基于SOM&SVM组合分类器的客户细分方法实证研究

为解决传统的RFM客户细分方法还不能很好地刻画客户行为,同时也没有就RFM指标权重进行分析这一问题,在RFM指标的基础上扩充了客户细分的指标体系,并提出了基于AHP的RFM指标权重确定策略.鉴于传统的单一分类器存在的很多缺陷,提出基于SOM&SVM的组合分类器模型,充分利用SOM和SVM单一分类器各自的优点,综合两种分类器的分类信息,避免单一分类器可能存在的片面性,从而提高分类的准确性.最后通过实例对上述模型的有效性进行验证.     

基于KNN和Bayes算法的组合分类器的垃圾评论识别研究

产品垃圾评论在一定程度上影响了评论信息的参考价值,本文旨在建立识别模型将垃圾评论从评论文本中剔除,保留真实的产品评论。首先,分析了产品评论的特点,从数据搜集、文本预处理、互信息检验、文本表示4个模块提取了14个特征。然后,利用高互补性建立了基于KNN和Bayes算法的组合分类器模型。最后,利用交叉验证对iPhone 6Plus的产品评论进行检验,得到评价指标分别为:正确识别率75.3%、召回率82.1%以及F1值77.5%.     

国内生产总值的一种组合预测方法

对于国内生产总值的预测问题,运用贝叶斯估计方法将主观先验信息、样本拟合区信息和单个模型的预测信息进行了有效综合,导出了三种组合预测方法,并给出了误差方差的估计量.最后是一个应用实例.     

基于贝叶斯方法的低违约组合违约率估计

现代信用风险建模的核心是估计违约率,违约率估计是否准确将直接影响信用风险建模的质量。在估计违约率的众多文献中,频率法或logistic回归等统计方法的运用非常广泛,此类统计模型的基础是大样本,它客观上需要最低数量或最优数量的违约数据,而低违约组合(LDP)是指只有很少违约数据甚至没有违约数据的组合,如何估计LDP的违约率、反映违约率的非预期波动是一个值得关注的现实问题。本文针对银行贷款LDP缺乏足够历史违约数据的情况,采用贝叶斯方法估计LDP的违约率,并进一步探讨了根据专家判断或者根据同类银行LDP违约数量的历史数据来确定先验分布的方法。在贝叶斯估计中,通过先验分布的设定,不仅可以实现违约率估计的科学性和合理性,而且可以反映违约的非预期波动,有助于银行实施谨慎稳健的风险管理。     

一个古老等式的组合证明

采用组合的方法,对∑nk=0n+kknk(m-1)n-k=∑nk=0nk2mk这一等式提供了一种全新的证明.此外,还提供了一种完全不用微积分的代数证明.     

基于RS-Bag分类器集成技术的上市公司财务危机预测

财务危机预测是金融管理决策中的重要问题,其实质是对未来财务状况的预报和分类。鉴于目前单一分类器预测性能不稳定,本文运用分类器集成技术,以BP神经网络为分类学习算法,建立基于RS-Bag算法的神经网络分类器集成模型。然后,以我国上市公司财务数据为例进行财务危机预测实证研究,结果表明,基于RS-Bag算法的神经网络分类器集成预测精度和泛化性能优于单一神经网络分类器,也优于Bagging分类器集成和RS分类器集成。     

基于交互耦合网络的项目组合决策模型研究

随着项目活动进入“大尺度”时代,复杂性成为现代化项目组合管理中的突出问题。在项目组合决策系统复杂性分析基础上,提出了交互耦合网络视角下的项目组合决策系统表征方法;借鉴非线性动力学建模方法构建项目组合决策系统复杂动力网络模型,结合模型的稳定解和稳定条件将项目组合决策系统划分为竞争型、共生型、强依存型和弱依存型,并通过数值仿真方法对系统的稳定域、分岔和混沌进行分析。研究表明,项目组合决策系统的复杂性和稳定性依赖于系统内交互关系作用,改善协作关系,避免过分竞争,以系统整体为先优化配置有利于项目组合目标实现。     

