定量金融
查看 最近的 文章
显示 2025年06月02日， 星期一 新的列表
- [1] arXiv:2505.24250 [中文pdf, pdf, html, 其他]
-
标题： 赢家与输家：基于动量的ESG投资组合跨期选择策略标题： Winners vs. Losers: Momentum-based Strategies with Intertemporal Choice for ESG Portfolios主题： 一般经济学 (econ.GN)
本文介绍了一种基于状态依赖动量框架，该框架整合了环境、社会和治理（ESG）制度转换与尾部风险感知的收益风险度量。通过动态规划方法并求解有限时域贝尔曼方程，我们构建了长短期动量投资组合，这些投资组合能够根据不断变化的ESG情绪制度进行调整。与基于历史回报的传统动量策略不同，我们的方法结合了稳定的尾部调整回报率（STAR）比率和Rachev比率，以更好地捕捉动荡市场中的下行风险。我们在三个资产类别——罗素3000股票、道琼斯30只股票和加密货币下应用了这一框架，在亲ESG和反ESG市场制度下均进行了测试。研究发现，在亲ESG市场制度下，ESG输家投资组合显著优于ESG赢家投资组合，这一反直觉的结果表明，市场对ESG情绪的过度反应导致了短期定价效率低下。这种模式在对尾部敏感的绩效指标下表现稳健，并且在两周的形成期和持有期内最为明显。我们的框架强调了ESG考量和情绪制度如何改变收益动态，为寻求在可持续性约束下实施响应式动量策略的投资者提供了实用指导。这些发现挑战了关于ESG投资的传统假设，并突显了在受监管信号、投资者流动性和行为偏差影响的环境中动态、制度意识强的投资组合构建的重要性。
This paper introduces a state-dependent momentum framework that integrates ESG regime switching with tail-risk-aware reward-risk metrics. Using a dynamic programming approach and solving a finite-horizon Bellman equation, we construct long-short momentum portfolios that adjust to changing ESG sentiment regimes. Unlike traditional momentum strategies based on historical returns, our approach incorporates the Stable Tail Adjusted Return ratio and Rachev ratio to better capture downside risk in turbulent markets. We apply this framework across three asset classes, Russell 3000 equities, Dow Jones~30 stocks, and cryptocurrencies, under both pro- and anti-ESG market regimes. We find that ESG-loser portfolios significantly outperform ESG-winner portfolios in pro-ESG regimes, a counterintuitive result suggesting that market overreaction to ESG sentiment creates short-term pricing inefficiencies. This pattern is robust across tail-sensitive performance metrics and is most pronounced under a two-week formation and holding period. Our framework highlights how ESG considerations and sentiment regimes alter return dynamics, offering practical guidance for investors seeking to implement responsive momentum strategies under sustainability constraints. These findings challenge conventional assumptions about ESG investing and underscore the importance of dynamic, regime-aware portfolio construction in environments shaped by regulatory signals, investor flows, and behavioral biases.
- [2] arXiv:2505.24435 [中文pdf, pdf, html, 其他]
-
标题： 基于二维偏微分方程的路径依赖期权定价与MPDATA标题： Path-dependent option pricing with two-dimensional PDE using MPDATA主题： 计算金融 (q-fin.CP)
本文讨论了一种简单而稳健的偏微分方程（PDE）方法，用于利用非振荡向前时间二阶MPDATA有限差分格式评估路径依赖型亚洲式期权。估值方法涉及通过变量替换将布莱克-默顿-斯科尔斯方程转化为一个传输问题，然后使用伪速度技术将扩散项表示为对流通量。因此，布莱克-默顿-斯科尔斯方程的所有项都用单一的高阶数值方案来一致地表示对流算子。我们详细说明了与先前研究中记录的普通工具MPDATA估值相比，在解决二维估值问题时所需的额外步骤。使用固定敲定测试案例，我们将解决方案与蒙特卡罗估值以及几何平均而非算术平均的近似解析解进行验证。分析强调了MPDATA校正步骤的重要性，这些步骤改进了解决方案相对于基础的一阶“迎风”步骤。引入的估值方案是稳健的：保守的、非振荡的和正定的；但同时清晰明了：显式的，具有直观的稳定性条件解释和流入/流出边界条件启发式方法。对于二维问题，MPDATA特别适合，因为它不是一个维度分裂方案。文档化的估值工作流程也构成了一个有用的二维案例，用于测试具有蒙特卡罗解和解析边界的对流方案。基于PyMPDATA包和Python的Numba即时编译器实现的引入估值工作流程，作为免费和开源软件提供。
In this paper, we discuss a simple yet robust PDE method for evaluating path-dependent Asian-style options using the non-oscillatory forward-in-time second-order MPDATA finite-difference scheme. The valuation methodology involves casting the Black-Merton-Scholes equation as a transport problem by first transforming it into a homogeneous advection-diffusion PDE via variable substitution, and then expressing the diffusion term as an advective flux using the pseudo-velocity technique. As a result, all terms of the Black-Merton-Sholes equation are consistently represented using a single high-order numerical scheme for the advection operator. We detail the additional steps required to solve the two-dimensional valuation problem compared to MPDATA valuations of vanilla instruments documented in a prior study. Using test cases employing fixed-strike instruments, we validate the solutions against Monte Carlo valuations, as well as against an approximate analytical solution in which geometric instead of arithmetic averaging is used. The analysis highlights the critical importance of the MPDATA corrective steps that improve the solution over the underlying first-order "upwind" step. The introduced valuation scheme is robust: conservative, non-oscillatory, and positive-definite; yet lucid: explicit in time, engendering intuitive stability-condition interpretation and inflow/outflow boundary-condition heuristics. MPDATA is particularly well suited for two-dimensional problems as it is not a dimensionally split scheme. The documented valuation workflow also constitutes a useful two-dimensional case for testing advection schemes featuring both Monte Carlo solutions and analytic bounds. An implementation of the introduced valuation workflow, based on the PyMPDATA package and the Numba Just-In-Time compiler for Python, is provided as free and open source software.
