Investment portfolios, central to finance, balance potential returns and risks. This paper introduces a hybrid approach combining Markowitz's portfolio theory with reinforcement learning, utilizing knowledge distillation for training agents. In particular, our proposed method, called KDD (Knowledge Distillation DDPG), consist of two training stages: supervised and reinforcement learning stages. The trained agents optimize portfolio assembly. A comparative analysis against standard financial models and AI frameworks, using metrics like returns, the Sharpe ratio, and nine evaluation indices, reveals our model's superiority. It notably achieves the highest yield and Sharpe ratio of 2.03, ensuring top profitability with the lowest risk in comparable return scenarios.
{"title":"Markowitz Meets Bellman: Knowledge-distilled Reinforcement Learning for Portfolio Management","authors":"Gang Hu, Ming Gu","doi":"arxiv-2405.05449","DOIUrl":"https://doi.org/arxiv-2405.05449","url":null,"abstract":"Investment portfolios, central to finance, balance potential returns and\u0000risks. This paper introduces a hybrid approach combining Markowitz's portfolio\u0000theory with reinforcement learning, utilizing knowledge distillation for\u0000training agents. In particular, our proposed method, called KDD (Knowledge\u0000Distillation DDPG), consist of two training stages: supervised and\u0000reinforcement learning stages. The trained agents optimize portfolio assembly.\u0000A comparative analysis against standard financial models and AI frameworks,\u0000using metrics like returns, the Sharpe ratio, and nine evaluation indices,\u0000reveals our model's superiority. It notably achieves the highest yield and\u0000Sharpe ratio of 2.03, ensuring top profitability with the lowest risk in\u0000comparable return scenarios.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"44 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140941059","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}
The Multilevel Monte Carlo (MLMC) method has been applied successfully in a wide range of settings since its first introduction by Giles (2008). When using only two levels, the method can be viewed as a kind of control-variate approach to reduce variance, as earlier proposed by Kebaier (2005). We introduce a generalization of the MLMC formulation by extending this control variate approach to any number of levels and deriving a recursive formula for computing the weights associated with the control variates and the optimal numbers of samples at the various levels. We also show how the generalisation can also be applied to the emph{multi-index} MLMC method of Haji-Ali, Nobile, Tempone (2015), at the cost of solving a $(2^d-1)$-dimensional minimisation problem at each node when $d$ index dimensions are used. The comparative performance of the weighted MLMC method is illustrated in a range of numerical settings. While the addition of weights does not change the emph{asymptotic} complexity of the method, the results show that significant efficiency improvements over the standard MLMC formulation are possible, particularly when the coarse level approximations are poorly correlated.
{"title":"A weighted multilevel Monte Carlo method","authors":"Yu Li, Antony Ware","doi":"arxiv-2405.03453","DOIUrl":"https://doi.org/arxiv-2405.03453","url":null,"abstract":"The Multilevel Monte Carlo (MLMC) method has been applied successfully in a\u0000wide range of settings since its first introduction by Giles (2008). When using\u0000only two levels, the method can be viewed as a kind of control-variate approach\u0000to reduce variance, as earlier proposed by Kebaier (2005). We introduce a\u0000generalization of the MLMC formulation by extending this control variate\u0000approach to any number of levels and deriving a recursive formula for computing\u0000the weights associated with the control variates and the optimal numbers of\u0000samples at the various levels. We also show how the generalisation can also be applied to the\u0000emph{multi-index} MLMC method of Haji-Ali, Nobile, Tempone (2015), at the cost\u0000of solving a $(2^d-1)$-dimensional minimisation problem at each node when $d$\u0000index dimensions are used. The comparative performance of the weighted MLMC method is illustrated in a\u0000range of numerical settings. While the addition of weights does not change the\u0000emph{asymptotic} complexity of the method, the results show that significant\u0000efficiency improvements over the standard MLMC formulation are possible,\u0000particularly when the coarse level approximations are poorly correlated.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140882170","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}
Exploring complex adaptive financial trading environments through multi-agent based simulation methods presents an innovative approach within the realm of quantitative finance. Despite the dominance of multi-agent reinforcement learning approaches in financial markets with observable data, there exists a set of systematically significant financial markets that pose challenges due to their partial or obscured data availability. We, therefore, devise a multi-agent simulation approach employing small-scale meta-heuristic methods. This approach aims to represent the opaque bilateral market for Australian government bond trading, capturing the bilateral nature of bank-to-bank trading, also referred to as "over-the-counter" (OTC) trading, and commonly occurring between "market makers". The uniqueness of the bilateral market, characterized by negotiated transactions and a limited number of agents, yields valuable insights for agent-based modelling and quantitative finance. The inherent rigidity of this market structure, which is at odds with the global proliferation of multilateral platforms and the decentralization of finance, underscores the unique insights offered by our agent-based model. We explore the implications of market rigidity on market structure and consider the element of stability, in market design. This extends the ongoing discourse on complex financial trading environments, providing an enhanced understanding of their dynamics and implications.
