基于EMD与DVG的非线性时间序列预测模型及其应用研究

针对具有非线性和不稳定性的时间序列,提出一种结合经验模态分解(EMD)、有向可见图(DVG)网络的动态预测模型。利用经验模态分解将原时间序列分解为多个固有模态函数(IMF),然后对分解后的高频和低频IMF利用快速傅里叶变换得到各自的周期;依据每个周期,从原时间序列的尾部截取长短不一的子序列,然后采用有向可见图算法转换为多个有向网络,利用随机游走在每个有向网络中寻找与时间序列最后一个节点相似的节点;最后,依据平行线法,预测时间序列的下一个数值。原油价格的时间序列是一类典型的具有非线性和不稳定性的序列,利用此模型对WTI原油每日价格进行实证分析。研究结果表明,此模型不但可以有效地预测时间序列的变化趋势,而且具有较高的预测精度。     

违约预测的小波结构模型研究

本文针对上市公司违约预测问题,按照行业类型对我国2009年的上市企业进行分层抽样,构建了小波结构模型.小波结构模型通过应用小波变换来分解上市公司日收益序列,进而对低频序列和高频序列分别构建预测模型,再依据预测模型对未来收益进行预测,最后使用小波逆变换重构预测收益序列.通过小波结构模型可以避免时间序列模型进行收益波动预测的累加计算过程.在结合我国上市公司的实际数据对这两种模型的校验中,可以发现小波结构模型比时序结构模型在违约预测上有更好的识别力和准确度.     

小波包与混沌集成的股票市场预测新方法

基于小波包变换和混沌理论提出了一种股票市场建模及其预测的新方法,既能刻划时间序列的规律,又能捕捉混沌状态的特征.首先,应用小波包变换对上证综指和深证成指日收益率序列进行三层分解,分别得到第三层从低频到高频八个频率成分的时序,并在此基础上作进一步分析,结果表明中国股市存在混沌特性;然后,应用混沌理论分别建立从低频到高频八个时序的预测模型,分别对八个时序进行预测;最后,基于小波包理论对混沌模型预测的结果予以重构,实现对原始收益率序列的预测.与现有方法比较,结果表明该方法具有较高的精度,有极大的应用范围.     

基于EMD和SVMs的原油价格预测方法

针对原油价格预测问题,提出一种基于EMD(经验模式分解)和SVMs(支持向量机)的非线性组合预测方法.该方法运用EMD技术将原油价格序列分解成若干个不同频率的分量,根据频率高低将各分量分组叠加得到3个新序列,分别代表市场波动价格、重大事件价格、趋势价格;针对此3个序列,构建不同SVMs模型分别进行预测,得到各序列预测值;用SVMs针对各序列预测值构建组合模型得到最终预测值.采用WTI和Brent原油现货价格数据验证本方法的有效性,结果表明,此方法与单一的SVMs模型和人工神经网络模型相比,具有较高的预测精度.     

股市预测中的小波神经网络方法的研究

本文首先论述了股市时间序列中的明显随机性,可能是由于非线性确定性系统中混沌行为的缘故,利用混沌的确定性可以进行短期预测.混沌时间序列预测首先要重构相空间,接着充分利用小波变换时频分析的局部化特性,提出了一种改进的小波网络结构,探讨了股市预测模型问题.经实例验证,该方法能有效地提高预测精度,避免了人工神经网络模型和指数自回归的固有缺陷.     

基于EEMD-LSTM的农产品价格短期预测模型研究

本文将集成经验模态分解(EEMD)方法与长短期记忆网络(LSTM)相结合，构建了一个端到端的农产品价格短期预测模型。首先，对原始价格信号进行EEMD分解，得到若干IMF子序列和一个残差序列；然后，运用Fine-to-coarse高低频重构方法对IMF子序列进行高频—低频重构；最后将原始价格序列、高频项、低频项和残差趋势项作为特征，输入到LSTM网络进行训练得到预测模型。本文以广州市江南农副产品市场的富士苹果日价格为例进行实证分析，结果表明，本文提出的EEMD-LSTM模型在农产品价格短期预测问题上具有一定的性能优势。     