- [3] arXiv:2505.24457 [中文pdf, pdf, 其他]
-
标题： 全球健康饮食的气候影响和货币成本标题： Climate impacts and monetary costs of healthy diets worldwide主题： 一般经济学 (econ.GN)
全世界约有28亿人买不起维持健康饮食所需的最廉价食物。自2020年以来，粮农组织与世界银行已为所有国家发布《健康膳食的成本与可负担性》（CoAHD），被广泛用于指导社会保护、农业以及公共卫生和营养政策。在此，我们衡量了如何以最低的温室气体（GHG）排放获得健康的膳食，这可以进一步为迈向可持续发展目标的食物选择和政策决策提供信息。我们发现，2021年健康膳食的最低可能温室气体排放量为每天0.67千克CO2e（标准差=0.10），成本为6.95美元（标准差=1.86），而每个国家最便宜的食品组合会排放1.65千克CO2e（标准差=0.56），成本为3.68美元（标准差=0.75）。各国实际消费比例的食物构成的健康膳食会排放2.44千克CO2e（标准差=1.27），成本为9.96美元（标准差=4.92）。排放差异主要由动物源食品和淀粉类主食的选择驱动，其他食品类别仅有微小差异。结果表明，农业政策和食物选择的变化如何能以最经济有效的方式支持全球更健康、更可持续的膳食。
About 2.8 billion people worldwide cannot afford the least expensive foods required for a healthy diet. Since 2020, the Cost and Affordability of a Healthy Diet (CoAHD) has been published for all countries by FAO and the World Bank and is widely used to guide social protection, agricultural, and public health and nutrition policies. Here, we measure how healthy diets could be obtained with the lowest possible greenhouse gas (GHG) emissions, in ways that could further inform food choice and policy decisions toward sustainability goals. We find that the lowest possible GHG emissions for a healthy diet in 2021 would emit 0.67 kg CO2e (SD=0.10) and cost USD 6.95 (SD=1.86) per day, while each country's lowest-priced items would emit 1.65 kg CO2e (SD=0.56) and cost USD 3.68 (SD=0.75). Healthy diets with foods in proportions actually consumed in each country would emit 2.44 kg CO2e (SD=1.27) and cost USD 9.96 (SD=4.92). Differences in emissions are driven by item selection within animal-source foods, and starchy staples to a lesser extent, with only minor differences in other food groups. Results show how changes in agricultural policy and food choice can most cost-effectively support healthier and more sustainable diets worldwide.
- [4] arXiv:2505.24460 [中文pdf, pdf, 其他]
-
标题： 垄断竞争中的摩擦与福利标题： Frictions and Welfare in Monopolistic Competition主题： 一般经济学 (econ.GN)
在一个存在垄断竞争的异质性企业经济中，企业家和金融中介之间的信息不对称有时是否能够改善福利？ 我们通过构建一个银行在信息不对称情况下为企业家提供融资的模型来研究这个问题。 尽管总体生产率会随着信息摩擦而下降，但我们发现由于生产率与产品多样性之间的权衡，福利可以在适度的信息不对称水平下达到最大化。 此外，当金融摩擦严重时，适度的投入成本扭曲可以改善福利，因为这可以抵消由此导致的弱企业筛选效应。
In a heterogeneous firm economy with monopolistic competition, could informational asymmetries between entrepreneurs and financial intermediaries sometimes improve welfare? We study this question by developing a model where banks finance entrepreneurs under asymmetric information. While aggregate productivity decreases with informational frictions, we find that welfare can be maximized at intermediate levels of information asymmetry due to a trade-off between productivity and product variety. Additionally, moderate input cost distortions can improve welfare when financial frictions are severe by offsetting the resulting weak firm selection.
新提交 (展示 4 之 4 条目 )
- [5] arXiv:2505.23842 (交叉列表自 cs.CL) [中文pdf, pdf, html, 其他]
-
标题： LLM摘要中的文档估值：集群Shapley方法标题： Document Valuation in LLM Summaries: A Cluster Shapley Approach主题： 计算与语言 (cs.CL) ; 一般经济学 (econ.GN)
大型语言模型（LLMs）越来越多地被用于检索和汇总来自多个来源的内容的系统中，例如搜索引擎和人工智能助手。 尽管这些模型通过生成连贯的摘要提升了用户体验，但它们模糊了原始内容创作者的贡献，引发了关于功劳归属和补偿的问题。 我们解决了评估LLM生成的摘要中使用的单个文档价值的挑战。 我们提议使用Shapley值，这是一种基于每篇文档边际贡献来分配功劳的游戏论方法。 虽然理论上很有吸引力，但在大规模计算Shapley值成本高昂。 因此，我们提出了Cluster Shapley，一种利用文档之间语义相似性的高效近似算法。 通过使用基于LLM的嵌入聚类文档并在集群级别计算Shapley值，我们的方法显著减少了计算量，同时保持了功劳归属的质量。 我们在亚马逊产品评论的摘要任务中展示了我们的方法。 Cluster Shapley显著降低了计算复杂度，同时保持了高精度，在效率前沿方面优于基线方法，例如蒙特卡洛抽样和Kernel SHAP。 我们的方法与所用的具体LLM、所用的摘要过程以及评估程序无关，这使其广泛适用于各种摘要设置。
Large Language Models (LLMs) are increasingly used in systems that retrieve and summarize content from multiple sources, such as search engines and AI assistants. While these models enhance user experience by generating coherent summaries, they obscure the contributions of original content creators, raising concerns about credit attribution and compensation. We address the challenge of valuing individual documents used in LLM-generated summaries. We propose using Shapley values, a game-theoretic method that allocates credit based on each document's marginal contribution. Although theoretically appealing, Shapley values are expensive to compute at scale. We therefore propose Cluster Shapley, an efficient approximation algorithm that leverages semantic similarity between documents. By clustering documents using LLM-based embeddings and computing Shapley values at the cluster level, our method significantly reduces computation while maintaining attribution quality. We demonstrate our approach to a summarization task using Amazon product reviews. Cluster Shapley significantly reduces computational complexity while maintaining high accuracy, outperforming baseline methods such as Monte Carlo sampling and Kernel SHAP with a better efficient frontier. Our approach is agnostic to the exact LLM used, the summarization process used, and the evaluation procedure, which makes it broadly applicable to a variety of summarization settings.
