基于结构方程模型的市场细分方法应用研究

结构方程模型是当前研究顾客满意和顾客忠诚的主流方法之一,但基于结构方程对顾客满意和顾客忠诚进行市场细分方法的研究却十分缺乏.基于结构方程模型进行市场细分算法的应用研究,并对得出的细分结果进行了解释.     

基于数据和整体的航空网络静态定价模型

建立了一个静态定价与座位分配联合模型.利用模型的性质,将问题简化为一个可分的凹规划模型.特别地,在一个三航段网络上,从模型的网络流形式推出最优目标函数具有良好的性质,并对模型的最优价格决策进行了灵敏度分析.最后给出了一个双枢纽网络上对细分产品定价的算例.     

混合回归模型在百货商店市场细分中的应用

基于国内20家大型百货商店消费者满意调查数据,本文采用混合回归模型,对百货商店的消费者进行市场细分研究,发现百货商店的消费者可以分为6个差异化的细分市场.同时对每个细分市场的需求特征及市场规模进行了描述,并探讨了消费者人口统计变量与所属细分市场的关系.     

消费者异质性下基础产品及其附加品的供应链定价策略研究

建立一个由制造商和销售商组成的二级供应链模型,在销售商向消费者销售制造商基础产品的同时提供可选附加品的供应链多产品定价背景下研究了制造商及销售商的定价策略。以消费者对附加品价值增值存在的异质性将基础产品及其附加品的消费市场细分为基础产品单独消费市场及产品共同消费市场。基于市场细分比例以及附加品价值增值程度,讨论了不同条件下制造商及销售商的定价策略以及所形成的供应链定价均衡,分析了产品定价均衡与市场细分比例、附加品价值增值程度之间的关系。     

考虑消费者偏好的绿色产品歧视定价决策研究

考虑到消费者对绿色产品和普通产品的偏好程度不同,对消费者的类型进行细分,运用价格歧视理论,构建了绿色产品的歧视定价模型.通过对定价模型进行数值仿真和消费者偏好系数的敏感性分析,分析了消费者细分区间对定价、需求量及利润的影响,并比较了常规定价和歧视定价策略下需求量之间的关系.研究表明:区间需求量与该区间消费者的比例及普通消费者的消费水平正相关,且随着消费者细分区间的增加,绿色产品的区间需求量随之降低,所以,常规定价策略下绿色产品制造商的利润较高;在普通产品的生产成本较小时,普通产品的区间需求量随之增加,歧视定价策略下普通产品制造商的利润较高.     

带有缺失数据的结构方程模型中的模型选择问题

结构方程模型在社会学、教育学、医学、市场营销学和行为学中有很广泛的应用。在这些领域中,缺失数据比较常见,很多学者提出了带有缺失数据的结构方程模型,并对此模型进行过很多研究。在这一类模型的应用中,模型选择非常重要,本文将一个基于贝叶斯准则的统计量,称为L_v测度,应用到此类模型中进行模型选择。最后,本文通过一个模拟研究及实例分析来说明L_v测度的有效性及应用,并在实例分析中给出了根据贝叶斯因子进行模型选择的结果,以此来进一步说明该测度的有效性。     

前馈神经网络和Logit回归的比较研究

近年来 ,前馈神经网络广泛地应用在 Logit回归作为标准统计方法的分析领域 .但却很少作它们之间的直接比较 ,本文是 Logit回归和前馈神经网络“比较研究”的一个尝试 ,说明了一些理论结果和特性 ,讨论了在它们的应用中碰到的一些实际问题 ,还进一步用分析的和模拟的两种方法研究了一些重要的渐近概念、过分拟合以及模型选择等问题 ,最后讨论并给出一些结论     

