基于试验设计的链路预测算法应用研究

链路预测是根据已有的网络结构等指标来对网络中尚未产生连边的两个节点间存在边的可能性大小进行预测。链路预测算法在社会网络中的应用是非常广泛的,且都具有很好的预测效果。但由于真实网络往往具有纷繁复杂的演化机制,这使得很难利用某一单指标去准确刻画,并且每种指标在不同网络结构中的预测效果各不相同,现有链路预测算法都是针对特定网络结构才可能有的最佳效果,缺乏普适性。本文基于均匀配方实验设计方法,构建了混合相似性指标,提出了改进的链路预测算法,并将其应用于微博社交网络和生物代谢合作网络中。研究结果表明,改进后的链路预测算法的预测准确性明显优于已有的链路预测算法,说明新构建的混合相似性指标具有一定的普适性;其次,试验设计方法大大缩减了混合相似性指标构建中最优权重确定的迭代次数及其复杂度。     

基于TOPSIS的网络舆情态势等级模糊多指标综合评价模型

网络舆情是社会舆情在网络空间中的映射,体现了社会稳定和谐程度.网络舆情态势分析对于有效预测和把握舆情导向具有重大的意义.文章主要研究构建基于TOPSIS的网络舆情态势等级模糊多指标综合评价模型.首先,根据网络舆情态势演化形成原因和发展规律,建立了网络舆情态势等级评价三级指标体系,提出了基于有序比值方法的网络舆情态势等级评价指标权重的确定方法.然后,构建了基于TOPSIS的网络舆情态势等级模糊多指标综合评价模型.最后,通过魏则西事件验证了该模型的有效性和适用性,并与线性加权综合评价模型进行对比分析,说明了文章模型的优越性.研究结果对政府和相关舆情监管人员及时有效的管理和引导网络舆情具有重要的指导意义与参考价值.     

厄兰极值混合模型的有效估计及其在保险中的应用

本文研究了Erlang混合分布和广义帕累托分布混合模型的估计问题.通过引入iSCAD惩罚函数,利用EM算法极大化iSCAD惩罚似然函数的方法,获得了混合序和参数的估计值,计算出有效的度量风险指标value-at-risk(VaR)和tail-VaR(TVaR),通过模拟实验和实际数据说明了模型和算法的有效性.推广了有限Erlang极值混合模型在保险数据拟合中的应用.     

基于DMC方法的城市空气质量SUR模型研究

我国现阶段城市化的日益发展,使城市空气质量的宏观调控面临越来越大的压力。本文建立了关于空气质量的似乎不相关(SUR)模型,采用Jeffreys's的不变先验分析直接蒙特卡罗(DMC)方法,计算各参数的贝叶斯后验密度和未来值的预测密度。对中国厦门市区三项污染指标及四项外部驱动因素的数据进行实证分析,并将其与贝叶斯分层模型得出的结果进行比较。     

填充烧结铜球的T型管中流体混合的大涡模拟

在FLUENT软件平台上,运用大涡模拟湍流模型及Smagorinsky-Lilly亚格子尺度模型,对填充有烧结铜球多孔介质的T型管道内冷热流体混合过程的流动与传热情况进行了数值计算,与未填充多孔介质时混合区域内的平均温度和温度波动、平均速度和速度波动等数据进行了对比,并对温度波动进行了功率谱密度分析．数值结果表明,多孔介质可有效削弱T型通道流体混合区域内的温度和速度波动,有效降低1 Hz至10 Hz频域中的温度波动的功率谱密度．     

交通流灰色RBF网络非线性组合预测方法

针对智能交通系统的开发,提出一种基于灰色GM(1,1)模型和RBF网络非线性组合的短时交通流预测方法.该方法采用三层结构的RBF网络将两种单一预测方法(灰色GM(1,1)模型和RBF网络)进行了非线性组合.利用实测数据对组合方法进行了仿真实验,结果表明:非线性组合模型的预测准确性高于单独的RBF网络预测的准确性;组合模型发挥了两种单一方法各自的优势,是短时交通流预测的有效方法.     

随机删失单函数型指标模型条件众数估计的渐近正态性

基于单函数型指标模型,构造了该模型下条件密度和条件众数的估计量,研究了 α-混合函数型数据在响应变量随机删失的情况下的条件密度和条件众数估计量的渐近正态分布,用模拟研究说明单函数型指标模型条件众数估计的有效性.     