- [6] arXiv:2505.23928 (交叉列表自 hep-th) [中文pdf, pdf, html, 其他]
-
标题： 随机表面的动力学与多重分形标度标题： Critical Dynamics of Random Surfaces and Multifractal Scaling评论： 19页，1幅图。是arXiv:2409.05547 [hep-th]的后续论文。主题： 高能物理 - 理论 (hep-th) ; 统计力学 (cond-mat.stat-mech) ; 数学金融 (q-fin.MF) ; 统计金融 (q-fin.ST)
研究了定义在随机曲面上的共形场论的动力学，超越了总体面积和亏格的动力学。 发现物理时间中序参量的演化是一种多重分形随机游走。 因此，序参量的时间变化的高阶矩表现出多重分形标度。 计算并用随机曲面上的Ising模型、3态Potts模型和广义最小模型的例子来说明了一系列Hurst指数。 确定了一些可以复制金融市场上观察到的多重分形标度的模型。
The critical dynamics of conformal field theories on random surfaces is investigated beyond the dynamics of the overall area and the genus. It is found that the evolution of the order parameter in physical time is a multifractal random walk. Accordingly, the higher moments of time variations of the order parameter exhibit multifractal scaling. The series of Hurst exponents is computed and illustrated with the examples of the Ising-, 3-state-Potts-, and general minimal models on a random surface. Models are identified that can replicate the observed multifractal scaling in financial markets.
- [7] arXiv:2505.24078 (交叉列表自 stat.AP) [中文pdf, pdf, html, 其他]
-
标题： 北卡罗来纳大学系统中的性别工资差距估计标题： Estimation of Gender Wage Gap in the University of North Carolina System主题： 应用 (stat.AP) ; 一般经济学 (econ.GN)
尽管经历了数十年的运动，学术界仍然面临着性别薪酬公平这一悬而未决的挑战。 然而，先前的研究主要依赖于描述性回归，对因果分析的探索相对不足。 本研究利用参数和非参数因果推断方法，考察了北卡罗来纳大学系统内终身教职员工的性别薪酬差异。 特别是，我们采用了倾向得分匹配和因果森林方法，以控制大学类型、学科、职称、工作年限以及学术生产力指标等因素，估计性别对学术薪酬的因果影响。 结果显示，平均而言，女性教授的薪酬比具有相似资历和职位的男性同事低约6%。
Gender pay equity remains an open challenge in academia despite decades of movements. Prior studies, however, have relied largely on descriptive regressions, leaving causal analysis underexplored. This study examines gender-based wage disparities among tenure-track faculty in the University of North Carolina system using both parametric and non-parametric causal inference methods. In particular, we employed propensity score matching and causal forests to estimate the causal effect of gender on academic salary while controlling for university type, discipline, titles, working years, and scholarly productivity metrics. The results indicate that on average female professors earn approximately 6% less than their male colleagues with similar qualifications and positions.
- [8] arXiv:2505.24159 (交叉列表自 eess.SY) [中文pdf, pdf, html, 其他]
-
标题： 基于因果关系的现代电力系统中能源、储备和输电定价与成本分摊框架标题： A Causation-Based Framework for Pricing and Cost Allocation of Energy, Reserves, and Transmission in Modern Power Systems主题： 系统与控制 (eess.SY) ; 理论经济学 (econ.TH) ; 优化与控制 (math.OC) ; 计算金融 (q-fin.CP) ; 证券定价 (q-fin.PR)
电力系统的脆弱性日益增加，迫切需要操作备用容量来应对发电机停机、线路故障和负荷突变等紧急情况。与受消费者需求驱动的能源成本不同，操作备用容量的成本源于处理最严重的可信紧急情况——从而引出了一个问题：如何通过有效的定价机制分配这些成本？ 作为对之前报告方案的替代，本文提出了一种基于紧急情况约束的能量和备用调度模型的新电价框架。 该框架的主要特点包括一种新颖的安全费用机制，以及对上调备用容量、下调备用容量和输电服务价格的明确定义。 这些特性确保了更全面和高效的成本反映市场运作。 此外，所提出的节点电价方案能够保证收入充足性和中立性，同时根据成本因果原则促进发电厂的可靠性激励。 该框架的一个显著方面是输电资产的经济激励，这些资产根据其在所有紧急情况下输送能源和备用容量的能力获得报酬。 两个案例研究的数值结果展示了所提出的定价方案的性能。
The increasing vulnerability of power systems has heightened the need for operating reserves to manage contingencies such as generator outages, line failures, and sudden load variations. Unlike energy costs, driven by consumer demand, operating reserve costs arise from addressing the most critical credible contingencies - prompting the question: how should these costs be allocated through efficient pricing mechanisms? As an alternative to previously reported schemes, this paper presents a new causation-based pricing framework for electricity markets based on contingency-constrained energy and reserve scheduling models. Major salient features include a novel security charge mechanism along with the explicit definition of prices for up-spinning reserves, down-spinning reserves, and transmission services. These features ensure more comprehensive and efficient cost-reflective market operations. Moreover, the proposed nodal pricing scheme yields revenue adequacy and neutrality while promoting reliability incentives for generators based on the cost-causation principle. An additional salient aspect of the proposed framework is the economic incentive for transmission assets, which are remunerated based on their use to deliver energy and reserves across all contingency states. Numerical results from two case studies illustrate the performance of the proposed pricing scheme.