基于小波域隐马尔可夫模型的时间序列分析-平滑、插值和预测

提出一种基于小波域隐马尔可夫模型的时间序列分析方法.首先介绍了离散小波变换;并针对小波系数进行统计建模,分别讨论了单个小波系数的混合高斯模型、不同尺度小波系数之间的隐马尔可夫树结构、模型训练及似然计算等问题;其次,提出了关于时间序列插值、平滑和预测的统一数学模型,并运用极大后验概率估计和贝叶斯原理,将小波域隐马尔可夫模型作为先验知识给出了一种分析时间序列的新方法;然后,详细推导了时间序列重建问题的Euler-Lagrange方程及对数似然的导数计算,将时间序列的插值、平滑和预测归结为一个简单线性方程的求解;最后通过期望极大化(EM)算法和共扼梯度算法进行交替迭代来计算小波域隐马尔可夫模型参数和重建时间序列.实验结果表明该方法在经济领域时间序列分析中的有效性.     

基于小波包和神经网络的股票价格预测模型

股票价格是大量因素影响的综合结果,波动规律异常复杂,即使是神经网络这样强大的非线性预测工具也不堪胜任对其的准确预测。本文利用小波包理论将价格波动序列最优地分解为一系列规律较易掌握的子波动,对原始价格波动的预测也就分成神经网络对各子波动的预测。实证研究结果表明,这种小波包和神经网络相结合的股票价格预测模型预测精度明显高于小波和神经网络相结合以及直接利用价格波动预测的同类神经网络模型。     

短期电价预测的组合混沌方法

电力市场中,电价的变化呈现的是一种非线性的、动态开放的过程,传统的方法已很难提高其预测精度。为此,本文提出一种基于小波变换、计量经济学模型和径向基函数网络的组合混沌预测方法。首先利用小波变换将原电价序列分解、重构成概貌序列和细节序列;在此基础上,针对不同的子序列建立不同的模型,并进行预测;最后将所有子序列的预测结果求和,作为最终的预测值。对西班牙电力市场短期电价的预测表明,该方法具有很高的预测精度。     

基于经验模态分解的房价周期波动实证分析

房地产市场是一个复杂的系统,房价是多种因素共同作用下最终的表现形式。经验模态分解方法是处理非平稳、非线性序列的有效工具,将其运用于房价分析,可以从房价时间序列自身出发揭示内在特征。以杭州市过去四年新建商品住宅交易的周度价格数据为例,对其分解,再根据本征模态函数的特征进行重组。研究表明:房价时间序列由经济基本面决定的长期趋势、金融危机等重大事件带来的低频振动和短期市场不均衡导致的随机波动三方面构成,为短期房价预测提供了思路。杭州市商品住宅市场存在3年的大周期,14个月和7个月的小周期。     

预测困难与预测发展

"凡事预则立,不预则废"这充分说明预测在决策中的重要性,但由于社会、经济系统的复杂性、不确定性,预测有时是困难的,基于此点,人们不断探索新的预测方法。神经网络预测正是近年来发展起来的一种新的预测方法,本文详细探讨了预测困难后,讨论了神经网络预测的优点与不足,并对预测发展提出了自己的思路。     

Forecasting organizational changes

In this article the author argues that because of the difficulties associated with human behaviour such factors are frequently omitted from forecasts. Yet no organization can afford to disregard these factors if their forecasts are to be meaningful. The author includes illustrations of organizational change which he maintains will spread rapidly. Finally he discusses his own initial experiments in forecasting organizational change.     

基于混合估计与预测方法的股市交易量预报

本文通过将目标状态的小波变换系数向量描述为卡尔曼滤波方法的状态变量,进而将卡尔曼滤波和小波分析相结合,提出了既具有实时性和递归性又具有多尺度分析能力的小波-卡尔曼滤波混合估计与预测方法(wavelet-Kalman filtering hybrid estimating and forecasting algorithm,WKHEFA).运用此方法,本文较好地预测了上证指数的交易量.     

