基于LS-SVM的电子政务评估模型研究

在确立了电子政务网站评估指标体系的基础上,建立了基于最小二乘支持向量机(LS-SVM)的电子政务网站评估模型.研究了新型支持向量机算法一最小二乘支持向量机,并确定支持向量学习决策模式;对华东地区某些科技网站建设水平进行了评估.结果表明,基于最小二乘支持向量机的电子政务网站评估是有效的、可行的.     

基于支持向量机的企业自我实现能力综合评价方法

在企业自我实现能力指标体系的基础上,提出了一种基于支持向量机的企业自我实现能力综合测评方法,该方法具有方便、准确、可靠、快速等特点。实证分析和该方法与BP算法仿真结果的比较表明,支持向量机方法更有效。     

基于支持向量机的突发事件分级研究

突发事件的分级是应急管理的重要环节。将支持向量机方法应用于突发事件的分级问题,阐述了基于支持向量机的突发事件分级方法的过程,以对地震灾害进行分级作为实例,采用多分类支持向量机中的一对一组合方法进行实验。实验结果表明,支持向量机应用于突发事件分级是可行而且有效的,能够为决策者准确地进行分级决策提供科学依据。     

半模糊超球支持向量机多类分类方法研究

针对支持向量机在大类别模式分类中存在的问题,提出了一种基于半模糊核聚类的超球支持向量机分类方法.该方法首先利用半模糊核聚类方法对样本进行预处理,完成边缘样本的选取,进而以所选样本为训练样本进行超球支持向量机训练,从而有效提高分类器的性能.实验表明,该方法比标准支持向量机多类分类方法具有更高的速度和精度.     

财务风险预警的支持向量机应用

本文给出了财务评价指标体系及其量化方法,利用支持向量机的分类能力建立财务风险预警的模型.对上市公司的财务数据进行训练和评估.证明基于支持向量机的财务风险预警模型的可行性和实用性,实验表明支持向量机在小样本情况下具有良好的非线性建模能力和泛化能力.     

锅炉受热面污染部位诊断

基于最小支持向量机,提出了一种快速、有效的锅炉受热面污染部位诊断的方法。以不同受热面出口烟气温度为特征参数,建立了最小支持向量机污染部位诊断模型。利用此模型可以有效诊断锅炉受热面污染情况,并进行仿真测试,证明了该方法的有效性。     

基于双正交小波支持向量机的变结构非线性协整研究

基于双正交小波在非线性信号逼近方面的良好性能,构造了一类新的双正交小波核函数并证明了该核函数满足正定核的容许性条件.在此基础上构造了基于双正交小波支持向量机的非线性协整模型,并基于双正交小波支持向量机和最小拟合误差原则,提出针对向量时间序列的最优非线性变结构点检测的动态规划方法.最后,以美元指数和原油、黄金、铜、铝、锌、铅和锡等七种国际大宗商品期货价格为对象,进行变结构非线性协整的实证研究.结果表明,美元指数与七种国际大宗商品期货价格之间具有复杂的变结构非线性关系,双正交小波支持向量机和最优非线性变结构点检测方法在变结构非线性协整分析上是有效的.     

基于改进支持向量机的电信客户流失预测模型

随着电信业改革的深入和竞争的加剧,电信企业的客户流失率逐步攀升,如何预测并有效减少客户流失直接关系到电信企业的生存和发展.流失客户在客户总体中占比例较低,因此电信客户数据集中存在明显的非平衡数据问题,传统的客户流失预测把客户流失作为普通的模式识别问题处理,建立基于普适机器学习的预测模型.在两类错误的错分代价相差较大的情况下,基于普适机器学习的预测模型缺乏实用价值,因此引入代价敏感学习理论建立了基于改进支持向量机的电信客户流失预测模型,将不同的错分代价纳入建模过程,有效的提高了模型的预测性能.     

基于最优支持向量机模型的经营失败预警研究

根据中国资本市场的实际和样本数据特点,设计一套从样本准备到模型参数优化、再到模型比较的集成解决方案,对上市公司经营失败进行预警,通过实验分析参数调整和核函数选择对支持向量机建模的影响,寻求最优的支持向量机模型.实证结果表明,经营失败预警应用中,参数和核函数的选择对预警模型有较大影响,基于最优支持向量机模型的预测效果优于统计方法和神经网络方法,支持向量机适合中国上市公司分行业小样本的实际.特别处理事件作为经营失败样本切分标准对模型产生一定影响.     

考虑样本不平衡的多准则库存分类加权支持向量机方法及其参数选择

针对ABC库存分类中存在的样本类别不平衡问题,提出了一种基于加权支持向量机的多准则库存分类方法,通过引入类权重因子来解决由于训练集中的类别差异引起的分类结果偏向多样本类的问题.实例研究中,通过一致测试、独立测试以及交叉校验方法进行学习,结果表明加权支持向量机比传统支持向量机具有更小的错分率和更好的稳定性.     

基于知识创造和知识溢出的R&D联盟的动态模型

本文通过对R&D联盟中企业间知识创造和知识溢出的分析,给出了知识存量的一般表示方法,并将参与企业的知识投入和开放水平视为内生变量,构造了知识联盟R&D两阶段的非合作动态博弈模型,提出了在对称的情况下纳什均衡存在并有唯一解的条件,分析了知识投入和知识开放水平在联盟不同时期对企业均衡利润的影响,并通过案例对部分命题提供佐证。最后,在模型假设和模型思想方面进行了一些简单探讨。     

Partnership with an asian family business-What every multinational corporation should know

The family-controlled firm and the state-owned enterprise are the most common ownership structures in Asia. Foreign firms seeking local joint venture partners in Asia will, of necessity, face the prospect of allying with family-controlled firms. Family control in firms creates special concerns that alliance partners should anticipate. Signs of family stability, well-laid succession plans and clearly demarcated professional decision-making represent attractive characteristics for foreign partners. This article will examine the implications of these and other features for alliance partners, using case studies from Indian business. It will also suggest useful sources from which potential partners can obtain information on family-controlled firms.     

