arXiv - QuantFin - Risk Management最新文献_第8页

A note on continuity and consistency of measures of risk and variability 关于风险和变异性测量的连续性和一致性的说明

arXiv - QuantFin - Risk Management Pub Date : 2024-05-16 DOI: arxiv-2405.09766

Niushan Gao, Foivos Xanthos

引用次数: 0

Geometric BSDEs 几何 BSDE

arXiv - QuantFin - Risk Management Pub Date : 2024-05-15 DOI: arxiv-2405.09260

Roger J. A. Laeven, Emanuela Rosazza Gianin, Marco Zullino

引用次数: 0

Optimizing Deep Reinforcement Learning for American Put Option Hedging 优化美式看跌期权对冲的深度强化学习

arXiv - QuantFin - Risk Management Pub Date : 2024-05-14 DOI: arxiv-2405.08602

Reilly Pickard, F. Wredenhagen, Y. Lawryshyn

{"title":"Optimizing Deep Reinforcement Learning for American Put Option Hedging","authors":"Reilly Pickard, F. Wredenhagen, Y. Lawryshyn","doi":"arxiv-2405.08602","DOIUrl":"https://doi.org/arxiv-2405.08602","url":null,"abstract":"This paper contributes to the existing literature on hedging American options\u0000with Deep Reinforcement Learning (DRL). The study first investigates\u0000hyperparameter impact on hedging performance, considering learning rates,\u0000training episodes, neural network architectures, training steps, and\u0000transaction cost penalty functions. Results highlight the importance of\u0000avoiding certain combinations, such as high learning rates with a high number\u0000of training episodes or low learning rates with few training episodes and\u0000emphasize the significance of utilizing moderate values for optimal outcomes.\u0000Additionally, the paper warns against excessive training steps to prevent\u0000instability and demonstrates the superiority of a quadratic transaction cost\u0000penalty function over a linear version. This study then expands upon the work\u0000of Pickard et al. (2024), who utilize a Chebyshev interpolation option pricing\u0000method to train DRL agents with market calibrated stochastic volatility models.\u0000While the results of Pickard et al. (2024) showed that these DRL agents achieve\u0000satisfactory performance on empirical asset paths, this study introduces a\u0000novel approach where new agents at weekly intervals to newly calibrated\u0000stochastic volatility models. Results show DRL agents re-trained using weekly\u0000market data surpass the performance of those trained solely on the sale date.\u0000Furthermore, the paper demonstrates that both single-train and weekly-train DRL\u0000agents outperform the Black-Scholes Delta method at transaction costs of 1% and\u00003%. This practical relevance suggests that practitioners can leverage readily\u0000available market data to train DRL agents for effective hedging of options in\u0000their portfolios.","PeriodicalId":501128,"journal":{"name":"arXiv - QuantFin - Risk Management","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141061955","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 Measure on $L^0$: NA Condition, Pricing and Dual Representation $L^0$上的相干风险度量：NA 条件、定价和二元表示法

arXiv - QuantFin - Risk Management Pub Date : 2024-05-10 DOI: arxiv-2405.06764

Emmanuel Lepinette, Duc Thinh Vu

引用次数: 0

Large Language Model in Financial Regulatory Interpretation 金融监管解释中的大语言模型

arXiv - QuantFin - Risk Management Pub Date : 2024-05-10 DOI: arxiv-2405.06808

Zhiyu Cao, Zachary Feinstein

引用次数: 0

Hedge Error Analysis In Black Scholes Option Pricing Model: An Asymptotic Approach Towards Finite Difference 布莱克-斯科尔斯期权定价模型中的对冲误差分析：迈向有限差分的渐近方法

arXiv - QuantFin - Risk Management Pub Date : 2024-05-05 DOI: arxiv-2405.02919

Agni Rakshit, Gautam Bandyopadhyay, Tanujit Chakraborty

引用次数: 0

Explainable Risk Classification in Financial Reports 财务报告中可解释的风险分类

arXiv - QuantFin - Risk Management Pub Date : 2024-05-03 DOI: arxiv-2405.01881

Xue Wen Tan, Stanley Kok

引用次数: 0

Backtesting Expected Shortfall: Accounting for both duration and severity with bivariate orthogonal polynomials 回测预期亏损：利用二元正交多项式计算持续时间和严重程度

