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

Constrained Max Drawdown: a Fast and Robust Portfolio Optimization Approach 受限最大缩减：快速稳健的投资组合优化方法

arXiv - QuantFin - Portfolio Management Pub Date : 2024-01-05 DOI: arxiv-2401.02601

Albert Dorador

引用次数: 0

A Portfolio's Common Causal Conditional Risk-neutral PDE 投资组合的共同因果条件风险中性 PDE

arXiv - QuantFin - Portfolio Management Pub Date : 2024-01-01 DOI: arxiv-2401.00949

Alejandro Rodriguez Dominguez

引用次数: 0

Almost Perfect Shadow Prices 几乎完美的阴影价格

arXiv - QuantFin - Portfolio Management Pub Date : 2024-01-01 DOI: arxiv-2401.00970

Eberhard Mayerhofer

引用次数: 0

Enhancing CVaR portfolio optimisation performance with GAM factor models 利用 GAM 因子模型提高 CVaR 投资组合优化性能

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-30 DOI: arxiv-2401.00188

Davide Lauria, W. Brent Lindquist, Svetlozar T. Rachev

引用次数: 0

Representation of forward performance criteria with random endowment via FBSDE and application to forward optimized certainty equivalent 通过 FBSDE 表示具有随机禀赋的前瞻性绩效标准，并将其应用于前瞻性优化确定性等价物

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-29 DOI: arxiv-2401.00103

Gechun Liang, Yifan Sun, Thaleia Zariphopoulou

{"title":"Representation of forward performance criteria with random endowment via FBSDE and application to forward optimized certainty equivalent","authors":"Gechun Liang, Yifan Sun, Thaleia Zariphopoulou","doi":"arxiv-2401.00103","DOIUrl":"https://doi.org/arxiv-2401.00103","url":null,"abstract":"We extend the notion of forward performance criteria to settings with random\u0000endowment in incomplete markets. Building on these results, we introduce and\u0000develop the novel concept of forward optimized certainty equivalent (forward\u0000OCE), which offers a genuinely dynamic valuation mechanism that accommodates\u0000progressively adaptive market model updates, stochastic risk preferences, and\u0000incoming claims with arbitrary maturities. In parallel, we develop a new methodology to analyze the emerging stochastic\u0000optimization problems by directly studying the candidate optimal control\u0000processes for both the primal and dual problems. Specifically, we derive two\u0000new systems of forward-backward stochastic differential equations (FBSDEs) and\u0000establish necessary and sufficient conditions for optimality, and various\u0000equivalences between the two problems. This new approach is general and\u0000complements the existing one based on backward stochastic partial differential\u0000equations (backward SPDEs) for the related value functions. We, also, consider\u0000representative examples for both forward performance criteria with random\u0000endowment and forward OCE, and for the case of exponential criteria, we\u0000investigate the connection between forward OCE and forward entropic risk\u0000measures.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"125 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139079756","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

Discrete-Time Mean-Variance Strategy Based on Reinforcement Learning 基于强化学习的离散时间均值-方差策略

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-24 DOI: arxiv-2312.15385

Xiangyu Cui, Xun Li, Yun Shi, Si Zhao

引用次数: 0

Shai: A large language model for asset management 沙伊用于资产管理的大型语言模型

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-21 DOI: arxiv-2312.14203

Zhongyang Guo, Guanran Jiang, Zhongdan Zhang, Peng Li, Zhefeng Wang, Yinchun Wang

{"title":"Shai: A large language model for asset management","authors":"Zhongyang Guo, Guanran Jiang, Zhongdan Zhang, Peng Li, Zhefeng Wang, Yinchun Wang","doi":"arxiv-2312.14203","DOIUrl":"https://doi.org/arxiv-2312.14203","url":null,"abstract":"This paper introduces \"Shai\" a 10B level large language model specifically\u0000designed for the asset management industry, built upon an open-source\u0000foundational model. With continuous pre-training and fine-tuning using a\u0000targeted corpus, Shai demonstrates enhanced performance in tasks relevant to\u0000its domain, outperforming baseline models. Our research includes the\u0000development of an innovative evaluation framework, which integrates\u0000professional qualification exams, tailored tasks, open-ended question\u0000answering, and safety assessments, to comprehensively assess Shai's\u0000capabilities. Furthermore, we discuss the challenges and implications of\u0000utilizing large language models like GPT-4 for performance assessment in asset\u0000management, suggesting a combination of automated evaluation and human\u0000judgment. Shai's development, showcasing the potential and versatility of\u000010B-level large language models in the financial sector with significant\u0000performance and modest computational requirements, hopes to provide practical\u0000insights and methodologies to assist industry peers in their similar endeavors.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"142 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139035922","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

