arXiv - QuantFin - Risk Management最新文献_第9页

Value-at-Risk- and Expectile-based Systemic Risk Measures and Second-order Asymptotics: With Applications to Diversification 基于风险价值和期望值的系统风险度量和二阶渐近线：多元化应用

arXiv - QuantFin - Risk Management Pub Date : 2024-04-27 DOI: arxiv-2404.18029

Bingzhen Geng, Yang Liu, Yimiao Zhao

{"title":"Value-at-Risk- and Expectile-based Systemic Risk Measures and Second-order Asymptotics: With Applications to Diversification","authors":"Bingzhen Geng, Yang Liu, Yimiao Zhao","doi":"arxiv-2404.18029","DOIUrl":"https://doi.org/arxiv-2404.18029","url":null,"abstract":"The systemic risk measure plays a crucial role in analyzing individual losses\u0000conditioned on extreme system-wide disasters. In this paper, we provide a\u0000unified asymptotic treatment for systemic risk measures. First, we classify\u0000them into two families of Value-at-Risk- (VaR-) and expectile-based systemic\u0000risk measures. While VaR has been extensively studied, in the latter family, we\u0000propose two new systemic risk measures named the Individual Conditional\u0000Expectile (ICE) and the Systemic Individual Conditional Expectile (SICE), as\u0000alternatives to Marginal Expected Shortfall (MES) and Systemic Expected\u0000Shortfall (SES). Second, to characterize general mutually dependent and\u0000heavy-tailed risks, we adopt a modeling framework where the system, represented\u0000by a vector of random loss variables, follows a multivariate Sarmanov\u0000distribution with a common marginal exhibiting second-order regular variation.\u0000Third, we provide second-order asymptotic results for both families of systemic\u0000risk measures. This analytical framework offers a more accurate estimate\u0000compared to traditional first-order asymptotics. Through numerical and\u0000analytical examples, we demonstrate the superiority of second-order asymptotics\u0000in accurately assessing systemic risk. Further, we conduct a comprehensive\u0000comparison between VaR-based and expectile-based systemic risk measures.\u0000Expectile-based measures output higher risk evaluation than VaR-based ones,\u0000emphasizing the former's potential advantages in reporting extreme events and\u0000tail risk. As a financial application, we use the asymptotic treatment to\u0000discuss the diversification benefits associated with systemic risk measures.\u0000The expectile-based diversification benefits consistently deduce an\u0000underestimation and suggest a conservative approximation, while the VaR-based\u0000diversification benefits consistently deduce an overestimation and suggest\u0000behaving optimistically.","PeriodicalId":501128,"journal":{"name":"arXiv - QuantFin - Risk Management","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140830553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The checkerboard copula and dependence concepts 棋盘式协程和依赖性概念

arXiv - QuantFin - Risk Management Pub Date : 2024-04-23 DOI: arxiv-2404.15023

Liyuan Lin, Ruodu Wang, Ruixun Zhang, Chaoyi Zhao

引用次数: 0

Dispensing with optimal control: a new approach for the pricing and management of share buyback contracts 放弃最优控制：股票回购合同定价和管理的新方法

arXiv - QuantFin - Risk Management Pub Date : 2024-04-21 DOI: arxiv-2404.13754

Bastien Baldacci, Philippe Bergault, Olivier Guéant

引用次数: 0

Extremal cases of distortion risk measures with partial information 部分信息失真风险度量的极端情况

arXiv - QuantFin - Risk Management Pub Date : 2024-04-21 DOI: arxiv-2404.13637

Mengshuo Zhao, Narayanaswamy Balakrishnan, Chuancun Yin

引用次数: 0

Derivatives of Risk Measures 风险度量的衍生工具

arXiv - QuantFin - Risk Management Pub Date : 2024-04-15 DOI: arxiv-2404.09646

Battulga Gankhuu

引用次数: 0

RiskLabs: Predicting Financial Risk Using Large Language Model Based on Multi-Sources Data RiskLabs：利用基于多源数据的大型语言模型预测金融风险

arXiv - QuantFin - Risk Management Pub Date : 2024-04-11 DOI: arxiv-2404.07452

Yupeng Cao, Zhi Chen, Qingyun Pei, Fabrizio Dimino, Lorenzo Ausiello, Prashant Kumar, K. P. Subbalakshmi, Papa Momar Ndiaye

