Hervé AndrèsCERMICS, Benjamin JourdainCERMICS, MATHRISK
We show the existence and uniqueness of a continuous solution to a path-dependent volatility model introduced by Guyon and Lekeufack (2023) to model the price of an equity index and its spot volatility. The considered model for the trend and activity features can be written as a Stochastic Volterra Equation (SVE) with non-convolutional and non-bounded kernels as well as non-Lipschitz coefficients. We first prove the existence and uniqueness of a solution to the SVE under integrability and regularity assumptions on the two kernels and under a condition on the second kernel weighting the past squared returns which ensures that the activity feature is bounded from below by a positive constant. Then, assuming in addition that the kernel weighting the past returns is of exponential type and that an inequality relating the logarithmic derivatives of the two kernels with respect to their second variables is satisfied, we show the positivity of the volatility process which is obtained as a non-linear function of the SVE's solution. We show numerically that the choice of an exponential kernel for the kernel weighting the past returns has little impact on the quality of model calibration compared to other choices and the inequality involving the logarithmic derivatives is satisfied by the calibrated kernels. These results extend those of Nutz and Valdevenito (2023).
{"title":"Existence, uniqueness and positivity of solutions to the Guyon-Lekeufack path-dependent volatility model with general kernels","authors":"Hervé AndrèsCERMICS, Benjamin JourdainCERMICS, MATHRISK","doi":"arxiv-2408.02477","DOIUrl":"https://doi.org/arxiv-2408.02477","url":null,"abstract":"We show the existence and uniqueness of a continuous solution to a\u0000path-dependent volatility model introduced by Guyon and Lekeufack (2023) to\u0000model the price of an equity index and its spot volatility. The considered\u0000model for the trend and activity features can be written as a Stochastic\u0000Volterra Equation (SVE) with non-convolutional and non-bounded kernels as well\u0000as non-Lipschitz coefficients. We first prove the existence and uniqueness of a\u0000solution to the SVE under integrability and regularity assumptions on the two\u0000kernels and under a condition on the second kernel weighting the past squared\u0000returns which ensures that the activity feature is bounded from below by a\u0000positive constant. Then, assuming in addition that the kernel weighting the\u0000past returns is of exponential type and that an inequality relating the\u0000logarithmic derivatives of the two kernels with respect to their second\u0000variables is satisfied, we show the positivity of the volatility process which\u0000is obtained as a non-linear function of the SVE's solution. We show numerically\u0000that the choice of an exponential kernel for the kernel weighting the past\u0000returns has little impact on the quality of model calibration compared to other\u0000choices and the inequality involving the logarithmic derivatives is satisfied\u0000by the calibrated kernels. These results extend those of Nutz and Valdevenito\u0000(2023).","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"22 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141932411","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}
Inspired by recent advances in Kolmogorov-Arnold Networks (KANs), we introduce a novel approach to latent factor conditional asset pricing models. While previous machine learning applications in asset pricing have predominantly used Multilayer Perceptrons with ReLU activation functions to model latent factor exposures, our method introduces a KAN-based autoencoder which surpasses MLP models in both accuracy and interpretability. Our model offers enhanced flexibility in approximating exposures as nonlinear functions of asset characteristics, while simultaneously providing users with an intuitive framework for interpreting latent factors. Empirical backtesting demonstrates our model's superior ability to explain cross-sectional risk exposures. Moreover, long-short portfolios constructed using our model's predictions achieve higher Sharpe ratios, highlighting its practical value in investment management.
