|
on Risk Management |
| By: | Robert Taylor |
| Abstract: | This paper presents the experimental process and results of SVM, Gradient Boosting, and an Attention-GRU Hybrid model in predicting the Implied Volatility of rolled-over five-year spread contracts of credit default swaps (CDS) on European corporate debt during the quarter following mid-May '24, as represented by the iTraxx/Cboe Europe Main 1-Month Volatility Index (BP Volatility). The analysis employs a feature matrix inspired by Merton's determinants of default probability. Our comparative assessment aims to identify strengths in SOTA and classical machine learning methods for financial risk prediction |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.15404 |
| By: | Mario Ghossoub; Michael B. Zhu; Wing Fung Chong |
| Abstract: | We study Pareto optimality in a decentralized peer-to-peer risk-sharing market where agents' preferences are represented by robust distortion risk measures that are not necessarily convex. We obtain a characterization of Pareto-optimal allocations of the aggregate risk in the market, and we show that the shape of the allocations depends primarily on each agent's assessment of the tail of the aggregate risk. We quantify the latter via an index of probabilistic risk aversion, and we illustrate our results using concrete examples of popular families of distortion functions. As an application of our results, we revisit the market for flood risk insurance in the United States. We present the decentralized risk sharing arrangement as an alternative to the current centralized market structure, and we characterize the optimal allocations in a numerical study with historical flood data. We conclude with an in-depth discussion of the advantages and disadvantages of a decentralized insurance scheme in this setting. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2409.05103 |
| By: | Kubitza, Christian |
| Abstract: | Financial losses can have persistent effects on the financial system. This paper proposes an empirical measure for the duration of these effects, Spillover Persistence. I document that Spillover Persistence is strongly correlated with financial conditions; during banking crises, Spillover Persistence is higher, whereas in the run-up phase of stock market bubbles it is lower. Lower Spillover Persistence also associates with a more fragile system, e.g., a higher probability of future crises, consistent with the volatility paradox. The results emphasize the dynamics of loss spillovers as an important dimension of systemic risk and financial constraints as a key determinant of persistence. JEL Classification: E44, G01, G12, G20, G32 |
| Keywords: | asset price bubbles, financial crises, fire sales, fragility, systemic risk |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:ecb:ecbwps:20242981 |
| By: | Vasily Melnikov |
| Abstract: | The abstract theory of risk measures is well-developed for certain classes of solid subspaces of $L^{0}$. We provide an example to illustrate that this framework is insufficient to deal with the subtleties of incomplete markets. To remedy this problem, we consider risk measures on the subspace generated by a closed, absolutely convex, and bounded subset $K\subset L^{0}$, which represents the attainable securities. In this context, we introduce the equicontinuous Fatou property. Under the existence of a certain topology $\tau$ on $\mathrm{span}(K)$, interpreted as a generalized weak-star topology, we obtain an equivalence between the equicontinuous Fatou property, and lower semicontinuity with respect to $\tau$. As a corollary, we obtain tractable dual representations for such risk measures, which subsumes essentially all known results on weak-star representations of risk measures. This dual representation allows one to prove that all risk measures of this form extend, in a maximal way, to the ideal generated by $\mathrm{span}(K)$ while preserving a Fatou-like property. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2409.05194 |
| By: | Zian Wang; Xinyi Lu |
| Abstract: | This paper investigates the forecasting performance of COMEX copper futures realized volatility across various high-frequency intervals using both econometric volatility models and deep learning recurrent neural network models. The econometric models considered are GARCH and HAR, while the deep learning models include RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), and GRU (Gated Recurrent Unit). In forecasting daily realized volatility for COMEX copper futures with a rolling window approach, the econometric models, particularly HAR, outperform recurrent neural networks overall, with HAR achieving the lowest QLIKE loss function value. However, when the data is replaced with hourly high-frequency realized volatility, the deep learning models outperform the GARCH model, and HAR attains a comparable QLIKE loss function value. Despite the black-box nature of machine learning models, the deep learning models demonstrate superior forecasting performance, surpassing the fixed QLIKE value of HAR in the experiment. Moreover, as the forecast horizon extends for daily realized volatility, deep learning models gradually close the performance gap with the GARCH model in certain loss function metrics. Nonetheless, HAR remains the most effective model overall for daily realized volatility forecasting in copper futures. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2409.08356 |