- [9] arXiv:2505.24284 (交叉列表自 cs.CR) [中文pdf, pdf, html, 其他]
-
标题： 交易接近性：一种基于图的区块链欺诈预防方法标题： Transaction Proximity: A Graph-Based Approach to Blockchain Fraud Prevention主题： 密码学与安全 (cs.CR) ; 计算工程、金融与科学 (cs.CE) ; 一般经济学 (econ.GN)
本文介绍了一种针对公共区块链的防欺诈访问验证系统，利用了两个互补的概念：“交易邻近性”，即衡量交易图中钱包之间的距离；以及“易获得身份（EAIs）”，即与中心化交易所存在直接交易连接的钱包。 认识到传统方法如黑名单（反应式、缓慢）和严格的白名单（侵犯隐私、阻碍采用）的局限性，我们提出了一种通过分析交易模式来识别与中心化交易所有密切联系的钱包的系统。 我们对以太坊区块链的有向图分析显示，56% 的大额 USDC 钱包（终身最大余额超过 10,000 美元）是 EAI，并且 88% 距离一个 EAI 不超过一个交易跳。对于超过 2,000 美元的交易，91% 涉及至少一个 EAI。 关键的是，对过去攻击的分析表明，83% 的已知攻击者地址不是 EAIs，其中 21% 距离任何受监管的交易所超过五个跳点。 我们提出了三种实现方法，具有不同的 gas 成本和隐私权衡，证明基于 EAI 的访问控制可能防止大多数此类事件，同时保留区块链的开放性。 重要的是，我们的方法不会限制访问或共享个人可识别信息，但它为协议提供了信息，使其可以根据具体需求实施自己的验证或风险评分系统。 这种折衷方案能够在保持开放区块链核心价值的同时实现程序化的合规性。
This paper introduces a fraud-deterrent access validation system for public blockchains, leveraging two complementary concepts: "Transaction Proximity", which measures the distance between wallets in the transaction graph, and "Easily Attainable Identities (EAIs)", wallets with direct transaction connections to centralized exchanges. Recognizing the limitations of traditional approaches like blocklisting (reactive, slow) and strict allow listing (privacy-invasive, adoption barriers), we propose a system that analyzes transaction patterns to identify wallets with close connections to centralized exchanges. Our directed graph analysis of the Ethereum blockchain reveals that 56% of large USDC wallets (with a lifetime maximum balance greater than \$10,000) are EAI and 88% are within one transaction hop of an EAI. For transactions exceeding \$2,000, 91% involve at least one EAI. Crucially, an analysis of past exploits shows that 83% of the known exploiter addresses are not EAIs, with 21% being more than five hops away from any regulated exchange. We present three implementation approaches with varying gas cost and privacy tradeoffs, demonstrating that EAI-based access control can potentially prevent most of these incidents while preserving blockchain openness. Importantly, our approach does not restrict access or share personally identifiable information, but it provides information for protocols to implement their own validation or risk scoring systems based on specific needs. This middle-ground solution enables programmatic compliance while maintaining the core values of open blockchain.
- [10] arXiv:2505.24650 (交叉列表自 cs.CE) [中文pdf, pdf, html, 其他]
-
标题： 超越黑箱：金融领域LLM的可解释性标题： Beyond the Black Box: Interpretability of LLMs in FinanceHariom Tatsat (Barclays), Ariye Shater (Barclays)评论： 28页，15幅图主题： 计算工程、金融与科学 (cs.CE) ; 机器学习 (cs.LG) ; 统计金融 (q-fin.ST)
大型语言模型（LLMs）在金融服务的众多任务中展现出显著能力，包括报告生成、聊天机器人、情感分析、监管合规、投资顾问、金融知识检索和摘要。 然而，它们内在的复杂性和缺乏透明性带来了重大挑战，尤其是在高度受监管的金融领域，可解释性、公平性和责任性至关重要。 据我们所知，本文首次在金融领域应用了通过机械式可解释性理解和利用LLMs内部工作机制的方法，解决了AI系统对透明度和控制需求的紧迫问题。 机械式可解释性是理解LLMs行为的最直观且透明的方式，通过对这些模型内部机制进行逆向工程实现。 通过剖析模型中的激活和电路，它提供了关于特定特征或组件如何影响预测的见解——不仅能够观察模型行为，还能对其进行修改。 在本文中，我们探索了机械式可解释性的理论方面，并通过一系列金融应用场景和实验展示了其实际相关性，包括在交易策略、情感分析、偏见和幻觉检测中的应用。 尽管尚未广泛采用，但随着LLMs的普及，机械式可解释性预计会变得越来越重要。 先进的可解释性工具可以确保AI系统保持道德、透明并与不断发展的金融法规保持一致。 在本文中，我们特别强调了这些技术如何帮助满足监管和合规方面的可解释性要求——既应对当前需求，又预见全球金融监管机构未来的期望。
Large Language Models (LLMs) exhibit remarkable capabilities across a spectrum of tasks in financial services, including report generation, chatbots, sentiment analysis, regulatory compliance, investment advisory, financial knowledge retrieval, and summarization. However, their intrinsic complexity and lack of transparency pose significant challenges, especially in the highly regulated financial sector, where interpretability, fairness, and accountability are critical. As far as we are aware, this paper presents the first application in the finance domain of understanding and utilizing the inner workings of LLMs through mechanistic interpretability, addressing the pressing need for transparency and control in AI systems. Mechanistic interpretability is the most intuitive and transparent way to understand LLM behavior by reverse-engineering their internal workings. By dissecting the activations and circuits within these models, it provides insights into how specific features or components influence predictions - making it possible not only to observe but also to modify model behavior. In this paper, we explore the theoretical aspects of mechanistic interpretability and demonstrate its practical relevance through a range of financial use cases and experiments, including applications in trading strategies, sentiment analysis, bias, and hallucination detection. While not yet widely adopted, mechanistic interpretability is expected to become increasingly vital as adoption of LLMs increases. Advanced interpretability tools can ensure AI systems remain ethical, transparent, and aligned with evolving financial regulations. In this paper, we have put special emphasis on how these techniques can help unlock interpretability requirements for regulatory and compliance purposes - addressing both current needs and anticipating future expectations from financial regulators globally.
