发布求助
文献互助 智能选刊 最新文献

arXiv - QuantFin - Portfolio Management最新文献

筛选
英文 中文
Intertemporal Cost-efficient Consumption 具有成本效益的跨期消费
arXiv - QuantFin - Portfolio Management Pub Date : 2024-05-25 DOI: arxiv-2405.16336
Mauricio Elizalde, Stephan Sturm
{"title":"Intertemporal Cost-efficient Consumption","authors":"Mauricio Elizalde, Stephan Sturm","doi":"arxiv-2405.16336","DOIUrl":"https://doi.org/arxiv-2405.16336","url":null,"abstract":"We aim to provide an intertemporal, cost-efficient consumption model that\u0000extends the consumption optimization inspired by the Distribution Builder, a\u0000tool developed by Sharpe, Johnson, and Goldstein. The Distribution Builder\u0000enables the recovery of investors' risk preferences by allowing them to select\u0000a desired distribution of terminal wealth within their budget constraints. This approach differs from the classical portfolio optimization, which\u0000considers the agent's risk aversion modeled by utility functions that are\u0000challenging to measure in practice. Our intertemporal model captures the\u0000dependent structure between consumption periods using copulas. This strategy is\u0000demonstrated using both the Black-Scholes and CEV models.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"60 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141168373","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
DSPO: An End-to-End Framework for Direct Sorted Portfolio Construction DSPO：直接分类投资组合构建的端到端框架
arXiv - QuantFin - Portfolio Management Pub Date : 2024-05-24 DOI: arxiv-2405.15833
Jianyuan Zhong, Zhijian Xu, Saizhuo Wang, Xiangyu Wen, Jian Guo, Qiang Xu
{"title":"DSPO: An End-to-End Framework for Direct Sorted Portfolio Construction","authors":"Jianyuan Zhong, Zhijian Xu, Saizhuo Wang, Xiangyu Wen, Jian Guo, Qiang Xu","doi":"arxiv-2405.15833","DOIUrl":"https://doi.org/arxiv-2405.15833","url":null,"abstract":"In quantitative investment, constructing characteristic-sorted portfolios is\u0000a crucial strategy for asset allocation. Traditional methods transform raw\u0000stock data of varying frequencies into predictive characteristic factors for\u0000asset sorting, often requiring extensive manual design and misalignment between\u0000prediction and optimization goals. To address these challenges, we introduce\u0000Direct Sorted Portfolio Optimization (DSPO), an innovative end-to-end framework\u0000that efficiently processes raw stock data to construct sorted portfolios\u0000directly. DSPO's neural network architecture seamlessly transitions stock data\u0000from input to output while effectively modeling the intra-dependency of\u0000time-steps and inter-dependency among all tradable stocks. Additionally, we\u0000incorporate a novel Monotonical Logistic Regression loss, which directly\u0000maximizes the likelihood of constructing optimal sorted portfolios. To the best\u0000of our knowledge, DSPO is the first method capable of handling market\u0000cross-sections with thousands of tradable stocks fully end-to-end from raw\u0000multi-frequency data. Empirical results demonstrate DSPO's effectiveness,\u0000yielding a RankIC of 10.12% and an accumulated return of 121.94% on the New\u0000York Stock Exchange in 2023-2024, and a RankIC of 9.11% with a return of\u0000108.74% in other markets during 2021-2022.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141168486","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
Autonomous Sparse Mean-CVaR Portfolio Optimization 自主稀疏均值-CVaR 投资组合优化
arXiv - QuantFin - Portfolio Management Pub Date : 2024-05-13 DOI: arxiv-2405.08047
Yizun Lin, Yangyu Zhang, Zhao-Rong Lai, Cheng Li
{"title":"Autonomous Sparse Mean-CVaR Portfolio Optimization","authors":"Yizun Lin, Yangyu Zhang, Zhao-Rong Lai, Cheng Li","doi":"arxiv-2405.08047","DOIUrl":"https://doi.org/arxiv-2405.08047","url":null,"abstract":"The $ell_0$-constrained mean-CVaR model poses a significant challenge due to\u0000its NP-hard nature, typically tackled through combinatorial methods\u0000characterized by high computational demands. From a markedly different\u0000perspective, we propose an innovative autonomous sparse mean-CVaR portfolio\u0000model, capable of approximating the original $ell_0$-constrained mean-CVaR\u0000model with arbitrary accuracy. The core idea is to convert the $ell_0$\u0000constraint into an indicator function and subsequently handle it through a\u0000tailed approximation. We then propose a proximal alternating linearized\u0000minimization algorithm, coupled with a nested fixed-point proximity algorithm\u0000(both convergent), to iteratively solve the model. Autonomy in sparsity refers\u0000to retaining a significant portion of assets within the selected asset pool\u0000during adjustments in pool size. Consequently, our framework offers a\u0000theoretically guaranteed approximation of the $ell_0$-constrained mean-CVaR\u0000model, improving computational efficiency while providing a robust asset\u0000selection scheme.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141063588","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
Portfolio Management using Deep Reinforcement Learning 利用深度强化学习进行投资组合管理
arXiv - QuantFin - Portfolio Management Pub Date : 2024-05-01 DOI: arxiv-2405.01604
