首页 > 最新文献

arXiv - QuantFin - Statistical Finance最新文献

英文 中文
Workplace sustainability or financial resilience? Composite-financial resilience index 工作场所的可持续性还是财务复原力?财务复原力综合指数
Pub Date : 2024-03-24 DOI: arxiv-2403.16296
Elham Daadmehr
Due to the variety of corporate risks in turmoil markets and the consequentfinancial distress especially in COVID-19 time, this paper investigatescorporate resilience and compares different types of resilience that can bepotential sources of heterogeneity in firms' implied rate of return.Specifically, the novelty is not only to quantify firms' financial resiliencebut also to compare it with workplace resilience which matters more in theCOVID-19 era. The study prepares several pieces of evidence of the necessityand insufficiency of these two main types of resilience by comparing earningsexpectations and implied discount rates of high- and low-resilience firms.Particularly, results present evidence of the possible amplification ofworkplace resilience by the financial status of firms in the COVID-19 era. Thepaper proposes a novel composite-financial resilience index as a potentialmeasure for disaster risk that significantly and persistently revealslow-resilience characteristics of firms and resilience-heterogeneity in implieddiscount rates.
由于动荡市场中企业风险的多样性以及随之而来的财务困境,尤其是在 COVID-19 时代,本文对企业的抗风险能力进行了研究,并比较了不同类型的抗风险能力,这些抗风险能力可能是企业隐含收益率异质性的潜在来源。研究通过比较高弹性和低弹性企业的收益预期和隐含贴现率,为这两种主要弹性的必要性和不足提供了若干证据。特别是,研究结果提供了在 COVID-19 时代企业财务状况可能会放大工作场所弹性的证据。本文提出了一种新的复合财务复原力指数,作为衡量灾害风险的潜在指标,该指数显著且持续地揭示了企业的低复原力特征和隐含贴现率中的复原力异质性。
{"title":"Workplace sustainability or financial resilience? Composite-financial resilience index","authors":"Elham Daadmehr","doi":"arxiv-2403.16296","DOIUrl":"https://doi.org/arxiv-2403.16296","url":null,"abstract":"Due to the variety of corporate risks in turmoil markets and the consequent\u0000financial distress especially in COVID-19 time, this paper investigates\u0000corporate resilience and compares different types of resilience that can be\u0000potential sources of heterogeneity in firms' implied rate of return.\u0000Specifically, the novelty is not only to quantify firms' financial resilience\u0000but also to compare it with workplace resilience which matters more in the\u0000COVID-19 era. The study prepares several pieces of evidence of the necessity\u0000and insufficiency of these two main types of resilience by comparing earnings\u0000expectations and implied discount rates of high- and low-resilience firms.\u0000Particularly, results present evidence of the possible amplification of\u0000workplace resilience by the financial status of firms in the COVID-19 era. The\u0000paper proposes a novel composite-financial resilience index as a potential\u0000measure for disaster risk that significantly and persistently reveals\u0000low-resilience characteristics of firms and resilience-heterogeneity in implied\u0000discount rates.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"154 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140298765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Nonlinear shifts and dislocations in financial market structure and composition 金融市场结构和组成的非线性变化和混乱
Pub Date : 2024-03-22 DOI: arxiv-2403.15163
Nick James, Max Menzies
This paper develops new mathematical techniques to identify temporal shiftsamong a collection of US equities partitioned into a new and more detailed setof market sectors. Although conceptually related, our three analyses revealdistinct insights about financial markets, with meaningful implications forinvestment managers. First, we explore a variety of methods to identifynonlinear shifts in market sector structure and describe the mathematicalconnection between the measure used and the captured phenomena. Second, westudy network structure with respect to our new market sectors and identifymeaningfully connected sector-to-sector mappings. Finally, we conduct a seriesof sampling experiments over different sample spaces and contrast thedistribution of Sharpe ratios produced by long-only, long-short and short-onlyinvestment portfolios. In addition, we examine the sector composition of thetop-performing portfolios for each of these portfolio styles. In practice, themethods proposed in this paper could be used to identify regime shifts,optimally structured portfolios, and better communities of equities.