Market-Adaptive Ratio for Portfolio Management 投资组合管理的市场适应比率

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-21 DOI: arxiv-2312.13719

Ju-Hong Lee, Bayartsetseg Kalina, KwangTek Na

引用次数: 0

Learning Merton's Strategies in an Incomplete Market: Recursive Entropy Regularization and Biased Gaussian Exploration 在不完全市场中学习默顿策略：递归熵正则化与有偏高斯探索

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-19 DOI: arxiv-2312.11797

Min Dai, Yuchao Dong, Yanwei Jia, Xun Yu Zhou

{"title":"Learning Merton's Strategies in an Incomplete Market: Recursive Entropy Regularization and Biased Gaussian Exploration","authors":"Min Dai, Yuchao Dong, Yanwei Jia, Xun Yu Zhou","doi":"arxiv-2312.11797","DOIUrl":"https://doi.org/arxiv-2312.11797","url":null,"abstract":"We study Merton's expected utility maximization problem in an incomplete\u0000market, characterized by a factor process in addition to the stock price\u0000process, where all the model primitives are unknown. We take the reinforcement\u0000learning (RL) approach to learn optimal portfolio policies directly by\u0000exploring the unknown market, without attempting to estimate the model\u0000parameters. Based on the entropy-regularization framework for general\u0000continuous-time RL formulated in Wang et al. (2020), we propose a recursive\u0000weighting scheme on exploration that endogenously discounts the current\u0000exploration reward by the past accumulative amount of exploration. Such a\u0000recursive regularization restores the optimality of Gaussian exploration.\u0000However, contrary to the existing results, the optimal Gaussian policy turns\u0000out to be biased in general, due to the interwinding needs for hedging and for\u0000exploration. We present an asymptotic analysis of the resulting errors to show\u0000how the level of exploration affects the learned policies. Furthermore, we\u0000establish a policy improvement theorem and design several RL algorithms to\u0000learn Merton's optimal strategies. At last, we carry out both simulation and\u0000empirical studies with a stochastic volatility environment to demonstrate the\u0000efficiency and robustness of the RL algorithms in comparison to the\u0000conventional plug-in method.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"80 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138821164","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

Factor Risk Budgeting and Beyond 要素风险预算及其他

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-18 DOI: arxiv-2312.11132

Adil Rengim Cetingoz, Olivier Guéant

{"title":"Factor Risk Budgeting and Beyond","authors":"Adil Rengim Cetingoz, Olivier Guéant","doi":"arxiv-2312.11132","DOIUrl":"https://doi.org/arxiv-2312.11132","url":null,"abstract":"Portfolio optimization methods have evolved significantly since Markowitz\u0000introduced the mean-variance framework in 1952. While the theoretical appeal of\u0000this approach is undeniable, its practical implementation poses important\u0000challenges, primarily revolving around the intricate task of estimating\u0000expected returns. As a result, practitioners and scholars have explored\u0000alternative methods that prioritize risk management and diversification. One\u0000such approach is Risk Budgeting, where portfolio risk is allocated among assets\u0000according to predefined risk budgets. The effectiveness of Risk Budgeting in\u0000achieving true diversification can, however, be questioned, given that asset\u0000returns are often influenced by a small number of risk factors. From this\u0000perspective, one question arises: is it possible to allocate risk at the factor\u0000level using the Risk Budgeting approach? This paper introduces a comprehensive\u0000framework to address this question by introducing risk measures directly\u0000associated with risk factor exposures and demonstrating the desirable\u0000mathematical properties of these risk measures, making them suitable for\u0000optimization. We also propose a framework to find the portfolio that\u0000effectively balances the risk contributions from both assets and factors.\u0000Leveraging standard stochastic algorithms, our framework enables the use of a\u0000wide range of risk measures.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"55 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138744562","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