Ashish Anil Pawar, Vishnureddy Prashant Muskawar, Ritesh Tiku
{"title":"Portfolio Management using Deep Reinforcement Learning","authors":"Ashish Anil Pawar, Vishnureddy Prashant Muskawar, Ritesh Tiku","doi":"arxiv-2405.01604","DOIUrl":"https://doi.org/arxiv-2405.01604","url":null,"abstract":"Algorithmic trading or Financial robots have been conquering the stock\u0000markets with their ability to fathom complex statistical trading strategies.\u0000But with the recent development of deep learning technologies, these strategies\u0000are becoming impotent. The DQN and A2C models have previously outperformed\u0000eminent humans in game-playing and robotics. In our work, we propose a\u0000reinforced portfolio manager offering assistance in the allocation of weights\u0000to assets. The environment proffers the manager the freedom to go long and even\u0000short on the assets. The weight allocation advisements are restricted to the\u0000choice of portfolio assets and tested empirically to knock benchmark indices.\u0000The manager performs financial transactions in a postulated liquid market\u0000without any transaction charges. This work provides the conclusion that the\u0000proposed portfolio manager with actions centered on weight allocations can\u0000surpass the risk-adjusted returns of conventional portfolio managers.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"32 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140934738","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
A Multi-Period Black-Litterman Model 多期布莱克-利特曼模型
arXiv - QuantFin - Portfolio Management Pub Date : 2024-04-29 DOI: arxiv-2404.18822
Anas Abdelhakmi, Andrew Lim
{"title":"A Multi-Period Black-Litterman Model","authors":"Anas Abdelhakmi, Andrew Lim","doi":"arxiv-2404.18822","DOIUrl":"https://doi.org/arxiv-2404.18822","url":null,"abstract":"The Black-Litterman model is a framework for incorporating forward-looking\u0000expert views in a portfolio optimization problem. Existing work focuses almost\u0000exclusively on single-period problems and assumes that the horizon of expert\u0000forecasts matches that of the investor. We consider a multi-period\u0000generalization where the horizon of expert views may differ from that of a\u0000dynamically-trading investor. By exploiting an underlying graphical structure\u0000relating the asset prices and views, we derive the conditional distribution of\u0000asset returns when the price process is geometric Brownian motion. We also show\u0000that it can be written in terms of a multi-dimensional Brownian bridge. The new\u0000price process is an affine factor model with the conditional log-price process\u0000playing the role of a vector of factors. We derive an explicit expression for\u0000the optimal dynamic investment policy and analyze the hedging demand associated\u0000with the new covariate. More generally, the paper shows that Bayesian graphical\u0000models are a natural framework for incorporating complex information structures\u0000in the Black-Litterman model.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"66 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140836842","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
Application and practice of AI technology in quantitative investment 人工智能技术在量化投资中的应用与实践
arXiv - QuantFin - Portfolio Management Pub Date : 2024-04-28 DOI: arxiv-2404.18184
Shuochen Bi, Wenqing Bao, Jue Xiao, Jiangshan Wang, Tingting Deng
{"title":"Application and practice of AI technology in quantitative investment","authors":"Shuochen Bi, Wenqing Bao, Jue Xiao, Jiangshan Wang, Tingting Deng","doi":"arxiv-2404.18184","DOIUrl":"https://doi.org/arxiv-2404.18184","url":null,"abstract":"With the continuous development of artificial intelligence technology, using\u0000machine learning technology to predict market trends may no longer be out of\u0000reach. In recent years, artificial intelligence has become a research hotspot\u0000in the academic circle,and it has been widely used in image recognition,\u0000natural language processing and other fields, and also has a huge impact on the\u0000field of quantitative investment. As an investment method to obtain stable\u0000returns through data analysis, model construction and program trading,\u0000quantitative investment is deeply loved by financial institutions and\u0000investors. At the same time, as an important application field of quantitative\u0000investment, the quantitative investment strategy based on artificial\u0000intelligence technology arises at the historic moment.How to apply artificial\u0000intelligence to quantitative investment, so as to better achieve profit and\u0000risk control, has also become the focus and difficulty of the research. From a\u0000global perspective, inflation in the US and the Federal Reserve are the\u0000concerns of investors, which to some extent affects the direction of global\u0000assets, including the Chinese stock market. This paper studies the application\u0000of AI technology, quantitative investment, and AI technology in quantitative\u0000investment, aiming to provide investors with auxiliary decision-making, reduce\u0000the difficulty of investment analysis, and help them to obtain higher returns.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"82 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140836867","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