本文开发了新的数学技术,以识别被划分为一系列新的、更详细的市场板块的美国股票之间的时间变化。尽管在概念上是相关的,但我们的三项分析揭示了金融市场的不同见解,对投资经理具有重要意义。首先,我们探索了多种方法来识别市场板块结构的非线性变化,并描述了所使用的测量方法与所捕捉到的现象之间的数学联系。其次,我们研究了新市场部门的网络结构,并确定了有意义的部门与部门之间的映射关系。最后,我们对不同的样本空间进行了一系列抽样实验,并对比了只做多头、做多做空和只做空头的投资组合所产生的夏普比率的分布情况。此外,我们还研究了每种投资组合风格中表现最好的投资组合的行业构成。在实践中,本文提出的方法可用于识别制度转变、结构优化的投资组合以及更好的股票群体。
{"title":"Nonlinear shifts and dislocations in financial market structure and composition","authors":"Nick James, Max Menzies","doi":"arxiv-2403.15163","DOIUrl":"https://doi.org/arxiv-2403.15163","url":null,"abstract":"This paper develops new mathematical techniques to identify temporal shifts\u0000among a collection of US equities partitioned into a new and more detailed set\u0000of market sectors. Although conceptually related, our three analyses reveal\u0000distinct insights about financial markets, with meaningful implications for\u0000investment managers. First, we explore a variety of methods to identify\u0000nonlinear shifts in market sector structure and describe the mathematical\u0000connection between the measure used and the captured phenomena. Second, we\u0000study network structure with respect to our new market sectors and identify\u0000meaningfully connected sector-to-sector mappings. Finally, we conduct a series\u0000of sampling experiments over different sample spaces and contrast the\u0000distribution of Sharpe ratios produced by long-only, long-short and short-only\u0000investment portfolios. In addition, we examine the sector composition of the\u0000top-performing portfolios for each of these portfolio styles. In practice, the\u0000methods proposed in this paper could be used to identify regime shifts,\u0000optimally structured portfolios, and better communities of equities.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"267 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140301861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Modeling stock price dynamics on the Ghana Stock Exchange: A Geometric Brownian Motion approach 加纳证券交易所股票价格动态建模:几何布朗运动方法
Pub Date : 2024-03-19 DOI: arxiv-2403.13192
Dennis Lartey Quayesam, Anani Lotsi, Felix Okoe Mettle
Modeling financial data often relies on assumptions that may proveinsufficient or unrealistic in practice. The Geometric Brownian Motion (GBM)model is frequently employed to represent stock price processes. This studyinvestigates whether the behavior of weekly and monthly returns of selectedequities listed on the Ghana Stock Exchange conforms to the GBM model.Parameters of the GBM model were estimated for five equities, and forecastswere generated for three months. Evaluation of estimation accuracy wasconducted using mean square error (MSE). Results indicate that the expectedprices from the modeled equities closely align with actual stock pricesobserved on the Exchange. Furthermore, while some deviations were observed, theactual prices consistently fell within the estimated confidence intervals.
金融数据建模通常依赖于一些假设,而这些假设在实践中可能被证明是不充分或不现实的。几何布朗运动(GBM)模型经常被用来表示股票价格过程。本研究调查了在加纳证券交易所上市的部分股票的周收益率和月收益率是否符合 GBM 模型。使用均方误差 (MSE) 对估计精度进行了评估。结果表明,模型股票的预期价格与交易所实际股票价格非常接近。此外,虽然观察到一些偏差,但实际价格始终在估计的置信区间内。
{"title":"Modeling stock price dynamics on the Ghana Stock Exchange: A Geometric Brownian Motion approach","authors":"Dennis Lartey Quayesam, Anani Lotsi, Felix Okoe Mettle","doi":"arxiv-2403.13192","DOIUrl":"https://doi.org/arxiv-2403.13192","url":null,"abstract":"Modeling financial data often relies on assumptions that may prove\u0000insufficient or unrealistic in practice. The Geometric Brownian Motion (GBM)\u0000model is frequently employed to represent stock price processes. This study\u0000investigates whether the behavior of weekly and monthly returns of selected\u0000equities listed on the Ghana Stock Exchange conforms to the GBM model.\u0000Parameters of the GBM model were estimated for five equities, and forecasts\u0000were generated for three months. Evaluation of estimation accuracy was\u0000conducted using mean square error (MSE). Results indicate that the expected\u0000prices from the modeled equities closely align with actual stock prices\u0000observed on the Exchange. Furthermore, while some deviations were observed, the\u0000actual prices consistently fell within the estimated confidence intervals.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"259 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140205590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Advanced Statistical Arbitrage with Reinforcement Learning 利用强化学习进行高级统计套利
Pub Date : 2024-03-18 DOI: arxiv-2403.12180
Boming Ning, Kiseop Lee
Statistical arbitrage is a prevalent trading strategy which takes advantageof mean reverse property of spread of paired stocks. Studies on this strategyoften rely heavily on model assumption. In this study, we introduce aninnovative model-free and reinforcement learning based framework forstatistical arbitrage. For the construction of mean reversion spreads, weestablish an empirical reversion time metric and optimize asset coefficients byminimizing this empirical mean reversion time. In the trading phase, we employa reinforcement learning framework to identify the optimal mean reversionstrategy. Diverging from traditional mean reversion strategies that primarilyfocus on price deviations from a long-term mean, our methodology creativelyconstructs the state space to encapsulate the recent trends in price movements.Additionally, the reward function is carefully tailored to reflect the uniquecharacteristics of mean reversion trading.