- [11] arXiv:2505.24831 (交叉列表自 physics.pop-ph) [中文pdf, pdf, html, 其他]
-
标题： 通过价格相关性网络的稳定聚类优化加密货币投资组合标题： Optimising cryptocurrency portfolios through stable clustering of price correlation networks评论： 欢迎评论主题： 流行物理 (physics.pop-ph) ; 物理与社会 (physics.soc-ph) ; 投资组合管理 (q-fin.PM)
由于其不受监管的性质和固有的波动性，新兴的加密货币市场为投资带来了独特的挑战。 然而，可以探索集体价格走势，以最小的风险最大化利润，使用投资组合。 在本文中，我们开发了一个技术框架，利用每日收盘价的历史数据，并结合网络分析、价格预测和投资组合理论，来识别在不确定性下构建盈利投资组合的加密货币。 我们的方法利用 Louvain 网络社区算法和共识聚类来检测高度相关的加密货币的稳健且时间上稳定的聚类，从中选择所选的加密货币。 使用 ARIMA 模型的价格预测步骤保证了投资组合在投资期限内最多 14 天的表现良好。 为期五年的实证分析表明，尽管加密市场波动性很高，但隐藏的价格模式可以有效地被利用来生成始终盈利且与时间无关的加密货币投资组合。
The emerging cryptocurrency market presents unique challenges for investment due to its unregulated nature and inherent volatility. However, collective price movements can be explored to maximise profits with minimal risk using investment portfolios. In this paper, we develop a technical framework that utilises historical data on daily closing prices and integrates network analysis, price forecasting, and portfolio theory to identify cryptocurrencies for building profitable portfolios under uncertainty. Our method utilises the Louvain network community algorithm and consensus clustering to detect robust and temporally stable clusters of highly correlated cryptocurrencies, from which the chosen cryptocurrencies are selected. A price prediction step using the ARIMA model guarantees that the portfolio performs well for up to 14 days in the investment horizon. Empirical analysis over a 5-year period shows that despite the high volatility in the crypto market, hidden price patterns can be effectively utilised to generate consistently profitable, time-agnostic cryptocurrency portfolios.
交叉提交 (展示 7 之 7 条目 )
- [12] arXiv:2405.20912 (替换) [中文pdf, pdf, html, 其他]
-
标题： 一种针对机场行李处理任务中随机旅行时间的团队形成与路由优化的分支定价剪切与切换方法标题： A Branch-Price-Cut-And-Switch Approach for Optimizing Team Formation and Routing for Airport Baggage Handling Tasks with Stochastic Travel Times主题： 一般经济学 (econ.GN) ; 优化与控制 (math.OC)
在机场运营中，最优地分配专门人员从事行李处理任务对于设计资源高效的工作流程起着至关重要的作用。需要组建由不同资质工人组成的团队，并将装卸任务分配给他们。每个任务都有一个时间窗口，在此窗口内可以开始并应完成。违反这些时间限制将对运营商造成严重的经济损失。实际上，这一过程的各个组成部分都受到不确定性的影响。我们假设停机坪上的旅行时间具有随机性，从而考虑上述问题。我们提出了两种二元规划形式来建模该问题，并提出了一种称为“分支-定价-切割-切换”的新型解决方案方法，在其中我们动态切换两个主问题模型。此外，我们使用精确分离方法来识别违反的秩-1 Chvátal-Gomory切割，并利用依赖于任务完成时间的有效分枝规则。我们在基于一家欧洲主要枢纽机场真实数据生成的实例上测试了算法，规划范围可达两小时，每小时30个航班，并有三种可用的任务执行模式可供选择。我们的结果显示，我们的算法能够显著优于现有的解决方案方法。此外，显式考虑随机旅行时间允许更有效地利用现有劳动力，同时确保行李处理操作员的服务水平稳定。
In airport operations, optimally using dedicated personnel for baggage handling tasks plays a crucial role in the design of resource-efficient processes. Teams of workers with different qualifications must be formed, and loading or unloading tasks must be assigned to them. Each task has a time window within which it can be started and should be finished. Violating these temporal restrictions incurs severe financial penalties for the operator. In practice, various components of this process are subject to uncertainties. We consider the aforementioned problem under the assumption of stochastic travel times across the apron. We present two binary program formulations to model the problem at hand and propose a novel solution approach that we call Branch-Price-Cut-and-Switch, in which we dynamically switch between two master problem formulations. Furthermore, we use an exact separation method to identify violated rank-1 Chv\'atal-Gomory cuts and utilize an efficient branching rule relying on task finish times. We test the algorithm on instances generated based on real-world data from a major European hub airport with a planning horizon of up to two hours, 30 flights per hour, and three available task execution modes to choose from. Our results indicate that our algorithm is able to significantly outperform existing solution approaches. Moreover, an explicit consideration of stochastic travel times allows for solutions that utilize the available workforce more efficiently, while simultaneously guaranteeing a stable service level for the baggage handling operator.