Application of Deep Learning for Factor Timing in Asset Management 深度学习在资产管理中的因子计时应用
arXiv - QuantFin - Portfolio Management Pub Date : 2024-04-27 DOI: arxiv-2404.18017
Prabhu Prasad Panda, Maysam Khodayari Gharanchaei, Xilin Chen, Haoshu Lyu
{"title":"Application of Deep Learning for Factor Timing in Asset Management","authors":"Prabhu Prasad Panda, Maysam Khodayari Gharanchaei, Xilin Chen, Haoshu Lyu","doi":"arxiv-2404.18017","DOIUrl":"https://doi.org/arxiv-2404.18017","url":null,"abstract":"The paper examines the performance of regression models (OLS linear\u0000regression, Ridge regression, Random Forest, and Fully-connected Neural\u0000Network) on the prediction of CMA (Conservative Minus Aggressive) factor\u0000premium and the performance of factor timing investment with them.\u0000Out-of-sample R-squared shows that more flexible models have better performance\u0000in explaining the variance in factor premium of the unseen period, and the back\u0000testing affirms that the factor timing based on more flexible models tends to\u0000over perform the ones with linear models. However, for flexible models like\u0000neural networks, the optimal weights based on their prediction tend to be\u0000unstable, which can lead to high transaction costs and market impacts. We\u0000verify that tilting down the rebalance frequency according to the historical\u0000optimal rebalancing scheme can help reduce the transaction costs.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"82 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140836906","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
Constructing an Investment Fund through Stock Clustering and Integer Programming 通过股票聚类和整数编程构建投资基金
arXiv - QuantFin - Portfolio Management Pub Date : 2024-04-27 DOI: arxiv-2407.05912
Maysam Khodayari Gharanchaei, Prabhu Prasad Panda
{"title":"Constructing an Investment Fund through Stock Clustering and Integer Programming","authors":"Maysam Khodayari Gharanchaei, Prabhu Prasad Panda","doi":"arxiv-2407.05912","DOIUrl":"https://doi.org/arxiv-2407.05912","url":null,"abstract":"This paper focuses on the application of quantitative portfolio management by\u0000using integer programming and clustering techniques. Investors seek to gain the\u0000highest profits and lowest risk in capital markets. A data-oriented analysis of\u0000US stock universe is used to provide portfolio managers a device to track\u0000different Exchange Traded Funds. As an example, reconstructing of NASDAQ 100\u0000index fund is presented.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"78 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141576658","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
Quantitative Investment Diversification Strategies via Various Risk Models 通过各种风险模型实现量化投资多样化战略
arXiv - QuantFin - Portfolio Management Pub Date : 2024-04-27 DOI: arxiv-2407.01550
Maysam Khodayari Gharanchaei, Prabhu Prasad Panda, Xilin Chen
{"title":"Quantitative Investment Diversification Strategies via Various Risk Models","authors":"Maysam Khodayari Gharanchaei, Prabhu Prasad Panda, Xilin Chen","doi":"arxiv-2407.01550","DOIUrl":"https://doi.org/arxiv-2407.01550","url":null,"abstract":"This paper focuses on the developing of high-dimensional risk models to\u0000construct portfolios of securities in the US stock exchange. Investors seek to\u0000gain the highest profits and lowest risk in capital markets. We have developed\u0000various risk models and for each model different investment strategies are\u0000tested. Out of sample tests are performed on a long-term horizon from 1970\u0000until 2023.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"145 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141523137","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
On a fundamental statistical edge principle 关于基本统计边缘原理
arXiv - QuantFin - Portfolio Management Pub Date : 2024-04-22 DOI: arxiv-2404.14252
Tommaso Gastaldi
{"title":"On a fundamental statistical edge principle","authors":"Tommaso Gastaldi","doi":"arxiv-2404.14252","DOIUrl":"https://doi.org/arxiv-2404.14252","url":null,"abstract":"This paper establishes that conditioning the probability of execution of new\u0000orders on the self-generated historical trading information (HTI) of a trading\u0000strategy is a necessary condition for a statistical trading edge. It is shown,\u0000in particular, that, given any trading strategy S that does not use its own\u0000HTI, it is always possible to construct a new strategy S* that yields a\u0000systematically increasing improvement over S in terms of profit and loss (PnL)\u0000by using the self-generated HTI. This holds true under rather general\u0000conditions that are frequently met in practice, and it is proven through a\u0000decision mechanism specifically designed to formally prove this idea.\u0000Simulations and real-world trading evidence are included for validation and\u0000illustration, respectively.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"37 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140800446","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信