两个组合恒等式的联系及其组合意义和概率论证法

贵刊 2 0 0 1年第 6期刊载的文 [1 ]证明了组合等式 :∑ｎｉ=0(-1) ｉＣｉｎｉｋ =0　　　　　当ｋ≤ｎ-1且ｋ∈Ｎ时(-1) ｎｎ !　当ｋ =ｎ时笔者发现上述结论正是贵刊 1 996年第 6期刊载的文 [2 ]定理的推论的另外一种表述 .文 [2 ]的定理及推论如下 :定理　设ｆ(ｘ) =ａｘｎ+1 +ｂｘｎ+ｃｎ- 1 ｘｎ- 1 +…+ｃ1 ｘ+ｃ0 是ｎ+ 1次多项式 .则 ∑ｎｉ=0( - 1 ) ｉｆ(ｉ)Ｃｉｎ= ( - 1 ) ｎｎ !(ａＣ2 ｎ+1 +ｂ)… ( )推论 :设ｆ(ｘ) =ａｘｍ+ｂｍ- 1 ｘｍ- 1 +… +ｂ0 是ｍ次多项式 ,则　∑ｎｉ =0( - 1 ) ｉｆ(ｉ)Ｃｉｎ =( - 1 ) ｎｎ !ａ…     

基于分支定界组合权的综合评价方法

提出一种将主观权重区间和客观权重相结合的线性加权组合权确定方法.通过数学规划模型,不断寻找与组合权重综合评价结果序关系最为接近的主观权重,并由此采用分支定界思想优化主观权重区间,得到具有序关系一致性的最优主观权重.算例分析表明,优化后的主观权重、客观权重和组合权的综合评价结果将带来被评价对象序关系的一致性,验证了该综合评价方法的科学性.     

一个组合问题的研究

此文基本上还是“穷举法” ,只是稍加分类 ;五类中只选择了最容易的一个小类详细算出 ,四类复杂的情形只公布了他的计算结果 ,无法验证是否正确 ,这是赵慈庚先生五年多以前提出的问题 ,至今没有解答 .发表此文 ,作为抛砖引玉     

Stepwise BAN estimators for exponential families with multivariate normal applications

Consistent, asymptotically efficient and asymptotically normal stepwise estimators are given for a subclass of the uniparametric and multiparametric exponential families. The estimators are derived by using the Robbins-Monro stochastic approximation procedure with certain families of random variables arising from the normalized log-likelihood. Considered in detail are three multivariate normal examples where the maximum likelihood estimators are not tractable.     

The Combination of Forecasts

Two separate sets of forecasts of airline passenger data have been combined to form a composite set of forecasts. The main conclusion is that the composite set of forecasts can yield lower mean-square error than either of the original forecasts. Past errors of each of the original forecasts are used to determine the weights to attach to these two original forecasts in forming the combined forecasts, and different methods of deriving these weights are examined.     

成分数据的组合预测

成分数据是一类具有复杂性质的数据,特别是它的预测研究在管理学与经济学中占有很重要的地位.组合预测则是近年来在预测中应用比较广泛的一种方法,它能够充分利用单预测模型的信息,提高预测精度,增强预测的稳定性,且具有较高的适应能力.本文首次把组合预测方法应用到成分数据的预测分析中,基于成分数据的一些基本性质,利用组合预测得到了较好的预测结果.     