统计套利是一种利用配对股票价差均值反向特性的普遍交易策略。对这种策略的研究往往严重依赖模型假设。在本研究中,我们为统计套利引入了一个无模型、基于强化学习的创新框架。为了构建均值回归价差,我们建立了一个经验回归时间指标,并通过最小化这个经验均值回归时间来优化资产系数。在交易阶段,我们采用强化学习框架来确定最优均值回归策略。与主要关注价格偏离长期均值的传统均值回归策略不同,我们的方法创造性地构建了状态空间,以囊括价格走势的近期趋势。
{"title":"Advanced Statistical Arbitrage with Reinforcement Learning","authors":"Boming Ning, Kiseop Lee","doi":"arxiv-2403.12180","DOIUrl":"https://doi.org/arxiv-2403.12180","url":null,"abstract":"Statistical arbitrage is a prevalent trading strategy which takes advantage\u0000of mean reverse property of spread of paired stocks. Studies on this strategy\u0000often rely heavily on model assumption. In this study, we introduce an\u0000innovative model-free and reinforcement learning based framework for\u0000statistical arbitrage. For the construction of mean reversion spreads, we\u0000establish an empirical reversion time metric and optimize asset coefficients by\u0000minimizing this empirical mean reversion time. In the trading phase, we employ\u0000a reinforcement learning framework to identify the optimal mean reversion\u0000strategy. Diverging from traditional mean reversion strategies that primarily\u0000focus on price deviations from a long-term mean, our methodology creatively\u0000constructs the state space to encapsulate the recent trends in price movements.\u0000Additionally, the reward function is carefully tailored to reflect the unique\u0000characteristics of mean reversion trading.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"162 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140169653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
From Factor Models to Deep Learning: Machine Learning in Reshaping Empirical Asset Pricing 从因子模型到深度学习:重塑经验资产定价的机器学习
Pub Date : 2024-03-11 DOI: arxiv-2403.06779
Junyi Ye, Bhaskar Goswami, Jingyi Gu, Ajim Uddin, Guiling Wang
This paper comprehensively reviews the application of machine learning (ML)and AI in finance, specifically in the context of asset pricing. It starts bysummarizing the traditional asset pricing models and examining theirlimitations in capturing the complexities of financial markets. It explores how1) ML models, including supervised, unsupervised, semi-supervised, andreinforcement learning, provide versatile frameworks to address thesecomplexities, and 2) the incorporation of advanced ML algorithms intotraditional financial models enhances return prediction and portfoliooptimization. These methods can adapt to changing market dynamics by modelingstructural changes and incorporating heterogeneous data sources, such as textand images. In addition, this paper explores challenges in applying ML in assetpricing, addressing the growing demand for explainability in decision-makingand mitigating overfitting in complex models. This paper aims to provideinsights into novel methodologies showcasing the potential of ML to reshape thefuture of quantitative finance.