受科尔莫哥洛夫-阿诺德网络（KANs）最新进展的启发，我们为潜在因素条件资产定价模型引入了一种新方法。虽然以前在资产定价领域的机器学习应用主要使用带有 ReLU 激活函数的多层感知器对潜在因素暴露进行建模，但我们的方法引入了基于 KAN 的自动编码器，在准确性和可解释性方面都超越了 MLP 模型。我们的模型在将暴露近似为资产特征的非线性函数方面提供了更大的灵活性，同时还为用户提供了解释潜在因子的直观框架。实证回溯测试证明了我们的模型在解释横截面风险敞口方面的卓越能力。此外，利用我们的模型预测构建的多空投资组合获得了更高的夏普比率，凸显了其在投资管理中的实用价值。
{"title":"KAN based Autoencoders for Factor Models","authors":"Tianqi Wang, Shubham Singh","doi":"arxiv-2408.02694","DOIUrl":"https://doi.org/arxiv-2408.02694","url":null,"abstract":"Inspired by recent advances in Kolmogorov-Arnold Networks (KANs), we\u0000introduce a novel approach to latent factor conditional asset pricing models.\u0000While previous machine learning applications in asset pricing have\u0000predominantly used Multilayer Perceptrons with ReLU activation functions to\u0000model latent factor exposures, our method introduces a KAN-based autoencoder\u0000which surpasses MLP models in both accuracy and interpretability. Our model\u0000offers enhanced flexibility in approximating exposures as nonlinear functions\u0000of asset characteristics, while simultaneously providing users with an\u0000intuitive framework for interpreting latent factors. Empirical backtesting\u0000demonstrates our model's superior ability to explain cross-sectional risk\u0000exposures. Moreover, long-short portfolios constructed using our model's\u0000predictions achieve higher Sharpe ratios, highlighting its practical value in\u0000investment management.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141932410","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 present a unified framework for computing CVA sensitivities, hedging the CVA, and assessing CVA risk, using probabilistic machine learning meant as refined regression tools on simulated data, validatable by low-cost companion Monte Carlo procedures. Various notions of sensitivities are introduced and benchmarked numerically. We identify the sensitivities representing the best practical trade-offs in downstream tasks including CVA hedging and risk assessment.
{"title":"CVA Sensitivities, Hedging and Risk","authors":"Stéphane CrépeyUFR Mathématiques UPCité, Botao LiLPSM, Hoang NguyenIES, LPSM, Bouazza Saadeddine","doi":"arxiv-2407.18583","DOIUrl":"https://doi.org/arxiv-2407.18583","url":null,"abstract":"We present a unified framework for computing CVA sensitivities, hedging the\u0000CVA, and assessing CVA risk, using probabilistic machine learning meant as\u0000refined regression tools on simulated data, validatable by low-cost companion\u0000Monte Carlo procedures. Various notions of sensitivities are introduced and\u0000benchmarked numerically. We identify the sensitivities representing the best\u0000practical trade-offs in downstream tasks including CVA hedging and risk\u0000assessment.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141866099","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 present weak approximations schemes of any order for the Heston model that are obtained by using the method developed by Alfonsi and Bally (2021). This method consists in combining approximation schemes calculated on different random grids to increase the order of convergence. We apply this method with either the Ninomiya-Victoir scheme (2008) or a second-order scheme that samples exactly the volatility component, and we show rigorously that we can achieve then any order of convergence. We give numerical illustrations on financial examples that validate the theoretical order of convergence, and present also promising numerical results for the multifactor/rough Heston model.
{"title":"High order approximations of the log-Heston process semigroup","authors":"Aurélien Alfonsi, Edoardo Lombardo","doi":"arxiv-2407.17151","DOIUrl":"https://doi.org/arxiv-2407.17151","url":null,"abstract":"We present weak approximations schemes of any order for the Heston model that\u0000are obtained by using the method developed by Alfonsi and Bally (2021). This\u0000method consists in combining approximation schemes calculated on different\u0000random grids to increase the order of convergence. We apply this method with\u0000either the Ninomiya-Victoir scheme (2008) or a second-order scheme that samples\u0000exactly the volatility component, and we show rigorously that we can achieve\u0000then any order of convergence. We give numerical illustrations on financial\u0000examples that validate the theoretical order of convergence, and present also\u0000promising numerical results for the multifactor/rough Heston model.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"80 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141771985","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 non-identifiability issue has been frequently reported in the social simulation works, where different parameters of an agent-based simulation model yield indistinguishable simulated time series data under certain discrepancy metrics. This issue largely undermines the simulation fidelity yet lacks dedicated investigations. This paper theoretically analyzes that incorporating multiple time series data features in the model calibration phase can alleviate the non-identifiability exponentially with the increasing number of features. To implement this theoretical finding, a maximization-based aggregation function is applied to existing discrepancy metrics to form a new calibration objective function. For verification, the financial market simulation, a typical and complex social simulation task, is considered. Empirical studies on both synthetic and real market data witness the significant improvements in alleviating the non-identifiability with much higher simulation fidelity of the chosen agent-based simulation model. Importantly, as a model-agnostic method, it achieves the first successful simulation of the high-frequency market at seconds level. Hence, this work is expected to provide not only a rigorous understanding of non-identifiability in social simulation, but a high-fidelity calibration objective function for financial market simulations.