- [13] arXiv:2411.03502 (替换) [中文pdf, pdf, html, 其他]
-
标题： 全球粮食生产和贸易多层网络中的自适应冲击补偿标题： Adaptive Shock Compensation in the Multi-layer Network of Global Food Production and Trade主题： 一般经济学 (econ.GN)
全球粮食生产和贸易网络高度动态，尤其是在应对短缺时，各国会调整供应策略。 本研究考察了来自192个国家的123种农食产品的调整，产生了23616个粮食短缺的个体情景，并校准了一个多层网络模型以理解冲击的传播。 我们分析了诸如增加进口、提高生产或替换食品项目等冲击缓解措施。 我们的研究结果显示，这些措施可能导致溢出效应，可能加剧粮食不平等：印度大米冲击导致低人类发展指数（HDI）国家的稻米损失增加了5.8 %，而在高HDI国家则减少了14.2 %。 考虑到多个相互作用的冲击会导致全球粮食生产网络中总可用食物量高达12 %的超加性损失。 此框架使我们能够识别出造成重大系统风险并降低全球粮食供应韧性的冲击组合。
Global food production and trade networks are highly dynamic, especially in response to shortages when countries adjust their supply strategies. In this study, we examine adjustments across 123 agri-food products from 192 countries resulting in 23616 individual scenarios of food shortage, and calibrate a multi-layer network model to understand the propagation of the shocks. We analyze shock mitigation actions, such as increasing imports, boosting production, or substituting food items. Our findings indicate that these lead to spillover effects potentially exacerbating food inequality: an Indian rice shock resulted in a 5.8 % increase in rice losses in countries with a low Human Development Index (HDI) and a 14.2 % decrease in those with a high HDI. Considering multiple interacting shocks leads to super-additive losses of up to 12 % of the total available food volume across the global food production network. This framework allows us to identify combinations of shocks that pose substantial systemic risks and reduce the resilience of the global food supply.
- [14] arXiv:2412.07223 (替换) [中文pdf, pdf, 其他]
-
标题： 基于反向传播神经网络和遗传算法的整合波动率预测标题： A Consolidated Volatility Prediction with Back Propagation Neural Network and Genetic Algorithm评论： 6页，7幅图，1张表，论文将由IEEE出版于2024年第三届图像处理、计算机视觉与机器学习国际会议（ICICML 2024）上（V4版）。主题： 计算金融 (q-fin.CP) ; 机器学习 (cs.LG) ; 神经与进化计算 (cs.NE)
本文提供了一种独特的利用人工智能算法预测新兴股票市场波动的方法。 传统上，股票波动率来源于历史波动率、蒙特卡洛模拟和隐含波动率等。 在本文中，作者设计了一个结合反向传播神经网络和遗传算法的综合模型，用于预测新兴股票市场的未来波动率，并发现其结果非常准确且误差较低。
This paper provides a unique approach with AI algorithms to predict emerging stock markets volatility. Traditionally, stock volatility is derived from historical volatility,Monte Carlo simulation and implied volatility as well. In this paper, the writer designs a consolidated model with back-propagation neural network and genetic algorithm to predict future volatility of emerging stock markets and found that the results are quite accurate with low errors.
- [15] arXiv:2501.16772 (替换) [中文pdf, pdf, html, 其他]
-
标题： 金融市场在几分钟到几十年的时间尺度上的趋势和逆转标题： Trends and Reversion in Financial Markets on Time Scales from Minutes to Decades评论： 38页，10幅图。增加了额外的解释、参考文献，并进行了小修正。主题： 统计金融 (q-fin.ST) ; 统计力学 (cond-mat.stat-mech) ; 数学金融 (q-fin.MF) ; 交易与市场微观结构 (q-fin.TR)
我们通过从分钟到几十年的时间范围，实证分析了金融市场趋势的反转。 分析涵盖了股票、利率、货币和商品，并结合了14年的期货逐笔交易数据、30年的每日期货价格、330年的月度资产价格以及从中世纪以来的年度金融数据。 跨资产类别，我们发现市场在从几个小时到几年的时间尺度上处于趋势状态，而在较短和较长的时间尺度上则处于反转状态。 在趋势状态下，弱趋势倾向于持续，这可以通过投资者的羊群行为来解释。 然而，在这个状态下，趋势往往会在变得足够强而具有统计显著性之前反转，这可以被解释为资产价格回归其内在价值。 在反转状态下，我们发现了相反的模式：弱趋势倾向于反转，而那些变得具有统计显著性的趋势则倾向于持续。 我们的结果为金融市场的理论模型提供了一组实证检验。 我们用最近提出的格子气体模型来解释这些结果，其中格子代表交易者的社会网络，气体分子代表金融资产的份额，有效市场对应于临界点。 如果该模型准确的话，那么在从1小时到几天的时间尺度上，格子气体必须接近这个临界点，且相关时间约为几年。
We empirically analyze the reversion of financial market trends with time horizons ranging from minutes to decades. The analysis covers equities, interest rates, currencies and commodities and combines 14 years of futures tick data, 30 years of daily futures prices, 330 years of monthly asset prices, and yearly financial data since medieval times. Across asset classes, we find that markets are in a trending regime on time scales that range from a few hours to a few years, while they are in a reversion regime on shorter and longer time scales. In the trending regime, weak trends tend to persist, which can be explained by herding behavior of investors. However, in this regime trends tend to revert before they become strong enough to be statistically significant, which can be interpreted as a return of asset prices to their intrinsic value. In the reversion regime, we find the opposite pattern: weak trends tend to revert, while those trends that become statistically significant tend to persist. Our results provide a set of empirical tests of theoretical models of financial markets. We interpret them in the light of a recently proposed lattice gas model, where the lattice represents the social network of traders, the gas molecules represent the shares of financial assets, and efficient markets correspond to the critical point. If this model is accurate, the lattice gas must be near this critical point on time scales from 1 hour to a few days, with a correlation time of a few years.