本文全面回顾了机器学习(ML)和人工智能在金融领域的应用,特别是在资产定价方面的应用。文章首先总结了传统的资产定价模型,并探讨了这些模型在捕捉金融市场复杂性方面的局限性。它探讨了 1) 包括监督、无监督、半监督和强化学习在内的 ML 模型如何为解决这些复杂性提供多功能框架,以及 2) 将先进的 ML 算法纳入传统金融模型如何增强回报预测和投资组合优化。这些方法可以通过对结构变化进行建模并纳入异构数据源(如文本和图像)来适应不断变化的市场动态。此外,本文还探讨了在资产定价中应用 ML 所面临的挑战,以满足决策中对可解释性日益增长的需求,并减轻复杂模型中的过度拟合。本文旨在提供新颖方法的见解,展示 ML 重塑量化金融未来的潜力。
{"title":"From Factor Models to Deep Learning: Machine Learning in Reshaping Empirical Asset Pricing","authors":"Junyi Ye, Bhaskar Goswami, Jingyi Gu, Ajim Uddin, Guiling Wang","doi":"arxiv-2403.06779","DOIUrl":"https://doi.org/arxiv-2403.06779","url":null,"abstract":"This paper comprehensively reviews the application of machine learning (ML)\u0000and AI in finance, specifically in the context of asset pricing. It starts by\u0000summarizing the traditional asset pricing models and examining their\u0000limitations in capturing the complexities of financial markets. It explores how\u00001) ML models, including supervised, unsupervised, semi-supervised, and\u0000reinforcement learning, provide versatile frameworks to address these\u0000complexities, and 2) the incorporation of advanced ML algorithms into\u0000traditional financial models enhances return prediction and portfolio\u0000optimization. These methods can adapt to changing market dynamics by modeling\u0000structural changes and incorporating heterogeneous data sources, such as text\u0000and images. In addition, this paper explores challenges in applying ML in asset\u0000pricing, addressing the growing demand for explainability in decision-making\u0000and mitigating overfitting in complex models. This paper aims to provide\u0000insights into novel methodologies showcasing the potential of ML to reshape the\u0000future of quantitative finance.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"26 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140107820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The entropy corrected geometric Brownian motion 熵校正几何布朗运动
Pub Date : 2024-03-10 DOI: arxiv-2403.06253
Rishabh Gupta, Ewa Drzazga-Szczȩśniak, Sabre Kais, Dominik Szczȩśniak
The geometric Brownian motion (GBM) is widely employed for modelingstochastic processes, yet its solutions are characterized by the log-normaldistribution. This comprises predictive capabilities of GBM mainly in terms offorecasting applications. Here, entropy corrections to GBM are proposed to gobeyond log-normality restrictions and better account for intricacies of realsystems. It is shown that GBM solutions can be effectively refined by arguingthat entropy is reduced when deterministic content of considered dataincreases. Notable improvements over conventional GBM are observed for severalcases of non-log-normal distributions, ranging from a dice roll experiment toreal world data.
几何布朗运动(GBM)被广泛用于模拟随机过程,但其解的特征是对数正态分布。这使得 GBM 的预测能力主要局限于预测应用。本文提出了对 GBM 的熵修正,以超越对数正态性限制,更好地解释错综复杂的真实系统。研究表明,当考虑数据的确定性内容增加时,熵会减少,因此可以有效地完善 GBM 解决方案。从掷骰子实验到真实世界的数据,在非对数正态分布的几种情况下,与传统的 GBM 相比都有显著的改进。
{"title":"The entropy corrected geometric Brownian motion","authors":"Rishabh Gupta, Ewa Drzazga-Szczȩśniak, Sabre Kais, Dominik Szczȩśniak","doi":"arxiv-2403.06253","DOIUrl":"https://doi.org/arxiv-2403.06253","url":null,"abstract":"The geometric Brownian motion (GBM) is widely employed for modeling\u0000stochastic processes, yet its solutions are characterized by the log-normal\u0000distribution. This comprises predictive capabilities of GBM mainly in terms of\u0000forecasting applications. Here, entropy corrections to GBM are proposed to go\u0000beyond log-normality restrictions and better account for intricacies of real\u0000systems. It is shown that GBM solutions can be effectively refined by arguing\u0000that entropy is reduced when deterministic content of considered data\u0000increases. Notable improvements over conventional GBM are observed for several\u0000cases of non-log-normal distributions, ranging from a dice roll experiment to\u0000real world data.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140107812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Calibrated rank volatility stabilized models for large equity markets 大型股票市场的校准秩波动率稳定模型
Pub Date : 2024-03-07 DOI: arxiv-2403.04674
David Itkin, Martin Larsson
In the framework of stochastic portfolio theory we introduce rank volatilitystabilized models for large equity markets over long time horizons. Thesemodels are rank-based extensions of the volatility stabilized models introducedby Fernholz & Karatzas in 2005. On the theoretical side we establish globalexistence of the model and ergodicity of the induced ranked market weights. Wealso derive explicit expressions for growth-optimal portfolios and show theexistence of relative arbitrage with respect to the market portfolio. On theempirical side we calibrate the model to sixteen years of CRSP US equity datamatching (i) rank-based volatilities, (ii) stock turnover as measured by marketweight collisions, (iii) the average market rate of return and (iv) the capitaldistribution curve. Assessment of model fit and error analysis is conductedboth in and out of sample. To the best of our knowledge this is the first modelexhibiting relative arbitrage that has statistically been shown to have a goodquantitative fit with the empirical features (i)-(iv). We additionally simulatetrajectories of the calibrated model and compare them to historicaltrajectories, both in and out of sample.
