以世界十大股票市场指数为例,运用滚动Monte Carlo模拟技术,实证计算了R-vine、Dvine、C-vine及R-vine all t四种vine copula结构对投资组合的动态VaR预测值,并进一步运用严谨的Back-testing检验方法,实证对比了上述四种vine copula结...以世界十大股票市场指数为例,运用滚动Monte Carlo模拟技术,实证计算了R-vine、Dvine、C-vine及R-vine all t四种vine copula结构对投资组合的动态VaR预测值,并进一步运用严谨的Back-testing检验方法,实证对比了上述四种vine copula结构对投资组合的VaR预测能力的优劣.实证结果显示:不论是在等权重还是在mean-CVaR约束条件下,R-vine对投资组合的VaR预测效果是最好的.特别在高分位数水平下,其表现得更为突出.另外,D-vine的预测精度总体上要高于C-vine和R-vine all t的,而节点间全为t copula的R-vine all t表现相对较差.展开更多
随着面向服务的体系结构、云计算以及软件即服务的流行和发展,提供相同或相似的服务功能以及差异化服务质量(quality of service,QoS)的服务提供者越来越多.因此,如何为一个复合服务业务流程中的抽象服务选择合适的服务提供者,并通过动...随着面向服务的体系结构、云计算以及软件即服务的流行和发展,提供相同或相似的服务功能以及差异化服务质量(quality of service,QoS)的服务提供者越来越多.因此,如何为一个复合服务业务流程中的抽象服务选择合适的服务提供者,并通过动态组合来最大限度地保障并优化整体服务质量就成了一个重要的研究课题.对于一个复合服务,传统的服务组合方法会为所有服务请求实例选择一套共同的服务绑定方案直至下一次自适应调整.此外,这些方法只考虑了候选服务质量的期望值,而忽略了服务质量在运行时的波动带来的潜在风险.这些问题可能导致复合服务请求者和提供者之间达成的服务等级协议(service level agreement,SLA)经常被违反,从而影响复合服务提供者业务价值的实现.针对这一问题,本文提出了一种支持风险偏好的Web服务动态组合方法.该方法综合考虑了服务质量的期望值和波动性,应用投资组合理论产生适应给定风险偏好的多套服务绑定方案的组合,从而控制风险、适应不同的风险偏好.实验结果表明,该方法与全局服务选择方法相比能够有效降低SLA违反率,同时提高复合服务所创造的业务价值.展开更多
This paper investigates a multi-period mean-variance portfolio selection with regime switching and uncertain exit time. The returns of assets all depend on the states of the stochastic market which are assumed to foll...This paper investigates a multi-period mean-variance portfolio selection with regime switching and uncertain exit time. The returns of assets all depend on the states of the stochastic market which are assumed to follow a discrete-time Markov chain. The authors derive the optimal strategy and the efficient frontier of the model in closed-form. Some results in the existing literature are obtained as special cases of our results.展开更多
Online portfolio selection and simulation are some of the most important problems in several research communities,including finance,engineering,statistics,artificial intelligence,machine learning,etc.The primary aim o...Online portfolio selection and simulation are some of the most important problems in several research communities,including finance,engineering,statistics,artificial intelligence,machine learning,etc.The primary aim of online portfolio selection is to determine portfolio weights in every investment period(i.e.,daily,weekly,monthly,etc.)to maximize the investor’s final wealth after the end of investment period(e.g.,1 year or longer).In this paper,we present an efficient online portfolio selection strategy that makes use of market indices and benchmark indices to take advantage of the mean reversal phenomena at minimal risks.Based on empirical studies conducted on recent historical datasets for the period 2000 to 2015 on four different stock markets(i.e.,NYSE,S&P500,DJIA,and TSX),the proposed strategy has been shown to outperform both Anticor and OLMAR—the two most prominent portfolio selection strategies in contemporary literature.展开更多
This paper investigates a multi-period portfolio optimization problem for a defined contribution pension plan with Telser's safety-first criterion.The plan members aim to maximize the expected terminal wealth subj...This paper investigates a multi-period portfolio optimization problem for a defined contribution pension plan with Telser's safety-first criterion.The plan members aim to maximize the expected terminal wealth subject to a constraint that the probability of the terminal wealth falling below a disaster level is less than a pre-determined number called risk control level.By Tchebycheff inequality,Lagrange multiplier technique,the embedding method and Bellman's principle of optimality,the authors obtain the conditions under which the optimal strategy exists and derive the closed-form optimal strategy and value function.Special cases show that the obtained results in this paper can be reduced to those in the classical mean-variance model.Finally,numerical analysis is provided to analyze the effects of the risk control level,the disaster level and the contribution proportion on the disaster probability and the value function.The numerical analysis indicates that the disaster probability in this paper is less than that in the classical mean-variance model on the premise that the value functions are the same in two models.展开更多
文摘以世界十大股票市场指数为例,运用滚动Monte Carlo模拟技术,实证计算了R-vine、Dvine、C-vine及R-vine all t四种vine copula结构对投资组合的动态VaR预测值,并进一步运用严谨的Back-testing检验方法,实证对比了上述四种vine copula结构对投资组合的VaR预测能力的优劣.实证结果显示:不论是在等权重还是在mean-CVaR约束条件下,R-vine对投资组合的VaR预测效果是最好的.特别在高分位数水平下,其表现得更为突出.另外,D-vine的预测精度总体上要高于C-vine和R-vine all t的,而节点间全为t copula的R-vine all t表现相对较差.