{"title":"Modelling Opaque Bilateral Market Dynamics in Financial Trading: Insights from a Multi-Agent Simulation Study","authors":"Alicia Vidler, Toby Walsh","doi":"arxiv-2405.02849","DOIUrl":"https://doi.org/arxiv-2405.02849","url":null,"abstract":"Exploring complex adaptive financial trading environments through multi-agent\u0000based simulation methods presents an innovative approach within the realm of\u0000quantitative finance. Despite the dominance of multi-agent reinforcement\u0000learning approaches in financial markets with observable data, there exists a\u0000set of systematically significant financial markets that pose challenges due to\u0000their partial or obscured data availability. We, therefore, devise a\u0000multi-agent simulation approach employing small-scale meta-heuristic methods.\u0000This approach aims to represent the opaque bilateral market for Australian\u0000government bond trading, capturing the bilateral nature of bank-to-bank\u0000trading, also referred to as \"over-the-counter\" (OTC) trading, and commonly\u0000occurring between \"market makers\". The uniqueness of the bilateral market,\u0000characterized by negotiated transactions and a limited number of agents, yields\u0000valuable insights for agent-based modelling and quantitative finance. The\u0000inherent rigidity of this market structure, which is at odds with the global\u0000proliferation of multilateral platforms and the decentralization of finance,\u0000underscores the unique insights offered by our agent-based model. We explore\u0000the implications of market rigidity on market structure and consider the\u0000element of stability, in market design. This extends the ongoing discourse on\u0000complex financial trading environments, providing an enhanced understanding of\u0000their dynamics and implications.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140882247","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}
We propose an efficient and easy-to-implement gradient-enhanced least squares Monte Carlo method for computing price and Greeks (i.e., derivatives of the price function) of high-dimensional American options. It employs the sparse Hermite polynomial expansion as a surrogate model for the continuation value function, and essentially exploits the fast evaluation of gradients. The expansion coefficients are computed by solving a linear least squares problem that is enhanced by gradient information of simulated paths. We analyze the convergence of the proposed method, and establish an error estimate in terms of the best approximation error in the weighted $H^1$ space, the statistical error of solving discrete least squares problems, and the time step size. We present comprehensive numerical experiments to illustrate the performance of the proposed method. The results show that it outperforms the state-of-the-art least squares Monte Carlo method with more accurate price, Greeks, and optimal exercise strategies in high dimensions but with nearly identical computational cost, and it can deliver comparable results with recent neural network-based methods up to dimension 100.
{"title":"Gradient-enhanced sparse Hermite polynomial expansions for pricing and hedging high-dimensional American options","authors":"Jiefei Yang, Guanglian Li","doi":"arxiv-2405.02570","DOIUrl":"https://doi.org/arxiv-2405.02570","url":null,"abstract":"We propose an efficient and easy-to-implement gradient-enhanced least squares\u0000Monte Carlo method for computing price and Greeks (i.e., derivatives of the\u0000price function) of high-dimensional American options. It employs the sparse\u0000Hermite polynomial expansion as a surrogate model for the continuation value\u0000function, and essentially exploits the fast evaluation of gradients. The\u0000expansion coefficients are computed by solving a linear least squares problem\u0000that is enhanced by gradient information of simulated paths. We analyze the\u0000convergence of the proposed method, and establish an error estimate in terms of\u0000the best approximation error in the weighted $H^1$ space, the statistical error\u0000of solving discrete least squares problems, and the time step size. We present\u0000comprehensive numerical experiments to illustrate the performance of the\u0000proposed method. The results show that it outperforms the state-of-the-art\u0000least squares Monte Carlo method with more accurate price, Greeks, and optimal\u0000exercise strategies in high dimensions but with nearly identical computational\u0000cost, and it can deliver comparable results with recent neural network-based\u0000methods up to dimension 100.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140882372","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}
Eduardo Abi JaberXiaoyuan, ShaunXiaoyuan, Li, Xuyang Lin
We consider the Fourier-Laplace transforms of a broad class of polynomial Ornstein-Uhlenbeck (OU) volatility models, including the well-known Stein-Stein, Sch"obel-Zhu, one-factor Bergomi, and the recently introduced Quintic OU models motivated by the SPX-VIX joint calibration problem. We show the connection between the joint Fourier-Laplace functional of the log-price and the integrated variance, and the solution of an infinite dimensional Riccati equation. Next, under some non-vanishing conditions of the Fourier-Laplace transforms, we establish an existence result for such Riccati equation and we provide a discretized approximation of the joint characteristic functional that is exponentially entire. On the practical side, we develop a numerical scheme to solve the stiff infinite dimensional Riccati equations and demonstrate the efficiency and accuracy of the scheme for pricing SPX options and volatility swaps using Fourier and Laplace inversions, with specific examples of the Quintic OU and the one-factor Bergomi models and their calibration to real market data.