在随机投资组合理论的框架下,我们引入了长期大型股票市场的等级波动率稳定模型。这些模型是 Fernholz & Karatzas 于 2005 年推出的波动率稳定模型的等级扩展。在理论方面,我们建立了模型的全球存在性和诱导排序市场权重的遍历性。我们还推导出了增长最优投资组合的明确表达式,并证明了相对于市场投资组合的相对套利的存在性。在实证方面,我们根据 16 年的 CRSP 美国股票数据对模型进行了校准,以匹配(i)基于等级的波动率,(ii)通过市场权重碰撞衡量的股票周转率,(iii)平均市场收益率和(iv)资本分布曲线。在样本内和样本外都对模型拟合度和误差分析进行了评估。据我们所知,这是第一个从统计学角度证明与经验特征(i)-(iv)具有良好定量拟合的相对套利模式。此外,我们还模拟了校准模型的轨迹,并将其与样本内外的历史轨迹进行了比较。
{"title":"Calibrated rank volatility stabilized models for large equity markets","authors":"David Itkin, Martin Larsson","doi":"arxiv-2403.04674","DOIUrl":"https://doi.org/arxiv-2403.04674","url":null,"abstract":"In the framework of stochastic portfolio theory we introduce rank volatility\u0000stabilized models for large equity markets over long time horizons. These\u0000models are rank-based extensions of the volatility stabilized models introduced\u0000by Fernholz & Karatzas in 2005. On the theoretical side we establish global\u0000existence of the model and ergodicity of the induced ranked market weights. We\u0000also derive explicit expressions for growth-optimal portfolios and show the\u0000existence of relative arbitrage with respect to the market portfolio. On the\u0000empirical side we calibrate the model to sixteen years of CRSP US equity data\u0000matching (i) rank-based volatilities, (ii) stock turnover as measured by market\u0000weight collisions, (iii) the average market rate of return and (iv) the capital\u0000distribution curve. Assessment of model fit and error analysis is conducted\u0000both in and out of sample. To the best of our knowledge this is the first model\u0000exhibiting relative arbitrage that has statistically been shown to have a good\u0000quantitative fit with the empirical features (i)-(iv). We additionally simulate\u0000trajectories of the calibrated model and compare them to historical\u0000trajectories, both in and out of sample.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"34 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140069952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Prediction Of Cryptocurrency Prices Using LSTM, SVM And Polynomial Regression 使用 LSTM、SVM 和多项式回归预测加密货币价格
Pub Date : 2024-03-06 DOI: arxiv-2403.03410
Novan Fauzi Al Giffary, Feri Sulianta
The rapid development of information technology, especially the Internet, hasfacilitated users with a quick and easy way to seek information. With theseconvenience offered by internet services, many individuals who initiallyinvested in gold and precious metals are now shifting into digital investmentsin form of cryptocurrencies. However, investments in crypto coins are filledwith uncertainties and fluctuation in daily basis. This risk posed assignificant challenges for coin investors that could result in substantialinvestment losses. The uncertainty of the value of these crypto coins is acritical issue in the field of coin investment. Forecasting, is one of themethods used to predict the future value of these crypto coins. By utilizingthe models of Long Short Term Memory, Support Vector Machine, and PolynomialRegression algorithm for forecasting, a performance comparison is conducted todetermine which algorithm model is most suitable for predicting crypto currencyprices. The mean square error is employed as a benchmark for the comparison. Byapplying those three constructed algorithm models, the Support Vector Machineuses a linear kernel to produce the smallest mean square error compared to theLong Short Term Memory and Polynomial Regression algorithm models, with a meansquare error value of 0.02. Keywords: Cryptocurrency, Forecasting, Long ShortTerm Memory, Mean Square Error, Polynomial Regression, Support Vector Machine