arXiv - QuantFin - Risk Management Pub Date : 2024-05-03 DOI: arxiv-2405.02012

Sullivan Hué, Christophe Hurlin, Yang Lu

{"title":"Backtesting Expected Shortfall: Accounting for both duration and severity with bivariate orthogonal polynomials","authors":"Sullivan Hué, Christophe Hurlin, Yang Lu","doi":"arxiv-2405.02012","DOIUrl":"https://doi.org/arxiv-2405.02012","url":null,"abstract":"We propose an original two-part, duration-severity approach for backtesting\u0000Expected Shortfall (ES). While Probability Integral Transform (PIT) based ES\u0000backtests have gained popularity, they have yet to allow for separate testing\u0000of the frequency and severity of Value-at-Risk (VaR) violations. This is a\u0000crucial aspect, as ES measures the average loss in the event of such\u0000violations. To overcome this limitation, we introduce a backtesting framework\u0000that relies on the sequence of inter-violation durations and the sequence of\u0000severities in case of violations. By leveraging the theory of (bivariate)\u0000orthogonal polynomials, we derive orthogonal moment conditions satisfied by\u0000these two sequences. Our approach includes a straightforward, model-free Wald\u0000test, which encompasses various unconditional and conditional coverage\u0000backtests for both VaR and ES. This test aids in identifying any mis-specified\u0000components of the internal model used by banks to forecast ES. Moreover, it can\u0000be extended to analyze other systemic risk measures such as Marginal Expected\u0000Shortfall. Simulation experiments indicate that our test exhibits good finite\u0000sample properties for realistic sample sizes. Through application to two stock\u0000indices, we demonstrate how our methodology provides insights into the reasons\u0000for rejections in testing ES validity.","PeriodicalId":501128,"journal":{"name":"arXiv - QuantFin - Risk Management","volume":"212 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140938297","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

Some properties of Euler capital allocation 欧拉资本分配的一些特性

arXiv - QuantFin - Risk Management Pub Date : 2024-05-01 DOI: arxiv-2405.00606

Lars Holden

引用次数: 0

Innovative Application of Artificial Intelligence Technology in Bank Credit Risk Management 人工智能技术在银行信贷风险管理中的创新应用

arXiv - QuantFin - Risk Management Pub Date : 2024-04-28 DOI: arxiv-2404.18183

Shuochen Bi, Wenqing Bao

{"title":"Innovative Application of Artificial Intelligence Technology in Bank Credit Risk Management","authors":"Shuochen Bi, Wenqing Bao","doi":"arxiv-2404.18183","DOIUrl":"https://doi.org/arxiv-2404.18183","url":null,"abstract":"With the rapid growth of technology, especially the widespread application of\u0000artificial intelligence (AI) technology, the risk management level of\u0000commercial banks is constantly reaching new heights. In the current wave of\u0000digitalization, AI has become a key driving force for the strategic\u0000transformation of financial institutions, especially the banking industry. For\u0000commercial banks, the stability and safety of asset quality are crucial, which\u0000directly relates to the long-term stable growth of the bank. Among them, credit\u0000risk management is particularly core because it involves the flow of a large\u0000amount of funds and the accuracy of credit decisions. Therefore, establishing a\u0000scientific and effective credit risk decision-making mechanism is of great\u0000strategic significance for commercial banks. In this context, the innovative\u0000application of AI technology has brought revolutionary changes to bank credit\u0000risk management. Through deep learning and big data analysis, AI can accurately\u0000evaluate the credit status of borrowers, timely identify potential risks, and\u0000provide banks with more accurate and comprehensive credit decision support. At\u0000the same time, AI can also achieve realtime monitoring and early warning,\u0000helping banks intervene before risks occur and reduce losses.","PeriodicalId":501128,"journal":{"name":"arXiv - QuantFin - Risk Management","volume":"155 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140830700","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