory for AD investors and we call the theory ADSD theory. We then develop some properties for the ADSD theory, including properties of expected-utility maximization, hierarchy, transitivity, and diversification, and properties under the additional condition of equal mean so that we can use the theory to get the solutions for all the problems and hypotheses we set in this paper. Applying the ADSD theory, we first get a new solution for the Friedman-Savage paradox. In addition, we find that AD investors could invest in both completely diversified portfolio and individual assets and, in general, buy any pair of both less-risky and more-risky assets. For example, AD investors could invest in both bonds and stocks, both bonds and futures, and both stocks and futures to get higher expected utility. |
| Keywords: | Stochastic Dominance; Risk Aversion; Risk Seeking; Utility Function; riskier Asset; Less Risky Asset |
| JEL: | D81 G11 |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:nan:wpaper:2506 |
| By: | Matt Brigida |
| Abstract: | Research has shown banks match interest income and expense betas, and thereby obtain net interest income margins which are insensitive to changes in short-term interest rates. The present analysis extends this research in a number of ways. First, we use state-space methods to estimate time-varying betas and test whether they are matched at each time interval. We find substantial variation in interest income and expense betas, which drives variation in net interest margin beta coefficients. Second, we estimate the time-varying conditional volatility of beta forecasts the uncertainty of future beta values. We find uncertainty in interest expense beta coefficients drives uncertainty in interest income betas. Further, large banks have greater expense beta uncertainty, whereas small banks have greater income beta uncertainty. Lastly, we find evidence that uncertainty in interest expense betas is priced by the market, and is negatively related to bank stock prices. This is a new and previously unmeasured source of unhedgeable risk in bank stocks, and highlights an additional benefit of the Federal Reserve's Zero Interest Rate Policy. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.07671 |
| By: | Sid Ghatak; Arman Khaledian; Navid Parvini; Nariman Khaledian |
| Abstract: | There are inefficiencies in financial markets, with unexploited patterns in price, volume, and cross-sectional relationships. While many approaches use large-scale transformers, we take a domain-focused path: feed-forward and recurrent networks with curated features to capture subtle regularities in noisy financial data. This smaller-footprint design is computationally lean and reliable under low signal-to-noise, crucial for daily production at scale. At Increase Alpha, we built a deep-learning framework that maps over 800 U.S. equities into daily directional signals with minimal computational overhead. The purpose of this paper is twofold. First, we outline the general overview of the predictive model without disclosing its core underlying concepts. Second, we evaluate its real-time performance through transparent, industry standard metrics. Forecast accuracy is benchmarked against both naive baselines and macro indicators. The performance outcomes are summarized via cumulative returns, annualized Sharpe ratio, and maximum drawdown. The best portfolio combination using our signals provides a low-risk, continuous stream of returns with a Sharpe ratio of more than 2.5, maximum drawdown of around 3\%, and a near-zero correlation with the S\&P 500 market benchmark. We also compare the model's performance through different market regimes, such as the recent volatile movements of the US equity market in the beginning of 2025. Our analysis showcases the robustness of the model and significantly stable performance during these volatile periods. Collectively, these findings show that market inefficiencies can be systematically harvested with modest computational overhead if the right variables are considered. This report will emphasize the potential of traditional deep learning frameworks for generating an AI-driven edge in the financial market. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.16707 |
| By: | Benjamin Mosk; Nander de Vette |
| Abstract: | This paper investigates the phenomenon of financial fragmentation within the euro area and focuses on its implications for bond market stability. A three-step approach is used to assess the sensitivity of credit risk premiums to identified global risk shocks, distinguishing between regimes of higher and lower fragmentation. First, a time-varying indicator of euro area financial fragmentation is constructed on the basis of a principal component analysis of sovereign yield changes. The indicator reflects the extent to which yields across different country groupings—often characterized by differing structural and financial market conditions—move in opposite directions. Second, we construct a series of identified global risk shocks using a signrestricted Bayesian vector auto-regression model applied to a set of financial market variables. Third, we assess bond market stability/fragility in terms of the responsiveness of credit risk premiums to global risk shocks, using a non-linear panel local projections method, distinguishing between regimes of higher and lower fragmentation. We find that during times of elevated fragmentation, both sovereign CDS premiums and corporate option-adjusted spreads react more strongly to a given global risk shock. This elevated sensitivity appears across both country groupings, suggesting that in the higher-fragmentation regime, bond markets are more vulnerable throughout the euro area. These findings indicate that efforts to strengthen financial integration could contribute to greater bond market resilience. |
| Keywords: | financial fragmentation; credit risk premiums |
| Date: | 2025–09–26 |
| URL: | https://d.repec.org/n?u=RePEc:imf:imfwpa:2025/194 |
| By: | Giovanni Cerulli; Francesco Caracciolo |
| Abstract: | This paper develops a risk-adjusted alternative to standard optimal policy learning (OPL) for observational data by importing Roy's (1952) safety-first principle into the treatment assignment problem. We formalize a welfare functional that maximizes the probability that outcomes exceed a socially required threshold and show that the associated pointwise optimal rule ranks treatments by the ratio of conditional means to conditional standard deviations. We implement the framework using microdata from the Italian Farm Accountancy Data Network to evaluate the allocation of subsidies under the EU Common Agricultural Policy. Empirically, risk-adjusted optimal policies systematically dominate the realized allocation across specifications, while risk aversion lowers overall welfare relative to the risk-neutral benchmark, making transparent the social cost of insurance against uncertainty. The results illustrate how safety-first OPL provides an implementable, interpretable tool for risk-sensitive policy design, quantifying the efficiency-insurance trade-off that policymakers face when outcomes are volatile. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.05007 |
| By: | Mingshu Li; Dhruv Desai; Jerinsh Jeyapaulraj; Philip Sommer; Riya Jain; Peter Chu; Dhagash Mehta |
| Abstract: | Accurately measuring portfolio similarity is critical for a wide range of financial applications, including Exchange-traded Fund (ETF) recommendation, portfolio trading, and risk alignment. Existing similarity measures often rely on exact asset overlap or static distance metrics, which fail to capture similarities among the constituents (e.g., securities within the portfolio) as well as nuanced relationships between partially overlapping portfolios with heterogeneous weights. We introduce STRAPSim (Semantic, Two-level, Residual-Aware Portfolio Similarity), a novel method that computes portfolio similarity by matching constituents based on semantic similarity, weighting them according to their portfolio share, and aggregating results via residual-aware greedy alignment. We benchmark our approach against Jaccard, weighted Jaccard, as well as BERTScore-inspired variants across public classification, regression, and recommendation tasks, as well as on corporate bond ETF datasets. Empirical results show that our method consistently outperforms baselines in predictive accuracy and ranking alignment, achieving the highest Spearman correlation with return-based similarity. By leveraging constituent-aware matching and dynamic reweighting, portfolio similarity offers a scalable, interpretable framework for comparing structured asset baskets, demonstrating its utility in ETF benchmarking, portfolio construction, and systematic execution. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.24151 |