信息技术的飞速发展,尤其是互联网的发展,为用户提供了快速便捷的信息查询方式。有了互联网服务提供的这些便利,许多最初投资黄金和贵金属的个人现在开始转向加密货币形式的数字投资。然而,加密货币投资每天都充满了不确定性和波动。这种风险给硬币投资者带来了巨大挑战,可能导致巨大的投资损失。这些加密钱币价值的不确定性是钱币投资领域的一个关键问题。预测是用于预测这些加密钱币未来价值的方法之一。通过利用长短期记忆、支持向量机和多项式回归算法模型进行预测,进行性能比较,以确定哪种算法模型最适合预测加密货币的价格。比较的基准是均方误差。通过应用这三种构建的算法模型,与长短期记忆和多项式回归算法模型相比,支持向量机使用线性核产生的均方误差最小,均方误差值为 0.02。关键词加密货币 预测 长短期记忆 均方误差 多项式回归 支持向量机
{"title":"Prediction Of Cryptocurrency Prices Using LSTM, SVM And Polynomial Regression","authors":"Novan Fauzi Al Giffary, Feri Sulianta","doi":"arxiv-2403.03410","DOIUrl":"https://doi.org/arxiv-2403.03410","url":null,"abstract":"The rapid development of information technology, especially the Internet, has\u0000facilitated users with a quick and easy way to seek information. With these\u0000convenience offered by internet services, many individuals who initially\u0000invested in gold and precious metals are now shifting into digital investments\u0000in form of cryptocurrencies. However, investments in crypto coins are filled\u0000with uncertainties and fluctuation in daily basis. This risk posed as\u0000significant challenges for coin investors that could result in substantial\u0000investment losses. The uncertainty of the value of these crypto coins is a\u0000critical issue in the field of coin investment. Forecasting, is one of the\u0000methods used to predict the future value of these crypto coins. By utilizing\u0000the models of Long Short Term Memory, Support Vector Machine, and Polynomial\u0000Regression algorithm for forecasting, a performance comparison is conducted to\u0000determine which algorithm model is most suitable for predicting crypto currency\u0000prices. The mean square error is employed as a benchmark for the comparison. By\u0000applying those three constructed algorithm models, the Support Vector Machine\u0000uses a linear kernel to produce the smallest mean square error compared to the\u0000Long Short Term Memory and Polynomial Regression algorithm models, with a mean\u0000square error value of 0.02. Keywords: Cryptocurrency, Forecasting, Long Short\u0000Term Memory, Mean Square Error, Polynomial Regression, Support Vector Machine","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"42 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140056979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
"Digitwashing": The Gap between Words and Deeds in Digital Transformation and Stock Price Crash Risk "数字清洗":数字化转型中的言行差距与股价暴跌风险
Pub Date : 2024-03-03 DOI: arxiv-2403.01360
Shutter Zor
The contrast between companies' "fleshy" promises and the "skeletal"performance in digital transformation may lead to a higher risk of stock pricecrash. This paper selects a sample of Shanghai and Shenzhen A-share listedcompanies from 2010 to 2021, empirically analyses the specific impact of thegap between words and deeds in digital transformation (GDT) on the stock pricecrash risk, and explores the possible causes of GDT. We found that GDTsignificantly increases the stock price crash risk, and this finding is stillvalid after a series of robustness tests. In a further study, a deeperexamination of the causes of GDT reveals that firms' perceptions of economicpolicy uncertainty significantly increase GDT, and the effect is morepronounced in the sample of loss-making firms. At the same time, the results ofthe heterogeneity test suggest that investors are more tolerant of state-ownedenterprises when they are in the GDT situation. Taken together, we provide aconcrete bridge between the two measures of digital transformation - digitaltext frequency and digital technology share - and offer new insights to enhancecapital market stability.