我们考虑了一大类多项式奥恩斯坦-乌伦贝克（OU）波动率模型的傅里叶-拉普拉斯变换，包括著名的斯坦-斯坦（Stein-Stein）模型、施奥贝尔-朱（Sch"obel-Zhu）模型、单因子贝戈米（Bergomi）模型，以及最近由 SPX-VIX 联合校准问题激发而引入的昆特 OU 模型。我们展示了对数价格和综合方差的联合傅立叶-拉普拉斯函数与无限维里卡蒂方程的解之间的联系。接下来，在傅里叶-拉普拉斯变换的一些非消失条件下，我们建立了这种里卡提方程的存在性结果，并提供了指数整数的联合特征函数的离散近似值。在实际应用方面，我们开发了一种数值方案来求解僵硬的无限维 Riccati 方程，并利用傅里叶和拉普拉斯反演演示了该方案在 SPX 期权和波动率掉期定价方面的效率和准确性，并以 Quintic OU 和单因子 Bergomi 模型及其与真实市场数据的校准为例进行了具体说明。
{"title":"Fourier-Laplace transforms in polynomial Ornstein-Uhlenbeck volatility models","authors":"Eduardo Abi JaberXiaoyuan, ShaunXiaoyuan, Li, Xuyang Lin","doi":"arxiv-2405.02170","DOIUrl":"https://doi.org/arxiv-2405.02170","url":null,"abstract":"We consider the Fourier-Laplace transforms of a broad class of polynomial\u0000Ornstein-Uhlenbeck (OU) volatility models, including the well-known\u0000Stein-Stein, Sch\"obel-Zhu, one-factor Bergomi, and the recently introduced\u0000Quintic OU models motivated by the SPX-VIX joint calibration problem. We show\u0000the connection between the joint Fourier-Laplace functional of the log-price\u0000and the integrated variance, and the solution of an infinite dimensional\u0000Riccati equation. Next, under some non-vanishing conditions of the\u0000Fourier-Laplace transforms, we establish an existence result for such Riccati\u0000equation and we provide a discretized approximation of the joint characteristic\u0000functional that is exponentially entire. On the practical side, we develop a\u0000numerical scheme to solve the stiff infinite dimensional Riccati equations and\u0000demonstrate the efficiency and accuracy of the scheme for pricing SPX options\u0000and volatility swaps using Fourier and Laplace inversions, with specific\u0000examples of the Quintic OU and the one-factor Bergomi models and their\u0000calibration to real market data.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"40 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140882168","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}
In the distributed systems landscape, Blockchain has catalyzed the rise of cryptocurrencies, merging enhanced security and decentralization with significant investment opportunities. Despite their potential, current research on cryptocurrency trend forecasting often falls short by simplistically merging sentiment data without fully considering the nuanced interplay between financial market dynamics and external sentiment influences. This paper presents a novel Dual Attention Mechanism (DAM) for forecasting cryptocurrency trends using multimodal time-series data. Our approach, which integrates critical cryptocurrency metrics with sentiment data from news and social media analyzed through CryptoBERT, addresses the inherent volatility and prediction challenges in cryptocurrency markets. By combining elements of distributed systems, natural language processing, and financial forecasting, our method outperforms conventional models like LSTM and Transformer by up to 20% in prediction accuracy. This advancement deepens the understanding of distributed systems and has practical implications in financial markets, benefiting stakeholders in cryptocurrency and blockchain technologies. Moreover, our enhanced forecasting approach can significantly support decentralized science (DeSci) by facilitating strategic planning and the efficient adoption of blockchain technologies, improving operational efficiency and financial risk management in the rapidly evolving digital asset domain, thus ensuring optimal resource allocation.
