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

Artificial Intelligence-based Analysis of Change in Public Finance between US and International Markets 基于人工智能的美国与国际市场公共财政变化分析

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-10 DOI: arxiv-2403.18823

Kapil Panda

{"title":"Artificial Intelligence-based Analysis of Change in Public Finance between US and International Markets","authors":"Kapil Panda","doi":"arxiv-2403.18823","DOIUrl":"https://doi.org/arxiv-2403.18823","url":null,"abstract":"Public finances are one of the fundamental mechanisms of economic governance\u0000that refer to the financial activities and decisions made by government\u0000entities to fund public services, projects, and operations through assets. In\u0000today's globalized landscape, even subtle shifts in one nation's public debt\u0000landscape can have significant impacts on that of international finances,\u0000necessitating a nuanced understanding of the correlations between international\u0000and national markets to help investors make informed investment decisions.\u0000Therefore, by leveraging the capabilities of artificial intelligence, this\u0000study utilizes neural networks to depict the correlations between US and\u0000International Public Finances and predict the changes in international public\u0000finances based on the changes in US public finances. With the neural network\u0000model achieving a commendable Mean Squared Error (MSE) value of 2.79, it is\u0000able to affirm a discernible correlation and also plot the effect of US market\u0000volatility on international markets. To further test the accuracy and\u0000significance of the model, an economic analysis was conducted that aimed to\u0000correlate the changes seen by the results of the model with historical stock\u0000market changes. This model demonstrates significant potential for investors to\u0000predict changes in international public finances based on signals from US\u0000markets, marking a significant stride in comprehending the intricacies of\u0000global public finances and the role of artificial intelligence in decoding its\u0000multifaceted patterns for practical forecasting.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140325520","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

Onflow: an online portfolio allocation algorithm Onflow：在线投资组合分配算法

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-08 DOI: arxiv-2312.05169

Gabriel Turinici, Pierre Brugiere

{"title":"Onflow: an online portfolio allocation algorithm","authors":"Gabriel Turinici, Pierre Brugiere","doi":"arxiv-2312.05169","DOIUrl":"https://doi.org/arxiv-2312.05169","url":null,"abstract":"We introduce Onflow, a reinforcement learning technique that enables online\u0000optimization of portfolio allocation policies based on gradient flows. We\u0000devise dynamic allocations of an investment portfolio to maximize its expected\u0000log return while taking into account transaction fees. The portfolio allocation\u0000is parameterized through a softmax function, and at each time step, the\u0000gradient flow method leads to an ordinary differential equation whose solutions\u0000correspond to the updated allocations. This algorithm belongs to the large\u0000class of stochastic optimization procedures; we measure its efficiency by\u0000comparing our results to the mathematical theoretical values in a log-normal\u0000framework and to standard benchmarks from the 'old NYSE' dataset. For\u0000log-normal assets, the strategy learned by Onflow, with transaction costs at\u0000zero, mimics Markowitz's optimal portfolio and thus the best possible asset\u0000allocation strategy. Numerical experiments from the 'old NYSE' dataset show\u0000that Onflow leads to dynamic asset allocation strategies whose performances\u0000are: a) comparable to benchmark strategies such as Cover's Universal Portfolio\u0000or Helmbold et al. \"multiplicative updates\" approach when transaction costs are\u0000zero, and b) better than previous procedures when transaction costs are high.\u0000Onflow can even remain efficient in regimes where other dynamical allocation\u0000techniques do not work anymore. Therefore, as far as tested, Onflow appears to\u0000be a promising dynamic portfolio management strategy based on observed prices\u0000only and without any assumption on the laws of distributions of the underlying\u0000assets' returns. In particular it could avoid model risk when building a\u0000trading strategy.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"94 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138568467","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 General Framework for Portfolio Construction Based on Generative Models of Asset Returns 基于资产收益生成模型的投资组合构建总体框架