| By: | Di Wu |
| Abstract: | In the context of financial credit risk evaluation, the fairness of machine learning models has become a critical concern, especially given the potential for biased predictions that disproportionately affect certain demographic groups. This study investigates the impact of data preprocessing, with a specific focus on Truncated Singular Value Decomposition (SVD), on the fairness and performance of probability of default models. Using a comprehensive dataset sourced from Kaggle, various preprocessing techniques, including SVD, were applied to assess their effect on model accuracy, discriminatory power, and fairness. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.15452 |
| By: | Sario, Azhar ul Haque |
| Abstract: | This third volume in the “Stock Predictions” series builds on the success of the first edition, “Stock Price Predictions: An Introduction to Probabilistic Models” (ISBN 979-8223912712), and the second edition, “Forecasting Stock Prices: Mathematics of Probabilistic Models” (ISBN 979-8223038993). This new edition delves deeper into the complex world of quantitative finance, providing readers with a comprehensive guide to advanced financial models used in stock price prediction. The book covers a wide array of models, beginning with the foundational concept of Brownian Motion, which represents the random movement of stock prices and underpins many financial models. It then progresses to Geometric Brownian Motion, a model that accounts for the exponential growth often observed in stock prices. Mean Reversion Models are introduced to capture the tendency of stock prices to revert to their long-term average, offering a counterpoint to trend-following strategies. The book explores the world of volatility modeling with GARCH models, which capture the clustering and persistence of volatility in financial markets, crucial for risk management and option pricing. Extensions of GARCH, such as EGARCH and TGARCH, are examined to address the asymmetric impact of positive and negative news on volatility. In the latter part of the book, the focus shifts to Machine Learning, demonstrating how techniques like Support Vector Machines and Neural Networks can uncover complex patterns in financial data and enhance prediction accuracy. Recurrent Neural Networks, particularly LSTMs, are highlighted for their ability to model sequential data, making them ideal for capturing the temporal dynamics of stock prices. Monte Carlo simulations are discussed as a powerful tool for generating a range of possible future outcomes, enabling investors to assess risk and make informed decisions. Finally, Copula Models are introduced to model the dependence structure between multiple assets, critical for portfolio management and risk assessment. Throughout the book, each model is presented with a clear explanation of its mathematical formulation, parameter estimation techniques, and practical applications in stock price prediction. The book emphasizes the strengths and limitations of each model, equipping readers with the knowledge to select the most appropriate model for their specific needs. This book is an invaluable resource for students, researchers, and practitioners in finance and investments seeking to master the quantitative tools used in stock price prediction. With its rigorous yet accessible approach, this book empowers readers to leverage advanced financial models and make informed investment decisions in today’s dynamic markets. The book is based on 95 research studies, which are listed on the references page and uploaded on Harvard University’s Dataverse for transparency. As a published book, it has undergone review for originality. |
| Date: | 2024–09–13 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:pk7w3 |
| By: | Di Wu |