{"title":"DAM: A Universal Dual Attention Mechanism for Multimodal Timeseries Cryptocurrency Trend Forecasting","authors":"Yihang Fu, Mingyu Zhou, Luyao Zhang","doi":"arxiv-2405.00522","DOIUrl":"https://doi.org/arxiv-2405.00522","url":null,"abstract":"In the distributed systems landscape, Blockchain has catalyzed the rise of\u0000cryptocurrencies, merging enhanced security and decentralization with\u0000significant investment opportunities. Despite their potential, current research\u0000on cryptocurrency trend forecasting often falls short by simplistically merging\u0000sentiment data without fully considering the nuanced interplay between\u0000financial market dynamics and external sentiment influences. This paper\u0000presents a novel Dual Attention Mechanism (DAM) for forecasting cryptocurrency\u0000trends using multimodal time-series data. Our approach, which integrates\u0000critical cryptocurrency metrics with sentiment data from news and social media\u0000analyzed through CryptoBERT, addresses the inherent volatility and prediction\u0000challenges in cryptocurrency markets. By combining elements of distributed\u0000systems, natural language processing, and financial forecasting, our method\u0000outperforms conventional models like LSTM and Transformer by up to 20% in\u0000prediction accuracy. This advancement deepens the understanding of distributed\u0000systems and has practical implications in financial markets, benefiting\u0000stakeholders in cryptocurrency and blockchain technologies. Moreover, our\u0000enhanced forecasting approach can significantly support decentralized science\u0000(DeSci) by facilitating strategic planning and the efficient adoption of\u0000blockchain technologies, improving operational efficiency and financial risk\u0000management in the rapidly evolving digital asset domain, thus ensuring optimal\u0000resource allocation.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140829337","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}
Forecasting cryptocurrencies as a financial issue is crucial as it provides investors with possible financial benefits. A small improvement in forecasting performance can lead to increased profitability; therefore, obtaining a realistic forecast is very important for investors. Successful forecasting provides traders with effective buy-or-hold strategies, allowing them to make more profits. The most important thing in this process is to produce accurate forecasts suitable for real-life applications. Bitcoin, frequently mentioned recently due to its volatility and chaotic behavior, has begun to pay great attention and has become an investment tool, especially during and after the COVID-19 pandemic. This study provided a comprehensive methodology, including constructing continuous and trend data using one and seven years periods of data as inputs and applying machine learning (ML) algorithms to forecast Bitcoin price movement. A binarization procedure was applied using continuous data to construct the trend data representing each input feature trend. Following the related literature, the input features are determined as technical indicators, google trends, and the number of tweets. Random forest (RF), K-Nearest neighbor (KNN), Extreme Gradient Boosting (XGBoost-XGB), Support vector machine (SVM) Naive Bayes (NB), Artificial Neural Networks (ANN), and Long-Short-Term Memory (LSTM) networks were applied on the selected features for prediction purposes. This work investigates two main research questions: i. How does the sample size affect the prediction performance of ML algorithms? ii. How does the data type affect the prediction performance of ML algorithms? Accuracy and area under the ROC curve (AUC) values were used to compare the model performance. A t-test was performed to test the statistical significance of the prediction results.