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-06 DOI: arxiv-2312.03294

Tuoyuan Cheng, Kan Chen

{"title":"A General Framework for Portfolio Construction Based on Generative Models of Asset Returns","authors":"Tuoyuan Cheng, Kan Chen","doi":"arxiv-2312.03294","DOIUrl":"https://doi.org/arxiv-2312.03294","url":null,"abstract":"In this paper, we present an integrated approach to portfolio construction\u0000and optimization, leveraging high-performance computing capabilities. We first\u0000explore diverse pairings of generative model forecasts and objective functions\u0000used for portfolio optimization, which are evaluated using\u0000performance-attribution models based on LASSO. We illustrate our approach using\u0000extensive simulations of crypto-currency portfolios, and we show that the\u0000portfolios constructed using the vine-copula generative model and the\u0000Sharpe-ratio objective function consistently outperform. To accommodate a wide\u0000array of investment strategies, we further investigate portfolio blending and\u0000propose a general framework for evaluating and combining investment strategies.\u0000We employ an extension of the multi-armed bandit framework and use value models\u0000and policy models to construct eclectic blended portfolios based on past\u0000performance. We consider similarity and optimality measures for value models\u0000and employ probability-matching (\"blending\") and a greedy algorithm\u0000(\"switching\") for policy models. The eclectic portfolios are also evaluated\u0000using LASSO models. We show that the value model utilizing cosine similarity\u0000and logit optimality consistently delivers robust superior performances. The\u0000extent of outperformance by eclectic portfolios over their benchmarks\u0000significantly surpasses that achieved by individual generative model-based\u0000portfolios over their respective benchmarks.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138548596","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

Striking the Balance: Life Insurance Timing and Asset Allocation in Financial Planning 平衡:理财规划中的寿险时机与资产配置

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-05 DOI: arxiv-2312.02943

An Chen, Giorgio Ferrari, Shihao Zhu

引用次数: 0

Optimal dividend payout with path-dependent drawdown constraint 具有路径依赖递减约束的最优股利支付

arXiv - QuantFin - Portfolio Management Pub Date : 2023-12-04 DOI: arxiv-2312.01668

Chonghu Guan, Jiacheng Fan, Zuo Quan Xu

引用次数: 0

Determining the Difference in Predictive Capabilities of ESG Raw Scores versus ESG Aggregated Scores on Annual Company Stock Returns And Volatility 确定ESG原始分数与ESG综合分数对年度公司股票收益和波动性预测能力的差异

arXiv - QuantFin - Portfolio Management Pub Date : 2023-11-30 DOI: arxiv-2312.00202

Zhi Chen, Zachary Feinstein, Ionut Florescu, Papa Momar Ndiaye

{"title":"Determining the Difference in Predictive Capabilities of ESG Raw Scores versus ESG Aggregated Scores on Annual Company Stock Returns And Volatility","authors":"Zhi Chen, Zachary Feinstein, Ionut Florescu, Papa Momar Ndiaye","doi":"arxiv-2312.00202","DOIUrl":"https://doi.org/arxiv-2312.00202","url":null,"abstract":"Investors are increasingly incorporating Environmental, Social, and\u0000Governance (ESG) ratings into their investment strategies to evaluate and\u0000manage potential risks and sustainability of companies. ESG ratings typically\u0000follow a hierarchical structure, where raw data points are progressively\u0000aggregated, leading to individual E, S, G scores and ultimately aggregating in\u0000a broad, consolidated ESG score. While many studies have investigated the\u0000relationship between stock performance and individual or overall ESG scores,\u0000few have used raw ESG data into their analyses. Therefore, this paper aims to\u0000explore the difference in predictive capabilities of ESG raw scores versus\u0000aggregated scores on annual company stock returns and volatility. Our findings\u0000reveal a trend where the predictive power is strongest at the raw data level,\u0000and it gradually weakens through successive stages of aggregation, with the\u0000overall scores exhibiting the weakest predictive capability. This result\u0000highlights the effectiveness of raw ESG data in capturing the complex dynamics\u0000between ESG factors and financial performance, making it the superior choice in\u0000further study.","PeriodicalId":501045,"journal":{"name":"arXiv - QuantFin - Portfolio Management","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138516966","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 Time Consistency and Utility Weighted Discount Rates 投资组合时间一致性和效用加权贴现率

arXiv - QuantFin - Portfolio Management Pub Date : 2023-11-27 DOI: arxiv-2402.05113

Oumar Mbodji, Traian A. Pirvu

引用次数: 0

Discretization of continuous-time arbitrage strategies in financial markets with fractional Brownian motion 具有分数布朗运动的金融市场连续时间套利策略的离散化

arXiv - QuantFin - Portfolio Management Pub Date : 2023-11-27 DOI: arxiv-2311.15635

Kerstin Lamert, Benjamin R. Auer, Ralf Wunderlich

引用次数: 0

Planning for the Efficient Updating of Mutual Fund Portfolios 有效更新共同基金投资组合的规划

arXiv - QuantFin - Portfolio Management Pub Date : 2023-11-27 DOI: arxiv-2311.16204

Tomás de la Rosa

引用次数: 0

Information Content of Financial Youtube Channel: Case Study of 3PROTV and Korean Stock Market Youtube财经频道的信息内容:以3PROTV与韩国股市为例

arXiv - QuantFin - Portfolio Management Pub Date : 2023-11-26 DOI: arxiv-2311.15247

HyeonJun Kim

引用次数: 0