基于因子隐马尔可夫模型的VaR与ES联合预测

VaR和ES是衡量金融资产风险的重要测度,对风险控制和金融危机的识别具有重要意义。本文以CAViaR模型为基础,通过因子隐马尔可夫模型构造潜变量,作为CAViaR模型的回归系数的组成部分,最终提出了一个含潜变量的VaR和ES联合估计方法(FHM-CAViaR),实现了VaR和ES的联合预测。在该模型中,潜变量由一个因子隐马尔可夫模型驱动,可以刻画市场信息对模型系数带来的长期效应与短期冲击,该因子隐马尔可夫模型的引入实现了分位数回归模型参数在上百个状态间的转换。最后,基于本文提出的FHM-CAViaR模型分别对上证综指、深证综指和纳斯达克指数的对数收益率数据进行实证分析。实证结果表明,本文提出的模型具有更优的预测效果。此外实证结果还表明,在危机期间VaR的序列聚集性有着显著的增加。本文提出的模型可以通过潜变量的变化识别市场的机制变换,且能更精确地对金融资产的VaR以及ES进行估计,给出金融风险度量一种新的研究方法。     

对非对称有理细分矩阵的改进

在图形图像显示中,运算次数的多少直接影响图像的显示速度.通过对非对称细分矩阵的运算量较大的因素进行分析,并在分析的基础上对细分矩阵加以改进,简化细分矩阵结构减少一些不必要的运算与重复运算,构造出一种结构比较简单、运算量比较少的细分矩阵.新构造的细分矩阵可以有效的提高运算速度.应用新构造的细分矩阵生成细分曲线,对所生成的细分曲线进行比较,得出改进细分矩阵使得运算量明显减少,提高图形的显示速度.     

基于可拓集方法改进波士顿矩阵研究

传统波士顿矩阵分析模型衡量指标少、僵化,仅比较适用于市场上处于寡头垄断的大型企业.基于可拓集方法改进后的新波士顿矩阵分析模型,首先根据企业、行业实际情况设定评价指标,然后建立可拓集与综合关联函数,以对业务类型进一步细分.其次,再根据拓展分析方法和可拓变换方法对细分后属于问题类的业务进行拓展、变换,可形成使问题类业务转变为明星类或金牛类业务的若干策略,为企业市场决策提供参考.改进后的新波士顿矩阵分析模型不但适用于大型企业,亦适用于中小企业,更具有普适性.     

聚类回归分析(CLR)在市场细分研究中的应用

本文从市场细分方法的角度,打破了传统的根据样本在心理感知或偏好等多个变量的距离进行细分的思路,采用一种新的聚类回归分析方法基于变量间的因果关系对顾客进行细分,不仅可以把顾客有效地划分成具有不同特点的群体,而且可以根据不同要素的因果关系确定不同群体中的关键影响要素.本文以电热水器行业顾客满意度研究为例,根据不同要素对满意度影响的差异进行市场细分.分析表明,采用这种方法,企业可以在经营管理过程中通过差异化策略获得竞争优势.     

Noisy image segmentation based on nonlinear diffusion equation model

This paper addresses the segmentation problem in noisy image based on nonlinear diffusion equation model and proposes a new adaptive segmentation model based on gray-level image segmentation model. This model also can be extended to the vector value image segmentation. By virtue of the prior information of regions and boundary of image, a framework is established to construct different segmentation models using different probability density functions. A segmentation model exploiting Gauss probability density function is given in this paper. An efficient and unconditional stable algorithm based on locally one-dimensional (LOD) scheme is developed and it is used to segment the gray image and the vector values image. Comparing with existing classical models, the proposed approach gives the best performance.     