将加密货币作为一个金融问题进行预测至关重要，因为它能为投资者带来可能的经济利益。预测性能的微小改进都可能导致盈利能力的提高；因此，获得准确的预测对投资者来说非常重要。成功的预测为交易者提供了有效的买入或持有策略，使他们能够获得更多利润。在这一过程中，最重要的是做出适合实际应用的准确预测。比特币因其波动性和混沌行为最近经常被提及，已开始受到高度关注，并已成为一种投资工具，尤其是在 COVID-19 大流行期间和之后。本研究提供了一种全面的方法，包括使用一年和七年的数据作为输入，构建连续数据和趋势数据，并应用机器学习（ML）算法预测比特币的价格走势。根据相关文献，输入特征被确定为技术指标、谷歌趋势和推文数量。随机森林（RF）、K-近邻（KNN）、极梯度提升（XGBoost-XGB）、支持向量机（SVM）、奈夫贝叶斯（NB）、人工神经网络（ANN）和长短期记忆（LSTM）网络被应用于所选特征的预测。这项工作主要研究两个问题：i. 样本大小如何影响 ML 算法的预测性能？使用准确率和 ROC 曲线下面积（AUC）值来比较模型性能。采用 t 检验来检验预测结果的统计显著性。
{"title":"The Effect of Data Types' on the Performance of Machine Learning Algorithms for Financial Prediction","authors":"Hulusi Mehmet Tanrikulu, Hakan Pabuccu","doi":"arxiv-2404.19324","DOIUrl":"https://doi.org/arxiv-2404.19324","url":null,"abstract":"Forecasting cryptocurrencies as a financial issue is crucial as it provides\u0000investors with possible financial benefits. A small improvement in forecasting\u0000performance can lead to increased profitability; therefore, obtaining a\u0000realistic forecast is very important for investors. Successful forecasting\u0000provides traders with effective buy-or-hold strategies, allowing them to make\u0000more profits. The most important thing in this process is to produce accurate\u0000forecasts suitable for real-life applications. Bitcoin, frequently mentioned\u0000recently due to its volatility and chaotic behavior, has begun to pay great\u0000attention and has become an investment tool, especially during and after the\u0000COVID-19 pandemic. This study provided a comprehensive methodology, including\u0000constructing continuous and trend data using one and seven years periods of\u0000data as inputs and applying machine learning (ML) algorithms to forecast\u0000Bitcoin price movement. A binarization procedure was applied using continuous\u0000data to construct the trend data representing each input feature trend.\u0000Following the related literature, the input features are determined as\u0000technical indicators, google trends, and the number of tweets. Random forest\u0000(RF), K-Nearest neighbor (KNN), Extreme Gradient Boosting (XGBoost-XGB),\u0000Support vector machine (SVM) Naive Bayes (NB), Artificial Neural Networks\u0000(ANN), and Long-Short-Term Memory (LSTM) networks were applied on the selected\u0000features for prediction purposes. This work investigates two main research\u0000questions: i. How does the sample size affect the prediction performance of ML\u0000algorithms? ii. How does the data type affect the prediction performance of ML\u0000algorithms? Accuracy and area under the ROC curve (AUC) values were used to\u0000compare the model performance. A t-test was performed to test the statistical\u0000significance of the prediction results.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140829346","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}
We suggest new closely related methods for numerical inversion of $Z$-transform and Wiener-Hopf factorization of functions on the unit circle, based on sinh-deformations of the contours of integration, corresponding changes of variables and the simplified trapezoid rule. As applications, we consider evaluation of high moments of probability distributions and construction of causal filters. Programs in Matlab running on a Mac with moderate characteristics achieves the precision E-14 in several dozen of microseconds and E-11 in several milliseconds, respectively.
{"title":"Efficient inverse $Z$-transform and Wiener-Hopf factorization","authors":"Svetlana Boyarchenko, Sergei Levendorskiĭ","doi":"arxiv-2404.19290","DOIUrl":"https://doi.org/arxiv-2404.19290","url":null,"abstract":"We suggest new closely related methods for numerical inversion of\u0000$Z$-transform and Wiener-Hopf factorization of functions on the unit circle,\u0000based on sinh-deformations of the contours of integration, corresponding\u0000changes of variables and the simplified trapezoid rule. As applications, we\u0000consider evaluation of high moments of probability distributions and\u0000construction of causal filters. Programs in Matlab running on a Mac with\u0000moderate characteristics achieves the precision E-14 in several dozen of\u0000microseconds and E-11 in several milliseconds, respectively.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140829356","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}
Steven Reece, Emma O donnell, Felicia Liu, Joanna Wolstenholme, Frida Arriaga, Giacomo Ascenzi, Richard Pywell
There is growing recognition among financial institutions, financial regulators and policy makers of the importance of addressing nature-related risks and opportunities. Evaluating and assessing nature-related risks for financial institutions is challenging due to the large volume of heterogeneous data available on nature and the complexity of investment value chains and the various components' relationship to nature. The dual problem of scaling data analytics and analysing complex systems can be addressed using Artificial Intelligence (AI). We address issues such as plugging existing data gaps with discovered data, data estimation under uncertainty, time series analysis and (near) real-time updates. This report presents potential AI solutions for models of two distinct use cases, the Brazil Beef Supply Use Case and the Water Utility Use Case. Our two use cases cover a broad perspective within sustainable finance. The Brazilian cattle farming use case is an example of greening finance - integrating nature-related considerations into mainstream financial decision-making to transition investments away from sectors with poor historical track records and unsustainable operations. The deployment of nature-based solutions in the UK water utility use case is an example of financing green - driving investment to nature-positive outcomes. The two use cases also cover different sectors, geographies, financial assets and AI modelling techniques, providing an overview on how AI could be applied to different challenges relating to nature's integration into finance. This report is primarily aimed at financial institutions but is also of interest to ESG data providers, TNFD, systems modellers, and, of course, AI practitioners.