| Abstract: | The year 2024 witnessed a major development in the cryptocurrency industry with the long-awaited approval of spot Bitcoin exchange-traded funds (ETFs). This innovation provides investors with a new, regulated path to gain exposure to Bitcoin through a familiar investment vehicle (Kumar et al., 2024). However, unlike traditional ETFs that directly hold underlying assets, Bitcoin ETFs rely on a creation and redemption process managed by authorized participants (APs). This unique structure introduces distinct characteristics in terms of premium/discount behavior compared to traditional ETFs. This paper investigates the premium and discount patterns observed in Bitcoin ETFs during first four-month period (January 11th, 2024, to May 17th, 2024). Our analysis reveals that these patterns differ significantly from those observed in traditional index ETFs, potentially exposing investors to additional risk factors. By identifying and analyzing these risk factors associated with Bitcoin ETF premiums/discounts, this paper aims to achieve two key objectives: Enhance market understanding: Equip and market and investors with a deeper comprehension of the unique liquidity risks inherent in Bitcoin ETFs. Provide a clearer risk management frameworks: Offer a clearer perspective on the risk-return profile of digital asset ETFs, specifically focusing on Bitcoin ETFs. Through a thorough analysis of premium/discount behavior and the underlying factors contributing to it, this paper strives to contribute valuable insights for investors navigating the evolving landscape of digital asset investments |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2409.00270 |
| By: | Giraldo, Carlos (Latin American Reserve Fund); Giraldo, Iader (Latin American Reserve Fund); Huertas, Cristian (Universidad Nacional de Colombia); Sánchez, Juan Camilo (Dirección de impuestos y aduanas nacionales) |
| Abstract: | This study investigates the determinants of hedging practices among commodity-producing companies in Latin America. The extractive sector's significant economic importance in the region makes understanding these firms' hedging decisions highly relevant. The findings reveal several key insights. Firm size, leverage, and commodity prices are important factors consistent with prior research. Additionally, the region's exchange rate exposure means that firms' acquisition of US dollar-denominated debt is a significant determinant of their hedging activities, as well as the firms’ access to the international markets. Notably, the type of ownership also significantly impacts hedging, as state-owned firms are more likely to hedge to reduce volatility in their revenues for the case of oil-firms. In contrast to the limited research on Latin American extractive firms, an extensive literature has explored hedging strategies in developed countries' extractive companies. This study aims to address the gap by investigating the determinants of hedging practices among commodity-producing companies in Latin America. |
| Keywords: | hedging; risk management; derivatives; commodity-producing companies; |
| JEL: | C23 D81 G30 G32 Q02 |
| Date: | 2024–09–15 |
| URL: | https://d.repec.org/n?u=RePEc:col:000566:021196 |
| By: | Shuochen Bi; Yufan Lian; Ziyue Wang |
| Abstract: | In the financial field of the United States, the application of big data technology has become one of the important means for financial institutions to enhance competitiveness and reduce risks. The core objective of this article is to explore how to fully utilize big data technology to achieve complete integration of internal and external data of financial institutions, and create an efficient and reliable platform for big data collection, storage, and analysis. With the continuous expansion and innovation of financial business, traditional risk management models are no longer able to meet the increasingly complex market demands. This article adopts big data mining and real-time streaming data processing technology to monitor, analyze, and alert various business data. Through statistical analysis of historical data and precise mining of customer transaction behavior and relationships, potential risks can be more accurately identified and timely responses can be made. This article designs and implements a financial big data intelligent risk control platform. This platform not only achieves effective integration, storage, and analysis of internal and external data of financial institutions, but also intelligently displays customer characteristics and their related relationships, as well as intelligent supervision of various risk information |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2409.10331 |
| By: | Lo\"ic Mar\'echal; Nathan Monnet |
| Abstract: | We use a methodology based on a machine learning algorithm to quantify firms' cyber risks based on their disclosures and a dedicated cyber corpus. The model can identify paragraphs related to determined cyber-threat types and accordingly attribute several related cyber scores to the firm. The cyber scores are unrelated to other firms' characteristics. Stocks with high cyber scores significantly outperform other stocks. The long-short cyber risk factors have positive risk premia, are robust to all factors' benchmarks, and help price returns. Furthermore, we suggest the market does not distinguish between different types of cyber risks but instead views them as a single, aggregate cyber risk. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2409.08728 |
