基于小波神经网络与ARIMA组合模型在股票预测中的应用

为了实现对股票价格变化的短期预测,提出了一种基于小波神经网络(WNN)与自回归积分滑动平均模型(ARIMA)的组合预测模型.将股票的收盘价序列数据划分为线性以及非线性(误差项)两个部分,分别利用统计学中ARIMA模型和小波神经网络分别对两部分数据进行预测并得到结果,将两部分结果组合相加合成为整个股票价格的预测结果.实验结果表明该组合模型在预测精度方面有提高,是一种比较有效的预测模型.     

回收率依赖回收产品质量的再制造EOQ模型

研究回收率依赖回收产品质量情况下制造/再制造混合系统的EOQ模型.该模型假设顾客的需求可通过新产品的制造和回收产品的再制造两种方式满足,且这两种产品无质量差异;需求率是确定的、连续的;总成本包括制造和再制造的固定启动成本,可销售产品和回收品的库存成本,以及缺货成本.当假设缺货成本无限大时给出不允许缺货情况下的模型.给出算例验证模型的有效性.     

基于随机占优的股指期货市场有效性分析

2015年中金所出台严格监管措施后,股指期货成交低迷,异象频出。为验证严格监管措施对股指期货市场有效性的影响,本文利用随机占优DD测试法,为风险规避者和风险寻求者分别构建升序和降序占优模型。传统DD测试法用等间距划分的方式产生网格,且假设检验的两个判定阈值为相反数,这不符合金融数据的分布规律。因此,本文提出了对DD测试法的两处改进,利用“等频率划分法”产生网格,利用“非对称分位数法”产生阈值。实证方面,本文对三个股指期货及其现货的15分钟数据进行分析,发现在自股灾以来,上证50指数一阶占优于上证50股指期货,形成套利机会,且该套利策略的年化收益率、夏普比率和卡玛比率都非常优异。实证进一步显示,严格监管措施后占优数量达到最高峰,严格监管措施导致的股指期货功能受损比股灾更严重,而这一现象在中金所逐步放松监管措施后得以稍微缓解但没有根本改变。     

外汇市场、股票市场与房地产市场的风险传染研究——基于三元VAR-BEKK-GARCH模型实证分析

本文将人民币汇率、房价和股价三者纳入一个统一的分析框架中,从水平变动和波动风险两个方面考虑时变异方差和变量间的风险传递效应,使用“二次汇改”后的2010年6月到2017年12月的月度数据,采用三元GARCH和BEKK时序模型研究人民币汇率、房价和股价之间的动态影响关系及其波动风险互动机制。研究发现,三个市场相互之间具有明显的影响,特别是价格波动的风险传染上,房地产市场与股票之间、股票市场与汇率市场之间或长期或短期都存在风险的传递效应。具体而言,市场在均值溢出方面,人民币升值会促进房价和股价的上涨;但房价与股价之间的价格影响关系并不明显。在波动溢出方面,房价和股价之间的波动溢出效应明显,同时存在ARCH和GARCH型波动效应,而股价对汇率的波动影响也同时存在ARCH和GARCH型波动效应,但汇率对股价仅有GARCH型波动效应。     

Dyck paths with a first return decomposition constrained by height

We study the enumeration of Dyck paths having a first return decomposition with special properties based on a height constraint. We exhibit new restricted sets of Dyck paths counted by the Motzkin numbers, and we give a constructive bijection between these objects and Motzkin paths. As a byproduct, we provide a generating function for the number of Motzkin paths of height $k$ with a flat (resp. with no flats) at the maximal height.     

Embedding optimisation algorithms with Mosel

Algebraic modelling languages allow models to be implemented in such a way that they can easily be understood and modified. They are therefore a working environment commonly used by practitioners in Operations Research. Having once developed models, they need to be integrated inside the company information system. This step often involves embedding a model into a programming language environment: many existing algebraic modelling languages make possible to run parameterised models and subsequently retrieve their results, but without any facility for interacting with the model during the model generation or solution process.In this paper we show how to use the Mosel environment to implement complex algorithms directly in the modelling language.The Office cleaning problem is solved by a branch-and-cut algorithm, implemented entirely in the modelling language (including the definition of the callback function for the solver). Secondly, a cutting stock problem is solved by column generation, also implemented in the modelling language.AMS classification: 90Cxx, 65K05, 68N15     

How likely is Polya's drunkard to stay in x⩾ y⩾z?

In his celebrated paper, Polya has considered the random walk in the three-dimensional (cubic) lattice and showed that the probability of return to the origin is less than 1. Subsequent authors have shown that the probability is %34.053.... Here we consider the same random walk, with the restriction that the drunkard is only allowed to stay inxyz. It is shown that his probability of returning to the originand staying in the allowed region is %6.4844....     

Random walks on inhomogeneous lattices

For lattices with two kinds of points (black and white), distributed according to a translation-invariant joint probability distribution, we study statistical properties of the sequence of consecutive colors encountered by a random walker moving through the lattice. The probability distribution for the single steps of the walk is considered to be independent of the colors of the points. Several exact results are presented which are valid in any number of dimensions and for arbitrary probability distributions for the coloring of the points and the steps of the walk. They are used to derive a few general properties of random walks on lattices containing traps.Presented at the Symposium on Random Walks, Gaithersburg, MD, June 1982.     

Uniform estimate for maximum of randomly weighted sums with applications to insurance risk theory

This paper obtains the uniform estimate for maximum of sums of independent and heavy-tailed random variables with nonnegative random weights,which can be arbi- trarily dependent of each other.Then the applications to ruin probabilities in a discrete time risk model with dependent stochastic returns are considered.     

Investigation of patch antennas based on drilled PBG structure

The method of finite-difference-time domain (FDTD) was used to study the characteristics of the patch antenna based on drilling air holes in the PBG substrate. The results obtained show that the waves propagating along the substrate surface can be suppressed by the drilled photonic crystal band gap (PBG) structure due to the influence of its forbidden band. The energy of the electromagnetic waves is concentrated mainly in the substrate. As a result, patch antennas based on drilling air holes in the PBG substrate have lower return losses (S11) in comparison with the conventional patch antennas; thus, a high gain is reached and the performance is improved. Due to such the advantages, the use of patch antennas can be extended to such fields as mobile communication, satellite communication, aviation, etc.