公司在数字化转型中 "丰满 "的承诺与 "骨感 "的表现之间的反差可能会导致股价暴跌的风险。本文选取2010-2021年沪深A股上市公司为样本,实证分析了数字化转型中的言行不一(GDT)对股价崩盘风险的具体影响,并探讨了GDT可能的成因。我们发现,GDT 显著增加了股价暴跌风险,并且这一结论在经过一系列稳健性检验后仍然有效。在进一步的研究中,我们对 GDT 的成因进行了深入探讨,发现企业对经济政策不确定性的感知会显著增加 GDT,而且这种效应在亏损企业样本中更为明显。同时,异质性检验的结果表明,当国有企业处于 GDT 状态时,投资者对其更为宽容。综上所述,我们在数字转型的两个衡量指标--数字文本频率和数字技术份额之间架起了一座具体的桥梁,为增强资本市场的稳定性提供了新的见解。
{"title":"\"Digitwashing\": The Gap between Words and Deeds in Digital Transformation and Stock Price Crash Risk","authors":"Shutter Zor","doi":"arxiv-2403.01360","DOIUrl":"https://doi.org/arxiv-2403.01360","url":null,"abstract":"The contrast between companies' \"fleshy\" promises and the \"skeletal\"\u0000performance in digital transformation may lead to a higher risk of stock price\u0000crash. This paper selects a sample of Shanghai and Shenzhen A-share listed\u0000companies from 2010 to 2021, empirically analyses the specific impact of the\u0000gap between words and deeds in digital transformation (GDT) on the stock price\u0000crash risk, and explores the possible causes of GDT. We found that GDT\u0000significantly increases the stock price crash risk, and this finding is still\u0000valid after a series of robustness tests. In a further study, a deeper\u0000examination of the causes of GDT reveals that firms' perceptions of economic\u0000policy uncertainty significantly increase GDT, and the effect is more\u0000pronounced in the sample of loss-making firms. At the same time, the results of\u0000the heterogeneity test suggest that investors are more tolerant of state-owned\u0000enterprises when they are in the GDT situation. Taken together, we provide a\u0000concrete bridge between the two measures of digital transformation - digital\u0000text frequency and digital technology share - and offer new insights to enhance\u0000capital market stability.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140034856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
ARED: Argentina Real Estate Dataset ARED:阿根廷房地产数据集
Pub Date : 2024-03-01 DOI: arxiv-2403.00273
Iván Belenky
The Argentinian real estate market presents a unique case study characterizedby its unstable and rapidly shifting macroeconomic circumstances over the pastdecades. Despite the existence of a few datasets for price prediction, there isa lack of mixed modality datasets specifically focused on Argentina. In thispaper, the first edition of ARED is introduced. A comprehensive real estateprice prediction dataset series, designed for the Argentinian market. Thisedition contains information solely for Jan-Feb 2024. It was found that despitethe short time range captured by this zeroth edition (44 days), time dependentphenomena has been occurring mostly on a market level (market as a whole).Nevertheless future editions of this dataset, will most likely containhistorical data. Each listing in ARED comprises descriptive features, andvariable-length sets of images.
阿根廷房地产市场是一个独特的案例研究,其特点是在过去几十年中宏观经济环境不稳定且快速变化。尽管有一些用于价格预测的数据集,但缺乏专门针对阿根廷的混合模式数据集。本文介绍了 ARED 的第一版。这是一个专为阿根廷市场设计的综合性房地产价格预测数据集系列。本版仅包含 2024 年 1-2 月的信息。我们发现,尽管第 4 版的时间范围较短(44 天),但与时间相关的现象主要发生在市场层面(市场整体)。ARED 中的每个列表都包含描述性特征和长度可变的图像集。
{"title":"ARED: Argentina Real Estate Dataset","authors":"Iván Belenky","doi":"arxiv-2403.00273","DOIUrl":"https://doi.org/arxiv-2403.00273","url":null,"abstract":"The Argentinian real estate market presents a unique case study characterized\u0000by its unstable and rapidly shifting macroeconomic circumstances over the past\u0000decades. Despite the existence of a few datasets for price prediction, there is\u0000a lack of mixed modality datasets specifically focused on Argentina. In this\u0000paper, the first edition of ARED is introduced. A comprehensive real estate\u0000price prediction dataset series, designed for the Argentinian market. This\u0000edition contains information solely for Jan-Feb 2024. It was found that despite\u0000the short time range captured by this zeroth edition (44 days), time dependent\u0000phenomena has been occurring mostly on a market level (market as a whole).\u0000Nevertheless future editions of this dataset, will most likely contain\u0000historical data. Each listing in ARED comprises descriptive features, and\u0000variable-length sets of images.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"42 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140034608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
arXiv - QuantFin - Statistical Finance
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1