| By: | Camélia Sehaqui (Université Hassan 1er [Settat]); Mohamed Haissoune (Université Hassan 1er [Settat]) |
| Abstract: | This article seeks to analyze the application of artificial intelligence (AI) in counterparty risk management, focusing on Moroccan participatory banks. To this end, the authors first examine the reality of AI and its applications in Islamic finance before exploring how it can evaluate and mitigate the risks inherent to these institutions. The qualitative methodology used is based on semi-structured interviews with eight risk directors from Moroccan participatory banks and windows. The interviews were transcribed and subjected to systematic thematic analysis. The coding process identified recurring themes, which were then grouped into broader categories to identify key trends and perceptions about the use of AI in counterparty risk management. The survey results reveal that none of the banks interviewed currently use AI for counterparty risk management, although they intend to introduce it in the future. The expected benefits include increased accuracy in risk assessment and process optimization through automation. However, potential obstacles include financial constraints and a shortage of AI expertise. Indeed, AI could present promising prospects for strengthening financial stability and ensuring Sharia compliance within participatory banks. For effective integration, investments in resources and AI training are necessary. Overall, the future of AI in counterparty risk management promises to bring innovation and operational efficiency to the participatory finance sector. |
| Abstract: | Le présent article cherche à analyser l'application de l'intelligence artificielle (IA) dans la gestion du risque de contrepartie, en se concentrant sur les banques participatives marocaines. Pour ce faire, les auteurs examinent d'abord la réalité de l'IA et ses applications dans la finance islamique avant d'explorer comment elle peut évaluer et atténuer les risques propres à ces institutions. La méthodologie qualitative retenue se base sur des entretiens semi-directifs avec huit directeurs des risques de banques et fenêtres participatives marocaines. Les entretiens ont été transcrits et soumis à une analyse thématique systématique. Le processus de codage a permis d'identifier des thèmes récurrents, regroupés ensuite en catégories plus larges, afin de dégager des tendances et des perceptions clés sur l'utilisation de l'IA dans la gestion du risque de contrepartie. Les résultats de l'enquête révèlent qu'aucune des banques interrogées n'utilise actuellement l'IA pour la gestion du risque de contrepartie, bien qu'ils aient l'intention de l'introduire dans un avenir proche. Les avantages attendus incluent une précision accrue dans l'évaluation des risques et une optimisation des processus grâce à l'automatisation. Cependant, les obstacles potentiels incluent des contraintes financières et une pénurie d'expertise en IA. En effet, l'IA pourrait présenter des perspectives prometteuses pour renforcer la stabilité financière et garantir la conformité à la Charia au sein des banques participatives. Pour une intégration efficace, des investissements dans les ressources et la formation en IA sont nécessaires. En somme, l'avenir de l'IA dans la gestion du risque de contrepartie promet d'introduire innovation et efficacité opérationnelle dans le secteur de la finance participative. |
| Keywords: | Artificial Intelligence AI, Participatory Finance, Risk management, Counterparty Credit Risk, Intelligence Artificielle, Finance Participative, Gestion des risques, Risque de contrepartie |
| Date: | 2024–09–02 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-04690166 |
| By: | David Landriault; Bin Li; Hong Li; Yuanyuan Zhang |