Quadratic Majorization for Nonconvex Loss with Applications to the Boosting Algorithm

Classical robust statistical methods dealing with noisy data are often based on modifications of convex loss functions. In recent years, nonconvex loss-based robust methods have been increasingly popular. A nonconvex loss can provide robust estimation for data contaminated with outliers. The significant challenge is that a nonconvex loss can be numerically difficult to optimize. This article proposes quadratic majorization algorithm for nonconvex (QManc) loss. The QManc can decompose a nonconvex loss into a sequence of simpler optimization problems. Subsequently, the QManc is applied to a powerful machine learning algorithm: quadratic majorization boosting algorithm (QMBA). We develop QMBA for robust classification (binary and multi-category) and regression. In high-dimensional cancer genetics data and simulations, the QMBA is comparable with convex loss-based boosting algorithms for clean data, and outperforms the latter for data contaminated with outliers. The QMBA is also superior to boosting when directly implemented to optimize nonconvex loss functions. Supplementary material for this article is available online.     

加权线性支持向量分类机的数据扰动分析

加权线性支持向量分类机是数据挖掘的新方法.它对应于一个优化问题.针对加权线性支持向量分类机优化问题建立了数据扰动分析理论方法.具体地针对加权线性支持向量分类机的原始问题建立了数据扰动分析基本定理,定理可以得到加权线性支持向量分类机问题的解及决策函数对数据参数的偏导数,同时可以定量分析输入数据的误差以及数据各种变化对其解以及决策函数值的定量影响,可以回答加权线性支持向量分类机问题的稳定性问题和灵敏度分析问题.     

A simple extension of boosting for asymmetric mislabeled data

This letter provides a simple extension of boosting methods for binary data where the probability of mislabeling depends on the label of an example. Loss functions are derived from the statistical perspective, which is based on likelihood analysis. Our proposed methods can be interpreted as a correction of the decision boundary of observed labels. This interpretation partially relates to cost-sensitive learning, a classification method for the case in which the ratio of two labels in a dataset is skewed. Numerical experiments show that the proposed methods work well for asymmetric mislabeled data even when the probabilities of mislabeling may not be precisely specified.     

素环上导子的线性组合

In this paper we discuss the linear combination of derivations in prime rings which was initiated by Niu Fengwen.Our aim is to improve Niu‘s result.For the proof of the main theorem we generalize a result of Bresar and obtain a lemma that is of independent interest.     

群逆的仿射组合表示

In this paper, we first give two equalities in the operation of determinant. Using the expression of group inverse with full-rank factorization Ag = F（GF）^-2G and the Cramer rule of the nonsingular linear system Ax = b, we present a new method to prove the representation of group inverse with arlene combination
Ag=∑（I,J）∈N（A） 1/υ^2det（A）IJ ajd AJI.
A numerical example is given to demonstrate that the formula is efficient.     

Aggregated estimators and empirical complexity for least square regression

Numerous empirical results have shown that combining regression procedures can be a very efficient method. This work provides PAC bounds for the L² generalization error of such methods. The interest of these bounds are twofold.First, it gives for any aggregating procedure a bound for the expected risk depending on the empirical risk and the empirical complexity measured by the Kullback–Leibler divergence between the aggregating distribution and a prior distribution π and by the empirical mean of the variance of the regression functions under the probability .Secondly, by structural risk minimization, we derive an aggregating procedure which takes advantage of the unknown properties of the best mixture : when the best convex combination of d regression functions belongs to the d initial functions (i.e. when combining does not make the bias decrease), the convergence rate is of order (logd)/N. In the worst case, our combining procedure achieves a convergence rate of order which is known to be optimal in a uniform sense when (see [A. Nemirovski, in: Probability Summer School, Saint Flour, 1998; Y. Yang, Aggregating regression procedures for a better performance, 2001]).As in AdaBoost, our aggregating distribution tends to favor functions which disagree with the mixture on mispredicted points. Our algorithm is tested on artificial classification data (which have been also used for testing other boosting methods, such as AdaBoost).     

The Combination of Forecasts: a Bayesian Approach

This paper develops a general Bayesian approach to the problem of combining forecasts. This approach leads to the results of Bates and Granger in certain special cases and to a geometric averaging formula in other special cases.