{"title":"RiskLabs: Predicting Financial Risk Using Large Language Model Based on Multi-Sources Data","authors":"Yupeng Cao, Zhi Chen, Qingyun Pei, Fabrizio Dimino, Lorenzo Ausiello, Prashant Kumar, K. P. Subbalakshmi, Papa Momar Ndiaye","doi":"arxiv-2404.07452","DOIUrl":"https://doi.org/arxiv-2404.07452","url":null,"abstract":"The integration of Artificial Intelligence (AI) techniques, particularly\u0000large language models (LLMs), in finance has garnered increasing academic\u0000attention. Despite progress, existing studies predominantly focus on tasks like\u0000financial text summarization, question-answering (Q$&$A), and stock movement\u0000prediction (binary classification), with a notable gap in the application of\u0000LLMs for financial risk prediction. Addressing this gap, in this paper, we\u0000introduce textbf{RiskLabs}, a novel framework that leverages LLMs to analyze\u0000and predict financial risks. RiskLabs uniquely combines different types of\u0000financial data, including textual and vocal information from Earnings\u0000Conference Calls (ECCs), market-related time series data, and contextual news\u0000data surrounding ECC release dates. Our approach involves a multi-stage\u0000process: initially extracting and analyzing ECC data using LLMs, followed by\u0000gathering and processing time-series data before the ECC dates to model and\u0000understand risk over different timeframes. Using multimodal fusion techniques,\u0000RiskLabs amalgamates these varied data features for comprehensive multi-task\u0000financial risk prediction. Empirical experiment results demonstrate RiskLab's\u0000effectiveness in forecasting both volatility and variance in financial markets.\u0000Through comparative experiments, we demonstrate how different data sources\u0000contribute to financial risk assessment and discuss the critical role of LLMs\u0000in this context. Our findings not only contribute to the AI in finance\u0000application but also open new avenues for applying LLMs in financial risk\u0000assessment.","PeriodicalId":501128,"journal":{"name":"arXiv - QuantFin - Risk Management","volume":"2011 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140602324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The PEAL Method: a mathematical framework to streamline securitization structuring PEAL 方法：简化证券化结构的数学框架

arXiv - QuantFin - Risk Management Pub Date : 2024-04-08 DOI: arxiv-2404.05372

Andrea Pinto, Antonio Scala

{"title":"The PEAL Method: a mathematical framework to streamline securitization structuring","authors":"Andrea Pinto, Antonio Scala","doi":"arxiv-2404.05372","DOIUrl":"https://doi.org/arxiv-2404.05372","url":null,"abstract":"Securitization is a financial process where the cash flows of\u0000income-generating assets are sold to institutional investors as securities,\u0000liquidating illiquid assets. This practice presents persistent challenges due\u0000to the absence of a comprehensive mathematical framework for structuring\u0000asset-backed securities. While existing literature provides technical analysis\u0000of credit risk modeling, there remains a need for a definitive framework\u0000detailing the allocation of the inbound cash flows to the outbound positions.\u0000To fill this gap, we introduce the PEAL Method: a 10-step mathematical\u0000framework to streamline the securitization structuring across all time periods. The PEAL Method offers a rigorous and versatile approach, allowing\u0000practitioners to structure various types of securitizations, including those\u0000with complex vertical positions. By employing standardized equations, it\u0000facilitates the delineation of payment priorities and enhances risk\u0000characterization for both the asset and the liability sides throughout the\u0000securitization life cycle. In addition to its technical contributions, the PEAL Method aims to elevate\u0000industry standards by addressing longstanding challenges in securitization. By\u0000providing detailed information to investors and enabling transparent risk\u0000profile comparisons, it promotes market transparency and enables stronger\u0000regulatory oversight. In summary, the PEAL Method represents a significant advancement in\u0000securitization literature, offering a standardized framework for precision and\u0000efficiency in structuring transactions. Its adoption has the potential to drive\u0000innovation and enhance risk management practices in the securitization market.","PeriodicalId":501128,"journal":{"name":"arXiv - QuantFin - Risk Management","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140581626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Coherent risk measures and uniform integrability 连贯的风险度量和统一的可整性

arXiv - QuantFin - Risk Management Pub Date : 2024-04-04 DOI: arxiv-2404.03783

Muqiao Huang, Ruodu Wang

引用次数: 0

QFNN-FFD: Quantum Federated Neural Network for Financial Fraud Detection QFNN-FFD：用于金融欺诈检测的量子联邦神经网络

arXiv - QuantFin - Risk Management Pub Date : 2024-04-03 DOI: arxiv-2404.02595

Nouhaila Innan, Alberto Marchisio, Muhammad Shafique, Mohamed Bennai

引用次数: 0

Enhancing Anomaly Detection in Financial Markets with an LLM-based Multi-Agent Framework 利用基于 LLM 的多代理框架加强金融市场异常检测

arXiv - QuantFin - Risk Management Pub Date : 2024-03-28 DOI: arxiv-2403.19735

Taejin Park

引用次数: 0