Bayesian Forecasting via Deterministic Model

Rational decision making requires that the total uncertainty about a variate of interest (a predictand) be quantified in terms of a probability distribution, conditional on all available information and knowledge. Suppose the state-of-knowledge is embodied in a deterministic model, which is imperfect and outputs only an estimate of the predictand. Fundamentals are presented of two Bayesian methods for producing a probabilistic forecast via any deterministic model. The Bayesian Processor of Forecast (BPF) quantifies the total uncertainty in terms of a posterior distribution, conditional on model output. The Bayesian Forecasting System (BFS) decomposes the total uncertainty into input uncertainty and model uncertainty, which are characterized independently and then integrated into a predictive distribution. The BFS is compared with Monte Carlo simulation and ensemble forecasting technique, none of which can alone produce a probabilistic forecast that quantifies the total uncertainty, but each can serve as a component of the BFS.     

Forecasting expenditure on capital projects

S-curves are widely used for planning, forecasting and control of cost, time and resources of a project. In this paper, a comparison of two S-curve models developed at the Department of Health and Social Security (DHSS) and Bradford University is carried out both from the viewpoint of predictive accuracy and ease of use. The models are validated using expenditure data for 21 recent U.K. health building projects. Methods of least squares is used to estimate the parameters of the two models. These parameters are categorized according to the total cost of the projects. Both the models are shown to be of comparable accuracy for fitting actual expenditure data. The DHSS model has a major advantage of simplicity of form and use, although the slightly greater mathematical complexity of the Keller-Singh model is off-set by the readily interpretable nature of its form and basic parameters. It is concluded that both or either of the models could be used by clients/contractors for effective planning and control of project costs.     

Modeling and Forecasting Realized Volatility

We provide a framework for integration of high–frequency intraday data into the measurement, modeling, and forecasting of daily and lower frequency return volatilities and return distributions. Building on the theory of continuous–time arbitrage–free price processes and the theory of quadratic variation, we develop formal links between realized volatility and the conditional covariance matrix. Next, using continuously recorded observations for the Deutschemark/Dollar and Yen/Dollar spot exchange rates, we find that forecasts from a simple long–memory Gaussian vector autoregression for the logarithmic daily realized volatilities perform admirably. Moreover, the vector autoregressive volatility forecast, coupled with a parametric lognormal–normal mixture distribution produces well–calibrated density forecasts of future returns, and correspondingly accurate quantile predictions. Our results hold promise for practical modeling and forecasting of the large covariance matrices relevant in asset pricing, asset allocation, and financial risk management applications.     

电子商务环境下预测支持系统研究

电子商务的到来极大地改变着未来市场需求模式,预测工作面临着巨大的挑战,如何适应时代的需求,实现预测工作的高效化、智能化,已越来越受到商家的重视.根据近来发展的Agent技术,讨论了电子商务环境下的预测支持系统.     

Forecasting Spanish Natural Life Expectancy

Knowledge of trends in life expectancy is of major importance for policy planning. It is also a key indicator for assessing future development of life insurance products, substantiality of existing retirement schemes, and long-term care for the elderly. This article examines the feasibility of decomposing age-gender-specific accidental and natural mortality rates. We study this decomposition by using the Lee and Carter model. In particular, we fit the Poisson log-bilinear version of this model proposed by Wilmoth and Brouhns et al. to historical (1975-1998) Spanish mortality rates. In addition, by using the model introduced by Wilmoth and Valkonen we analyze mortality-gender differentials for accidental and natural rates. We present aggregated life expectancy forecasts compared with those constructed using nondecomposed mortality rates.     

Forecasting in conditions of uncertainty

Has the business environment grown in uncertainty? In this paper the authors suggest that the root problem is not uncertainty but the malevolence of events these past few years. In turn, this has made uncertainty and the techniques developed to cope with its consequences all the more important to the firm. But while improved forecasting may take the difference between a potentially profitable project and corporate disaster, good forecasting by itself is not enough. Most firms would benefit from examining their forecasting performance in relation to strategic decisionmaking and the various options available. The authors conclude that only in an organization where integration between expert forecaster and forecast user has been achieved can the full benefits of improved forecasting be realized.