Dynamic entry deterrence in the UK pathology services market

This paper describes work on a dynamic model of entry deterrence applied to the UK National Health Service (NHS) market for pathology services. The model, based on a game theoretical framework, is concerned with decision support applications. Presented in this paper is a case study analysis of a geographical region in which a provider of pathology services is concerned at the prospect of being exposed to competition from a new entrant. The incumbent provider may undertake strategic investments to create a stock of knowledge and goodwill with the intention of dissuading others from entering the market. The effect of a new entrant is modelled as perturbation of a pre-existing stable Nash-Cournot equilibrium in an oligopolistic market, and is influenced by market forces subject to Government regulation. The original contribution of this study is to identify the nature of these potential strategic investments and their interaction with cash flows. Recent historical data and managerial analysis are used to characterise market growth. An estimate of the incumbent provider's market share which is at risk can be found by examining the local geographical distribution of providers and purchasers of pathology services. On the basis of this analysis we propose a method for obtaining the strategic investment profile which minimises the total investment required to deter entry.     

金融市场波动性的拟合分析

金融市场的波动性是投资者关注的对象之一,也是被研究的热点。本文检验了我国股市的ARCH效应和序列相关性。并且在此基础上,将AR-IGARCH-M模型应用于上海综指和深圳成指,结果表明该模型能有效拟合我国深沪两股市的波动性。最后,针对结果分析了我国的股市行为。     

基于下界VaR对沪深股市市场风险的实证研究

本文应用Luciano和Marena提出的计算资产组合VaR的上下界的方法,对沪深股市的市场风险做了实证研究,并与传统的正态VaR做了比较。实证分析表明,沪深股市的市场风险确实存在“厚尾”和“波动聚集”现象。本文对国内市场的波动聚集现象进行了详细分析．并讨论了风险控制模型的相关检验,下界VaR通过了两次模型检验。     

Unsupervised construction of fuzzy measures through self-organizing feature maps and its application in color image segmentation

The paper presents a framework for the segmentation of multi-dimensional images, e.g., color, satellite, multi-sensory images, based on the employment of the fuzzy integral, which undertakes the classification of the input features. The framework makes use of a self-organizing feature map, whereby the coefficients of the fuzzy measure are determined. This process is unsupervised and therefore constitutes one of the main contributions of the paper.The performance of the framework is shown by successfully realizing the segmentation of color images in two different applications. First, the features of the framework and its parameterization are analyzed by segmenting different images used as benchmark in image processing. Finally, the framework is applied in the segmentation of different images taken under difficult illumination conditions. The images serve the development of an automated cashier system, where the weak segmentation constitutes the first step for the identification of different market items. The presented framework succeeds in the segmentation of all these color images.     

Customer choice prediction based on transfer learning

Choice behaviour prediction is valuable for developing suitable customer segmentation and finding target customers in marketing management. Constructing good choice models for choice behaviour prediction usually requires a sufficient amount of customer data. However, there is only a small amount of data in many marketing applications due to resource constraints. In this paper, we focus on choice behaviour prediction with a small sample size by introducing the idea of transfer learning and present a method that is applicable to choice prediction. The new model called transfer bagging extracts information from similar customers from different areas to improve the performance of the choice model for customers of interest. We illustrate an application of the new model for customer mode choice analysis in the long-distance communication market and compare it with other benchmark methods without information transfer. The results show that the new model can provide significant improvements in choice prediction.     

Analysing consumer segments to budget for loyalty and promotion programmes and maximize market share

This paper seeks to provide a framework and benchmark for the allocation of marketing budget between promotion and loyalty programmes using an approach that combines a Markov-type market share model and the Lagrange multiplier method to maximize market share. The Lagrange multiplier method, that takes into account the market share and the loyalty effect observable in preceding periods along with the estimated promotional effects, permits the allocation to be optimized and future market share to be maximized. Then, loyalty-based consumer segment are used to explain why the budgeting exercise can achieve the maximization objective. To this end, the study uses consumer panel data concerning three categories, namely, adult milk powder, shampoo, and detergent. It extends previous research on loyalty-based segmentation by focusing on the budget allocation between the two options of loyalty enhancement and promotion programming. A Budget Allocation Grid for Loyalty-based Segmentation is proposed as an aid to understand budget allocation between loyalty and promotion programmes based on the relative sizes of exclusive-loyalty and variety-seeking segments.