{"title":"Alleviating Non-identifiability: a High-fidelity Calibration Objective for Financial Market Simulation with Multivariate Time Series Data","authors":"Chenkai Wang, Junji Ren, Ke Tang, Peng Yang","doi":"arxiv-2407.16566","DOIUrl":"https://doi.org/arxiv-2407.16566","url":null,"abstract":"The non-identifiability issue has been frequently reported in the social\u0000simulation works, where different parameters of an agent-based simulation model\u0000yield indistinguishable simulated time series data under certain discrepancy\u0000metrics. This issue largely undermines the simulation fidelity yet lacks\u0000dedicated investigations. This paper theoretically analyzes that incorporating\u0000multiple time series data features in the model calibration phase can alleviate\u0000the non-identifiability exponentially with the increasing number of features.\u0000To implement this theoretical finding, a maximization-based aggregation\u0000function is applied to existing discrepancy metrics to form a new calibration\u0000objective function. For verification, the financial market simulation, a\u0000typical and complex social simulation task, is considered. Empirical studies on\u0000both synthetic and real market data witness the significant improvements in\u0000alleviating the non-identifiability with much higher simulation fidelity of the\u0000chosen agent-based simulation model. Importantly, as a model-agnostic method,\u0000it achieves the first successful simulation of the high-frequency market at\u0000seconds level. Hence, this work is expected to provide not only a rigorous\u0000understanding of non-identifiability in social simulation, but a high-fidelity\u0000calibration objective function for financial market simulations.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"61 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141771986","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 a gradient-based deep learning framework to calibrate the Heston option pricing model (Heston, 1993). Our neural network, henceforth deep differential network (DDN), learns both the Heston pricing formula for plain-vanilla options and the partial derivatives with respect to the model parameters. The price sensitivities estimated by the DDN are not subject to the numerical issues that can be encountered in computing the gradient of the Heston pricing function. Thus, our network is an excellent pricing engine for fast gradient-based calibrations. Extensive tests on selected equity markets show that the DDN significantly outperforms non-differential feedforward neural networks in terms of calibration accuracy. In addition, it dramatically reduces the computational time with respect to global optimizers that do not use gradient information.
{"title":"Calibrating the Heston Model with Deep Differential Networks","authors":"Chen Zhang, Giovanni Amici, Marco Morandotti","doi":"arxiv-2407.15536","DOIUrl":"https://doi.org/arxiv-2407.15536","url":null,"abstract":"We propose a gradient-based deep learning framework to calibrate the Heston\u0000option pricing model (Heston, 1993). Our neural network, henceforth deep\u0000differential network (DDN), learns both the Heston pricing formula for\u0000plain-vanilla options and the partial derivatives with respect to the model\u0000parameters. The price sensitivities estimated by the DDN are not subject to the\u0000numerical issues that can be encountered in computing the gradient of the\u0000Heston pricing function. Thus, our network is an excellent pricing engine for\u0000fast gradient-based calibrations. Extensive tests on selected equity markets\u0000show that the DDN significantly outperforms non-differential feedforward neural\u0000networks in terms of calibration accuracy. In addition, it dramatically reduces\u0000the computational time with respect to global optimizers that do not use\u0000gradient information.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"32 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141771987","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 contemporary financial landscape, accurately predicting the probability of filling a Request-For-Quote (RFQ) is crucial for improving market efficiency for less liquid asset classes. This paper explores the application of explainable AI (XAI) models to forecast the likelihood of RFQ fulfillment. By leveraging advanced algorithms including Logistic Regression, Random Forest, XGBoost and Bayesian Neural Tree, we are able to improve the accuracy of RFQ fill rate predictions and generate the most efficient quote price for market makers. XAI serves as a robust and transparent tool for market participants to navigate the complexities of RFQs with greater precision.