- [16] arXiv:2505.23336 (替换) [中文pdf, pdf, 其他]
-
标题： 政治自由的分配后果：转型国家的不平等标题： Distributional Consequences of Political Freedom: Inequality in Transition Countries期刊参考： 《共产主义与后共产主义研究》（2025）主题： 一般经济学 (econ.GN)
本文探讨了1991年至2016年间中东欧和中亚地区前社会主义国家收入不平等的起源。 目标是分析民主与收入不平等之间的关系。 在先前的研究中，这一主题导致了模棱两可的结果，尤其是在我们关注的国家群体背景下。 我们考察了民主化进程是否在整个研究期间伴随着收入分配的变化，并对其对个人收入十分位数的影响进行评估，以确定谁从新制度中受益最多。 获得的结果使我们能够确认，在20世纪90年代，民主化与收入不平等之间的实际关系不存在，或者至多是虚幻的，但在2001年至2016年期间，这种关系存在、相关且具有亲平等性。 在那段时期，民主制度的发展至少使收入分配下部80%的人受益，尤其以牺牲顶层十分位数的总收入份额为代价。 这些结果证实了民主化对前社会主义国家较低收入十分位数的份额产生了积极影响。
This article addresses the origins of income inequality in post-socialist countries from Central and Eastern Europe and Central Asia, from 1991 to 2016. The aim is to analyze the relationship between democracy and income inequality. In previous studies, this topic has led to ambiguous findings, especially in the context of the group of countries we are focusing on. We examine whether the process of democratization cooccurred with changes in income distribution over the entire period under study, and its impact on individual income deciles to determine who benefited most from the new system. The obtained results allowed us to confirm that the actual relationship between democratization and income inequality did not exist, or at most was illusory in the 1990s, but it was present, relevant, and had a proequality character between 2001 and 2016. During that period, the development of the democratic system benefited at least 80\% of the lower part of the income distribution, at the expense especially of the top deciles share of total income. Those results confirmed that democratization positively affected the shares of lower income deciles in postsocialist countries.
- [17] arXiv:2212.11833 (替换) [中文pdf, pdf, html, 其他]
-
标题： 时变扩散模型中实现方差估计的有效抽样方法标题： Efficient Sampling for Realized Variance Estimation in Time-Changed Diffusion ModelsTimo Dimitriadis, Roxana Halbleib, Jeannine Polivka, Jasper Rennspies, Sina Streicher, Axel Friedrich Wolter主题： 计量经济学 (econ.EM) ; 统计理论 (math.ST) ; 风险管理 (q-fin.RM)
本文分析了在固有时空中抽样日内收益率对实现方差（RV）估计量的益处。 我们在有限样本下理论证明，在允许的抽样信息条件下，RV估计量在以下两种情况下效率最高：一是击中时间抽样，即每当价格变化达到预设阈值时进行抽样；二是基于观察到的交易和估计的点方差组合的新概念——实际营业时间抽样。 该分析基于资产价格遵循随时间变化的扩散过程，并且这种扩散过程被跳跃过程所时间变换的假设。这提供了一个灵活的模型，允许杠杆规格和Hawkes型跳跃过程，并分别捕获实证中变化的交易强度和点方差过程，这对于分离抽样方案的驱动因素尤为重要。 广泛的模拟验证了我们的理论结果，并表明对于低噪声水平，击中时间抽样仍然更优，而对于不断增加的噪声水平，实际营业时间成为经验上最有效的抽样方案。 股票数据的应用提供了使用这些固有抽样方案构建更有效RV估计量以及提高预测性能的实证证据。
This paper analyzes the benefits of sampling intraday returns in intrinsic time for the realized variance (RV) estimator. We theoretically show in finite samples that depending on the permitted sampling information, the RV estimator is most efficient under either hitting time sampling that samples whenever the price changes by a pre-determined threshold, or under the new concept of realized business time that samples according to a combination of observed trades and estimated tick variance. The analysis builds on the assumption that asset prices follow a diffusion that is time-changed with a jump process that separately models the transaction times. This provides a flexible model that allows for leverage specifications and Hawkes-type jump processes and separately captures the empirically varying trading intensity and tick variance processes, which are particularly relevant for disentangling the driving forces of the sampling schemes. Extensive simulations confirm our theoretical results and show that for low levels of noise, hitting time sampling remains superior while for increasing noise levels, realized business time becomes the empirically most efficient sampling scheme. An application to stock data provides empirical evidence for the benefits of using these intrinsic sampling schemes to construct more efficient RV estimators as well as for an improved forecast performance.
- [18] arXiv:2502.19305 (替换) [中文pdf, pdf, html, 其他]
-
标题： 在丰富但嘈杂的财务图中检测企业欺诈标题： Corporate Fraud Detection in Rich-yet-Noisy Financial Graph主题： 机器学习 (cs.LG) ; 人工智能 (cs.AI) ; 风险管理 (q-fin.RM) ; 统计金融 (q-fin.ST)
企业欺诈检测旨在自动识别从事不当活动的公司，例如虚假财务报表或非法内幕交易。 以往基于学习的方法未能有效整合公司网络中的丰富交互信息。 为了解决这一问题，我们收集了中国18年的财务记录，形成三个带有欺诈标签的图数据集。 我们分析了财务图的特征，强调了两个显著的问题：(1) 信息过载：（噪声）非公司节点对公司的主导地位阻碍了图卷积网络 (GCN) 中的消息传递过程；以及 (2) 隐蔽欺诈：在收集的数据中存在大量可能未被发现的违规行为。 隐蔽欺诈问题会在训练数据集中引入噪声标签，并损害欺诈检测结果。 为了解决这些挑战，我们提出了一种新颖的基于图的方法，即具有鲁棒两阶段学习的知识增强型 GCN (${\rm KeGCN}_{R}$)，该方法利用知识图嵌入来减轻信息过载并有效学习丰富的表示形式。 所提出的模型采用两阶段学习方法以增强对隐蔽欺诈的鲁棒性。 广泛的实验结果不仅确认了交互的重要性，还展示了${\rm KeGCN}_{R}$在欺诈检测效果和鲁棒性方面相对于多个强大基线的优势。
Corporate fraud detection aims to automatically recognize companies that conduct wrongful activities such as fraudulent financial statements or illegal insider trading. Previous learning-based methods fail to effectively integrate rich interactions in the company network. To close this gap, we collect 18-year financial records in China to form three graph datasets with fraud labels. We analyze the characteristics of the financial graphs, highlighting two pronounced issues: (1) information overload: the dominance of (noisy) non-company nodes over company nodes hinders the message-passing process in Graph Convolution Networks (GCN); and (2) hidden fraud: there exists a large percentage of possible undetected violations in the collected data. The hidden fraud problem will introduce noisy labels in the training dataset and compromise fraud detection results. To handle such challenges, we propose a novel graph-based method, namely, Knowledge-enhanced GCN with Robust Two-stage Learning (${\rm KeGCN}_{R}$), which leverages Knowledge Graph Embeddings to mitigate the information overload and effectively learns rich representations. The proposed model adopts a two-stage learning method to enhance robustness against hidden frauds. Extensive experimental results not only confirm the importance of interactions but also show the superiority of ${\rm KeGCN}_{R}$ over a number of strong baselines in terms of fraud detection effectiveness and robustness.