| Abstract: | This paper introduces an economic framework to assess optimal longevity risk transfers between institutions, focusing on the interactions between a buyer exposed to long-term longevity risk and a seller offering longevity protection. While most longevity risk transfers have occurred in the reinsurance sector, where global reinsurers provide long-term protections, the capital market for longevity risk transfer has struggled to gain traction, resulting in only a few short-term instruments. We investigate how differences in risk aversion between the two parties affect the equilibrium structure of longevity risk transfer contracts, contrasting `static' contracts that offer long-term protection with `dynamic' contracts that provide short-term, variable coverage. Our analysis shows that static contracts are preferred by more risk-averse buyers, while dynamic contracts are favored by more risk-averse sellers who are reluctant to commit to long-term agreements. When incorporating information asymmetry through ambiguity, we find that ambiguity can cause more risk-averse sellers to stop offering long-term contracts. With the assumption that global reinsurers, acting as sellers in the reinsurance sector and buyers in the capital market, are generally less risk-averse than other participants, our findings provide theoretical explanations for current market dynamics and suggest that short-term instruments offer valuable initial steps toward developing an efficient and active capital market for longevity risk transfer. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2409.08914 |
| By: | Fredy Gamboa-Estrada; José Vicente Romero |
| Abstract: | This study examines the determinants of sovereign risk, focusing on the impact of geopolitical risk in emerging market economies (EMEs) sovereign risk metrics. Using local projection techniques, we evaluate the effects of geopolitical risk on credit default swaps (CDS) and EMBI indices in EMEs, including the recent war between Ukraine and Russia. Our findings highlight the significance of considering geopolitical risk when analyzing risk premiums for emerging markets. Notably, we find that the impact of geopolitical risk shocks on CDS is higher than the effect on EMBI spread dynamics. Furthermore, using recursive estimations, we show that the effect of geopolitical risk on sovereign CDS and EMBI spreads has been relatively stable. On the other hand, we find an important degree of heterogeneity across countries by analyzing evidence from individual countries. Some countries in our sample seem statistically unaffected by geopolitical risk, particularly when examining EMBI dynamics. **** RESUMEN: Este estudio examina los determinantes del riesgo soberano, centrándose en el impacto del riesgo geopolítico en las métricas para una muestra de mercados emergentes (EMEs). Utilizando técnicas de proyección local, evaluamos los efectos del riesgo geopolítico en los swaps de incumplimiento crediticio (CDS) y en los índices EMBI, incluyendo la reciente guerra entre Ucrania y Rusia. Nuestros hallazgos resaltan la importancia de considerar el riesgo geopolítico al analizar las primas de riesgo para los mercados emergentes. En particular, encontramos que el impacto de los choques de riesgo geopolítico en los CDS es mayor que el efecto en la dinámica del EMBI. Además, utilizando estimaciones recursivas, mostramos que el efecto del riesgo geopolítico en los CDS soberanos y en el EMBI ha sido relativamente estable. Por otro lado, presentamos evidencia de un importante grado de heterogeneidad entre los países al examinar las estimaciones de países individuales. Algunos países de nuestra muestra parecen no estar afectados por el riesgo geopolítico, particularmente al examinar la dinámica del EMBI. |
| Keywords: | Sovereign risk, credit default swaps, EMBI, emerging markets, geopolitical risk, local projection, riesgo soberano, swaps de incumplimiento crediticio, EMBI, mercados emergentes, riesgo geopolítico, proyecciones locales. |
| JEL: | C22 F37 G15 G17 |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:bdr:borrec:1282 |
| By: | Soumil Hooda; Shubham Sharma; Kunal Bansal |
| Abstract: | This technical report presents a stochastic framework for pricing temperature derivatives in Indian markets accounting for both monsoon and winter seasons. Utilising historical temperature and electricity consumption data from 12 Indian states we develop a model based on a modified mean-reverting Ornstein-Uhlenbeck process and employ Monte Carlo simulations for pricing. Our analysis reveals significant variations in option pricing across states with monsoon call options ranging from 10.78 USD to 182.82 USD and winter put options from 48.65 USD to 194.99 USD. The introduction of a risk aversion parameter shows substantial impacts on pricing leading to an increase of up to 416 percentage in option prices for certain states. Sensitivity analyses indicate that option prices are more responsive to changes in volatility than to mean reversion rates. Additionally extreme weather scenarios can shift option prices by up to 409 percentage during heatwaves and decrease by 60 percentage during cold waves. These findings emphasise the importance of state-specific and season-specific approaches in temperature derivative pricing highlighting the need for tailored risk management strategies in India's diverse climate. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2409.04541 |