{"title":"Explainable AI in Request-for-Quote","authors":"Qiqin Zhou","doi":"arxiv-2407.15038","DOIUrl":"https://doi.org/arxiv-2407.15038","url":null,"abstract":"In the contemporary financial landscape, accurately predicting the\u0000probability of filling a Request-For-Quote (RFQ) is crucial for improving\u0000market efficiency for less liquid asset classes. This paper explores the\u0000application of explainable AI (XAI) models to forecast the likelihood of RFQ\u0000fulfillment. By leveraging advanced algorithms including Logistic Regression,\u0000Random Forest, XGBoost and Bayesian Neural Tree, we are able to improve the\u0000accuracy of RFQ fill rate predictions and generate the most efficient quote\u0000price for market makers. XAI serves as a robust and transparent tool for market\u0000participants to navigate the complexities of RFQs with greater precision.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141771988","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}
Recently, the invention of quantum computers was so revolutionary that they bring transformative challenges in a variety of fields, especially for the traditional cryptographic blockchain, and it may become a real thread for most of the cryptocurrencies in the market. That is, it becomes inevitable to consider to implement a post-quantum cryptography, which is also referred to as quantum-resistant cryptography, for attaining quantum resistance in blockchains.
{"title":"Towards A Post-Quantum Cryptography in Blockchain I: Basic Review on Theoretical Cryptography and Quantum Information Theory","authors":"Tatsuru Kikuchi","doi":"arxiv-2407.18966","DOIUrl":"https://doi.org/arxiv-2407.18966","url":null,"abstract":"Recently, the invention of quantum computers was so revolutionary that they\u0000bring transformative challenges in a variety of fields, especially for the\u0000traditional cryptographic blockchain, and it may become a real thread for most\u0000of the cryptocurrencies in the market. That is, it becomes inevitable to\u0000consider to implement a post-quantum cryptography, which is also referred to as\u0000quantum-resistant cryptography, for attaining quantum resistance in\u0000blockchains.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141866100","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}
Ludovic Goudenege, Andrea Molent, Antonino Zanette
This paper explores the application of Machine Learning techniques for pricing high-dimensional options within the framework of the Uncertain Volatility Model (UVM). The UVM is a robust framework that accounts for the inherent unpredictability of market volatility by setting upper and lower bounds on volatility and the correlation among underlying assets. By leveraging historical data and extreme values of estimated volatilities and correlations, the model establishes a confidence interval for future volatility and correlations, thus providing a more realistic approach to option pricing. By integrating advanced Machine Learning algorithms, we aim to enhance the accuracy and efficiency of option pricing under the UVM, especially when the option price depends on a large number of variables, such as in basket or path-dependent options. Our approach evolves backward in time, dynamically selecting at each time step the most expensive volatility and correlation for each market state. Specifically, it identifies the particular values of volatility and correlation that maximize the expected option value at the next time step. This is achieved through the use of Gaussian Process regression, the computation of expectations via a single step of a multidimensional tree and the Sequential Quadratic Programming optimization algorithm. The numerical results demonstrate that the proposed approach can significantly improve the precision of option pricing and risk management strategies compared with methods already in the literature, particularly in high-dimensional contexts.