文摘随着面向服务的体系结构、云计算以及软件即服务的流行和发展,提供相同或相似的服务功能以及差异化服务质量(quality of service,QoS)的服务提供者越来越多.因此,如何为一个复合服务业务流程中的抽象服务选择合适的服务提供者,并通过动态组合来最大限度地保障并优化整体服务质量就成了一个重要的研究课题.对于一个复合服务,传统的服务组合方法会为所有服务请求实例选择一套共同的服务绑定方案直至下一次自适应调整.此外,这些方法只考虑了候选服务质量的期望值,而忽略了服务质量在运行时的波动带来的潜在风险.这些问题可能导致复合服务请求者和提供者之间达成的服务等级协议(service level agreement,SLA)经常被违反,从而影响复合服务提供者业务价值的实现.针对这一问题,本文提出了一种支持风险偏好的Web服务动态组合方法.该方法综合考虑了服务质量的期望值和波动性,应用投资组合理论产生适应给定风险偏好的多套服务绑定方案的组合,从而控制风险、适应不同的风险偏好.实验结果表明,该方法与全局服务选择方法相比能够有效降低SLA违反率,同时提高复合服务所创造的业务价值.
基金This research is supported by the National Science Foundation for Distinguished Young Scholars under Grant No. 70825002, the National Natural Science Foundation of China under Grant No. 70518001, and the National Basic Research Program of China 973 Program, under Grant No. 2007CB814902.
文摘This paper investigates a multi-period mean-variance portfolio selection with regime switching and uncertain exit time. The returns of assets all depend on the states of the stochastic market which are assumed to follow a discrete-time Markov chain. The authors derive the optimal strategy and the efficient frontier of the model in closed-form. Some results in the existing literature are obtained as special cases of our results.
文摘Online portfolio selection and simulation are some of the most important problems in several research communities,including finance,engineering,statistics,artificial intelligence,machine learning,etc.The primary aim of online portfolio selection is to determine portfolio weights in every investment period(i.e.,daily,weekly,monthly,etc.)to maximize the investor’s final wealth after the end of investment period(e.g.,1 year or longer).In this paper,we present an efficient online portfolio selection strategy that makes use of market indices and benchmark indices to take advantage of the mean reversal phenomena at minimal risks.Based on empirical studies conducted on recent historical datasets for the period 2000 to 2015 on four different stock markets(i.e.,NYSE,S&P500,DJIA,and TSX),the proposed strategy has been shown to outperform both Anticor and OLMAR—the two most prominent portfolio selection strategies in contemporary literature.
基金supported by grants from Innovation Research in Central University of Finance and Economics,National Natural Science Foundation of China under Grant Nos.11671411,71871071,72071051,Guangdong Basic and Applied Basic Research Foundation under Grant No.2018B030311004,the Key Program of the National Social Science Foundation of China under Grant No.21AZD071 and the 111 Project under Grant No.B17050.
文摘This paper investigates a multi-period portfolio optimization problem for a defined contribution pension plan with Telser's safety-first criterion.The plan members aim to maximize the expected terminal wealth subject to a constraint that the probability of the terminal wealth falling below a disaster level is less than a pre-determined number called risk control level.By Tchebycheff inequality,Lagrange multiplier technique,the embedding method and Bellman's principle of optimality,the authors obtain the conditions under which the optimal strategy exists and derive the closed-form optimal strategy and value function.Special cases show that the obtained results in this paper can be reduced to those in the classical mean-variance model.Finally,numerical analysis is provided to analyze the effects of the risk control level,the disaster level and the contribution proportion on the disaster probability and the value function.The numerical analysis indicates that the disaster probability in this paper is less than that in the classical mean-variance model on the premise that the value functions are the same in two models.