改进LSTM网络对于时间有效性经济指标预测模型的研究

针对经济指标的预测,尤其是关于时间有效性的预测,具有重要的现实意义.通过筛选,得到对于起经济预测影响较高的指标.基于LSTM网络模型,对LSTM模型的初始权重及阈值进行了优化,提升了模型的经济预测效果.结合不同类型的灰度模型算法,重点体现时间有效性,进而构建新的组合灰度改进-BA-LSTM网络模型,将其用于经济指标的预测.利用其他三种不同的灰度模型和组合灰度模型分别结合效果更稳定的改进BA-LSTM模型对经济指标进行预测,实验结果证明,对比其他的经济预测模型,模型的精度更高,预测结果更准确,可以有效用于CPI和GDP等数据的预测,预测结果满足时间有效性要求,证明该模型的实用价值.     

基于GMDH的LSSVM预测模型及其实证

自从Suykens提出新型统计理论学习方法-最小二乘支持向量机(LSSVM)以来,这种方法引起了广泛的关注,它在预测方面的良好性能得到了广泛应用.应用自组织数据挖掘(GMDH)方法改进LSSVM,提升了预测精度.首先利用GMDH方法选择有效的输入变量,再将这些变量作为LSSVM模型的输入,进行时间序列的预测,从而建立LSSVM和GMDH组合的混合模型GLSSVM.并通过汇率时间序列对本文模型进行了实证.结果表明,混合模型预测精度得到了明显的提高.     

基于预测有效度的非负变权组合预测模型研究

本以预测方法有效度为准则,分别在样本区间、预测区间及总区间上建立了非负变权的组合预测模型,并给出其线性规划的解法,该模型具有较二次规划计算简便的特点,而且目标函数具有可比性,能反映不同指标序列预测方法有效性,同时变权能适应外界环境的变化。     

Expected Shortfall and optimal hedging payoff

By using variational techniques, we provide an optimal payoff written on a given random variable for hedging – in the sense of minimizing the Expected Shortfall at a given threshold – a payoff written on another random variable. In numerous financially relevant examples, our result leads to optimal payoffs in closed form. From a theoretical viewpoint, our result is also useful for providing bounds to the classical Expected Shortfall minimization problem with given financial instruments.     

Risk quantification and validation for Bitcoin

This paper introduces a semi-nonparametric approach for modeling Bitcoin risk relatively to other parametric distributions and volatility models. Model performance is assessed through different backtesting techniques, including multinomial test, for three risk measures: Value-at-Risk, Expected Shortfall and Median Shortfall. Our results show that the ‘large’ semi-nonparametric expansion is a good alternative to measure Bitcoin risk according to recommendations of Basel Committee on Banking Supervision, but also that 99%-Median Shortfall seems to be an accurate and robust risk measure for Bitcoin.     

Portfolio selection with transaction costs under expected shortfall constraints

An investor subject to proportional transaction costs allocates funds to multiple stocks and a bank account, to maximise the expected growth rate of the portfolio value under Expected Shortfall (ES) constraints. In a numerical example with ten time steps and one stock important innovations are caused by the introduction of the Expected Shortfall constraint: First, expected returns are reduced by less than one-tenth when the ES constraint is introduced. In comparison, economic capital as measured by ES, is reduced to amounts between one-half and three-quarters, when the ES constraint is introduced. Second, the dependence of expected return and ES on the initial portfolio, in particular when transaction costs are high, is largely removed by the introduction of the ES constraint.     

α-混合序列下期望损失ES的两步核估计

期望损失(Expected Shortfall,ES)是当今最流行的金融资产风险管理的工具之一,是一个理想的一致性风险度量.本文在α-混合序列具有幂衰减混合系数条件下,用两步核估计估算风险度量ES的值,第一步是在险价值(Value at Risk,VaR)的核估计,第二步是ES的核估计.得到ES的核估计量的Bahadur表示,以及均方误差和渐近正态性的收敛速度.     