- [19] arXiv:2504.03743 (替换) [中文pdf, pdf, html, 其他]
-
标题： 通过 Wasserstein 约束对有限理性决策进行建模标题： Modelling bounded rational decision-making through Wasserstein constraints评论： 已被RLDM 2025接受主题： 机器学习 (cs.LG) ; 人工智能 (cs.AI) ; 计算机科学与博弈论 (cs.GT) ; 一般经济学 (econ.GN)
通过受信息约束处理的有界理性决策建模为在强化学习框架内表示偏离理性提供了原则性方法，同时仍将决策视为一种优化过程。 然而，现有的方法通常基于熵、Kullback-Leibler 散度或互信息。 在这项工作中，我们强调了这些方法在处理序数动作空间时存在的问题。 具体来说，熵假设均匀的先验信念，忽略了先验偏差对决策的影响。 KL-散度解决了这个问题，但没有“动作接近性”的概念，并且还具有一些众所周知的潜在不理想特性，例如缺乏对称性，并且要求分布具有相同的支撑集（例如，所有动作都有正概率）。 互信息往往难以估计。 在这里，我们提出了一种利用 Wasserstein 距离来模拟有界理性的 RL 智能体的替代方法。 这种方法克服了上述问题。 至关重要的是，该方法考虑了序数动作的接近性，建模了智能体决策中的“粘滞性”以及不太可能迅速切换到远离的动作，同时支持低概率动作、零支撑先验分布，并且易于直接计算。
Modelling bounded rational decision-making through information constrained processing provides a principled approach for representing departures from rationality within a reinforcement learning framework, while still treating decision-making as an optimization process. However, existing approaches are generally based on Entropy, Kullback-Leibler divergence, or Mutual Information. In this work, we highlight issues with these approaches when dealing with ordinal action spaces. Specifically, entropy assumes uniform prior beliefs, missing the impact of a priori biases on decision-makings. KL-Divergence addresses this, however, has no notion of "nearness" of actions, and additionally, has several well known potentially undesirable properties such as the lack of symmetry, and furthermore, requires the distributions to have the same support (e.g. positive probability for all actions). Mutual information is often difficult to estimate. Here, we propose an alternative approach for modeling bounded rational RL agents utilising Wasserstein distances. This approach overcomes the aforementioned issues. Crucially, this approach accounts for the nearness of ordinal actions, modeling "stickiness" in agent decisions and unlikeliness of rapidly switching to far away actions, while also supporting low probability actions, zero-support prior distributions, and is simple to calculate directly.
- [20] arXiv:2505.23432 (替换) [中文pdf, pdf, html, 其他]
-
标题： 工作环境中的人工智能-人类集成的数学框架标题： A Mathematical Framework for AI-Human Integration in Work评论： 本文将于2025年ICML会议上发表。主题： 人工智能 (cs.AI) ; 计算机与社会 (cs.CY) ; 一般经济学 (econ.GN)
生成式人工智能（GenAI）工具的快速兴起引发了关于它们在不同工作场景中补充或取代人类工作者角色的争论。 我们提出了一种数学框架来建模工作、工人以及工人与工作的匹配度，并引入了对技能的新分解方法，将技能分为决策层面和操作层面的子技能，以反映人类和GenAI的互补优势。 我们分析了子技能能力的变化如何影响工作成功，识别了成功概率发生急剧变化的条件。 我们还确立了在何种条件下结合具有互补子技能的工人显著优于依赖单一工人。 这解释了诸如生产力压缩现象，即GenAI辅助对低技能工人带来的更大收益。 我们使用O*NET和Big-Bench Lite的数据演示了该框架的实际应用，通过子技能划分方法将真实世界数据与我们的模型对齐。 我们的结果显示了GenAI何时以及如何补充而非取代人类技能。
The rapid rise of Generative AI (GenAI) tools has sparked debate over their role in complementing or replacing human workers across job contexts. We present a mathematical framework that models jobs, workers, and worker-job fit, introducing a novel decomposition of skills into decision-level and action-level subskills to reflect the complementary strengths of humans and GenAI. We analyze how changes in subskill abilities affect job success, identifying conditions for sharp transitions in success probability. We also establish sufficient conditions under which combining workers with complementary subskills significantly outperforms relying on a single worker. This explains phenomena such as productivity compression, where GenAI assistance yields larger gains for lower-skilled workers. We demonstrate the framework' s practicality using data from O*NET and Big-Bench Lite, aligning real-world data with our model via subskill-division methods. Our results highlight when and how GenAI complements human skills, rather than replacing them.