{"title":"Leveraging Machine Learning for High-Dimensional Option Pricing within the Uncertain Volatility Model","authors":"Ludovic Goudenege, Andrea Molent, Antonino Zanette","doi":"arxiv-2407.13213","DOIUrl":"https://doi.org/arxiv-2407.13213","url":null,"abstract":"This paper explores the application of Machine Learning techniques for\u0000pricing high-dimensional options within the framework of the Uncertain\u0000Volatility Model (UVM). The UVM is a robust framework that accounts for the\u0000inherent unpredictability of market volatility by setting upper and lower\u0000bounds on volatility and the correlation among underlying assets. By leveraging\u0000historical data and extreme values of estimated volatilities and correlations,\u0000the model establishes a confidence interval for future volatility and\u0000correlations, thus providing a more realistic approach to option pricing. By\u0000integrating advanced Machine Learning algorithms, we aim to enhance the\u0000accuracy and efficiency of option pricing under the UVM, especially when the\u0000option price depends on a large number of variables, such as in basket or\u0000path-dependent options. Our approach evolves backward in time, dynamically\u0000selecting at each time step the most expensive volatility and correlation for\u0000each market state. Specifically, it identifies the particular values of\u0000volatility and correlation that maximize the expected option value at the next\u0000time step. This is achieved through the use of Gaussian Process regression, the\u0000computation of expectations via a single step of a multidimensional tree and\u0000the Sequential Quadratic Programming optimization algorithm. The numerical\u0000results demonstrate that the proposed approach can significantly improve the\u0000precision of option pricing and risk management strategies compared with\u0000methods already in the literature, particularly in high-dimensional contexts.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141742102","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 era of rapid globalization and digitalization, accurate identification of similar stocks has become increasingly challenging due to the non-stationary nature of financial markets and the ambiguity in conventional regional and sector classifications. To address these challenges, we examine SimStock, a novel temporal self-supervised learning framework that combines techniques from self-supervised learning (SSL) and temporal domain generalization to learn robust and informative representations of financial time series data. The primary focus of our study is to understand the similarities between stocks from a broader perspective, considering the complex dynamics of the global financial landscape. We conduct extensive experiments on four real-world datasets with thousands of stocks and demonstrate the effectiveness of SimStock in finding similar stocks, outperforming existing methods. The practical utility of SimStock is showcased through its application to various investment strategies, such as pairs trading, index tracking, and portfolio optimization, where it leads to superior performance compared to conventional methods. Our findings empirically examine the potential of data-driven approach to enhance investment decision-making and risk management practices by leveraging the power of temporal self-supervised learning in the face of the ever-changing global financial landscape.
{"title":"Temporal Representation Learning for Stock Similarities and Its Applications in Investment Management","authors":"Yoontae Hwang, Stefan Zohren, Yongjae Lee","doi":"arxiv-2407.13751","DOIUrl":"https://doi.org/arxiv-2407.13751","url":null,"abstract":"In the era of rapid globalization and digitalization, accurate identification\u0000of similar stocks has become increasingly challenging due to the non-stationary\u0000nature of financial markets and the ambiguity in conventional regional and\u0000sector classifications. To address these challenges, we examine SimStock, a\u0000novel temporal self-supervised learning framework that combines techniques from\u0000self-supervised learning (SSL) and temporal domain generalization to learn\u0000robust and informative representations of financial time series data. The\u0000primary focus of our study is to understand the similarities between stocks\u0000from a broader perspective, considering the complex dynamics of the global\u0000financial landscape. We conduct extensive experiments on four real-world\u0000datasets with thousands of stocks and demonstrate the effectiveness of SimStock\u0000in finding similar stocks, outperforming existing methods. The practical\u0000utility of SimStock is showcased through its application to various investment\u0000strategies, such as pairs trading, index tracking, and portfolio optimization,\u0000where it leads to superior performance compared to conventional methods. Our\u0000findings empirically examine the potential of data-driven approach to enhance\u0000investment decision-making and risk management practices by leveraging the\u0000power of temporal self-supervised learning in the face of the ever-changing\u0000global financial landscape.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"12 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141742134","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：