基于扭曲混合Copula和ARMA-GARCH-t模型的投资组合风险分析——以上证综指、中证综合债和上证基金为例

利用扭曲混合Copula和ARMA-GARCH-t模型,对包含2015年股灾和2016年熔断期间的上证综指、中证综合债和上证基金的投资组合风险相关性进行建模分析。研究表明:扭曲混合Copula模型较混合Copula模型能更好地拟合各资产日收益率间的相关结构,尤其是"厚尾"特性。并运用蒙特卡罗模拟法计算各资产的风险价值、预期损失和中位数损失并讨论其差异性,以期为关注风险管理的人们提供更多借鉴。     

Evaluating Currency Risk in Emerging Markets

We present a systematic approach to the problem of evaluating currency risk. The approach involves a test for stationarity, and a method of estimating Value-at-Risk (VaR) and Expected Shortfall (ES) from dependent heavy-tailed data. Various estimation methods are compared and the accuracy of the approach is discussed. An application of the technique to the Mexican peso/US dollar exchange rate reveals the level of currency risk foreign investors face in Mexico.      

Drawdown: from practice to theory and back again

Maximum drawdown, the largest cumulative loss from peak to trough, is one of the most widely used indicators of risk in the fund management industry, but one of the least developed in the context of measures of risk. We formalize drawdown risk as Conditional Expected Drawdown (CED), which is the tail mean of maximum drawdown distributions. We show that CED is a degree one positive homogenous risk measure, so that it can be linearly attributed to factors; and convex, so that it can be used in quantitative optimization. We empirically explore the differences in risk attributions based on CED, Expected Shortfall (ES) and volatility. An important feature of CED is its sensitivity to serial correlation. In an empirical study that fits AR(1) models to US Equity and US Bonds, we find substantially higher correlation between the autoregressive parameter and CED than with ES or with volatility.     

Credit portfolio risk and asset price cycles

It is a stylized fact that credit risk is high at the same time when asset values are depressed. However, most of the standard credit risk models ignore this kind of correlation, leading to underestimation of risk measures of portfolio credit risk such as Value at Risk and Expected Shortfall. In our paper we make an attempt to quantify the underestimation of these risk measures when the dependence between credit risk and asset values is ignored and show that credit risk is underestimated by a significant margin.      

Extremes for coherent risk measures

Various concepts appeared in the existing literature to evaluate the risk exposure of a financial or insurance firm/subsidiary/line of business due to the occurrence of some extreme scenarios. Many of those concepts, such as Marginal Expected Shortfall or Tail Conditional Expectation, are simply some conditional expectations that evaluate the risk in adverse scenarios and are useful for signaling to a decision-maker the poor performance of its risk portfolio or to identify which sub-portfolio is likely to exhibit a massive downside risk. We investigate the latter risk under the assumption that it is measured via a coherent risk measure, which obviously generalizes the idea of only taking the expectation of the downside risk. Multiple examples are given and our numerical illustrations show how the asymptotic approximations can be used in the capital allocation exercise. We have concluded that the expectation of the downside risk does not fairly take into account the individual risk contribution when allocating the VaR-based regulatory capital, and thus, more conservative risk measurements are recommended. Finally, we have found that more conservative risk measurements do not improve the fairness of the cost of capital allocation when the uncertainty with parameter estimation is present, even at a very high level.     

Regularizing Portfolio Risk Analysis: A Bayesian Approach

It is important for a portfolio manager to estimate and analyze portfolio volatility, to keep the portfolio’s risk within limit. Though the number of financial instruments in the portfolio can be very large, sometimes more than thousands, daily returns considered for analysis are only for a month or even less. In this case rank of portfolio covariance matrix is less than full, hence solution is not unique. It is typically known as the “ill-posed” problem. In this paper we discuss a Bayesian approach to regularize the problem. One of the additional advantages of this approach is to analyze the source of risk by estimating the probability of positive ‘conditional contribution to total risk’ (CCTR). Each source’s CCTR would sum up to the portfolio’s total volatility risk. Existing methods only estimate CCTR of a source, and does not estimate the probability of CCTR to be significantly greater (or less) than zero. This paper presents Bayesian methodology to do so. We propose a simple Monte Carlo (MC) approach to achieve our objective, which can be paralleled. Estimation of various risk measures, such as Value at Risk and Expected Shortfall, becomes a by-product of this Monte-Carlo approach.