{"title":"Assessing the Potential of AI for Spatially Sensitive Nature-Related Financial Risks","authors":"Steven Reece, Emma O donnell, Felicia Liu, Joanna Wolstenholme, Frida Arriaga, Giacomo Ascenzi, Richard Pywell","doi":"arxiv-2404.17369","DOIUrl":"https://doi.org/arxiv-2404.17369","url":null,"abstract":"There is growing recognition among financial institutions, financial\u0000regulators and policy makers of the importance of addressing nature-related\u0000risks and opportunities. Evaluating and assessing nature-related risks for\u0000financial institutions is challenging due to the large volume of heterogeneous\u0000data available on nature and the complexity of investment value chains and the\u0000various components' relationship to nature. The dual problem of scaling data\u0000analytics and analysing complex systems can be addressed using Artificial\u0000Intelligence (AI). We address issues such as plugging existing data gaps with\u0000discovered data, data estimation under uncertainty, time series analysis and\u0000(near) real-time updates. This report presents potential AI solutions for\u0000models of two distinct use cases, the Brazil Beef Supply Use Case and the Water\u0000Utility Use Case. Our two use cases cover a broad perspective within\u0000sustainable finance. The Brazilian cattle farming use case is an example of\u0000greening finance - integrating nature-related considerations into mainstream\u0000financial decision-making to transition investments away from sectors with poor\u0000historical track records and unsustainable operations. The deployment of\u0000nature-based solutions in the UK water utility use case is an example of\u0000financing green - driving investment to nature-positive outcomes. The two use\u0000cases also cover different sectors, geographies, financial assets and AI\u0000modelling techniques, providing an overview on how AI could be applied to\u0000different challenges relating to nature's integration into finance. This report\u0000is primarily aimed at financial institutions but is also of interest to ESG\u0000data providers, TNFD, systems modellers, and, of course, AI practitioners.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"77 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140810550","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}
In this paper we apply second order stochastic dominance (SSD) to the problem of enhanced indexation with asset subset (sector) constraints. The problem we consider is how to construct a portfolio that is designed to outperform a given market index whilst having regard to the proportion of the portfolio invested in distinct market sectors. In our approach, subset SSD, the portfolio associated with each sector is treated in a SSD manner. In other words in subset SSD we actively try to find sector portfolios that SSD dominate their respective sector indices. However the proportion of the overall portfolio invested in each sector is not pre-specified, rather it is decided via optimisation. Computational results are given for our approach as applied to the S&P~500 over the period $29^{text{th}}$ August 2018 to $29^{text{th}}$ December 2023. This period, over 5 years, includes the Covid pandemic, which had a significant effect on stock prices. Our results indicate that the scaled version of our subset SSD approach significantly outperforms the S&P~500 over the period considered. Our approach also outperforms the standard SSD based approach to the problem.
{"title":"Subset SSD for enhanced indexation with sector constraints","authors":"Cristiano Arbex Valle, John E Beasley","doi":"arxiv-2404.16777","DOIUrl":"https://doi.org/arxiv-2404.16777","url":null,"abstract":"In this paper we apply second order stochastic dominance (SSD) to the problem\u0000of enhanced indexation with asset subset (sector) constraints. The problem we\u0000consider is how to construct a portfolio that is designed to outperform a given\u0000market index whilst having regard to the proportion of the portfolio invested\u0000in distinct market sectors. In our approach, subset SSD, the portfolio\u0000associated with each sector is treated in a SSD manner. In other words in\u0000subset SSD we actively try to find sector portfolios that SSD dominate their\u0000respective sector indices. However the proportion of the overall portfolio\u0000invested in each sector is not pre-specified, rather it is decided via\u0000optimisation. Computational results are given for our approach as applied to\u0000the S&P~500 over the period $29^{text{th}}$ August 2018 to $29^{text{th}}$\u0000December 2023. This period, over 5 years, includes the Covid pandemic, which\u0000had a significant effect on stock prices. Our results indicate that the scaled\u0000version of our subset SSD approach significantly outperforms the S&P~500 over\u0000the period considered. Our approach also outperforms the standard SSD based\u0000approach to the problem.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140798514","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：