Heterogeneity,diversity and complementarity in alliance portfolios

The divergence that a firm manages to achieve because of its partners is a fundamental question in an alliance portfolio configuration. Diversity can refer not only to the differences between the focal firm and its partners or between the partners themselves but also to the differences arising from various resource endowments in the alliance portfolio. Understanding the significance of these different sources, how they interrelate, and how they affect the firm performance is an unresolved question as unclear definitions and opposing arguments are proposed. This paper expounds the concepts of partner heterogeneity, alliance portfolio diversity, and network resource complementarity to gain a deeper comprehension of the alliance portfolio configuration and how it affects performance. Our analysis of airline alliances at a global level reveals the central role of resource complementarity in the focal firm performance.     

International alliance formation and stock market responses:: Industry globalization as an environmental contingency

This study examines the effects of the degree of industry globalization on international alliance formation in terms of the type of alliance chosen by partner firms and stock market responses to the chosen type of alliance. Using a sample of 244 international alliances formed between U.S. and non-U.S. firms for the 1992–97 period, we find that nonjoint venture (joint venture) alliances take place relatively more frequently in global (multidomestic) industries than in multidomestic (global) industries. We also find that in global industries, abnormal returns to nonjoint venture partners are relatively greater than those to joint venture partners, whereas in multidomestic industries, abnormal returns to nonjoint venture partners are relatively smaller, though insignificant, than those to joint venture partners. Our findings suggest that the degree of industry globalization plays an important role in explaining which type of international alliance is likely to be chosen by partner firms when entering an alliance and how stock markets tend to respond to the chosen type of alliance.     

Centrality Asymmetry and Partner Complementarity as Influences on Alliance Dissolution

Research on interfirm alliances indicates that partner firms’ asymmetry in network centrality increases the likelihood of alliance dissolution because it gives rise to a power imbalance and opportunism in the partnership. We contend that this view of centrality asymmetry does not consider the binding force that network resource complementarity can provide in an alliance, which motivates partners to ally for the long term. We propose that centrality asymmetry can have both divisive and cohesive forces in an alliance, which – when considered together – lead to a prediction that centrality asymmetry has a U‐shaped relationship with alliance dissolution. Moderate levels of asymmetry lead to lower rates of dissolution than high and low levels of asymmetry. The degree of cooperation between partners and the degree of external competition reduce the effects of centrality asymmetry on alliance dissolution because they mitigate power imbalances while encouraging partners to strengthen the alliance to withstand competitive challenges.     

竞合视角下高技术企业创新联盟稳定性研究

从竞合的理论视角出发,运用演化博弈理论,通过构建高技术企业创新联盟成员企业竞合关系的演化博弈模型,分析信任度、互补度、风险系数以及合作创新贴现因子等因素对创新联盟稳定性的影响,并运用Matlab对上述因素的影响进行了数值仿真。结果表明,较高的信任度和互补度可以提高联盟成员间的合作意愿,保障联盟的稳定运行;较高的合作创新贴现因子通过降低联盟成员未来收益的不确定性,增强了合作伙伴间进行长期合作的信心,维持了联盟的稳定运行;由于较高的风险系数增加了合作创新的风险成本,导致联盟成员间合作关系可能演变为竞争关系,从而阻碍了联盟的稳定发展。最后,根据演化博弈分析结果提出了相关建议。     

Coping with Diversity in Alliances for Innovation: The Role of Relational Social Capital and Knowledge Codifiability

Alliances are increasingly considered a key element for innovation, especially in knowledge‐intensive firms. While this is true, the mere membership to alliances does not explain innovation performance, and thus the alliance's characteristics that determine high performance must be examined. This research address the question of how the diversity of partners in a certain alliance for innovation affects innovation performance, and how this influence can be moderated by certain characteristics, such as the relational dimension of social capital and the type of knowledge shared among partners. The empirical analysis of a sample of 90 biotech companies shows that there is an inverted U‐shaped relationship between alliance partner diversity and innovation performance and confirms the positive moderating effects of relational social capital and knowledge codifiability. These findings contribute to the current research on alliances for innovation by providing empirical evidence on why some alliances perform better than others. Also, the results suggest that the study of alliance partner diversity, as a determinant of alliance performance, should not be addressed in isolation.     

Partnering with Russia's new entrepreneurs: Software tsarina olga kirova

This article focuses on a Russian woman entrepreneur who established a very successful software firm under license from an American software company. The case illustrates a productive and successful partnership between a Western company and a new Russian entrepreneur. Recent developments in Russian entrepreneurship are reviewed, and the selection of Russian entrepreneurs as business partners is evaluated. The American company is described briefly, followed by an in-depth discussion of its Russian partner and founder, Olga Kirova. Conclusions and interpretations are offered on choosing the right Russian partners, assessing their personal values, objectives and leadership skills, being a good Western business partner, and considering Russian women as business associates.     

The impact of different fit dimensions on spillover effects in brand alliances

Brand alliances represent a popular business strategy in many industries, because firms hope to evoke positive consumer evaluations of both the alliance’s product and the partner brands. However, extant research offers mixed findings regarding the effects of a brand alliance on its partner brands (i.e., spillover effects). In response, this study separates spillover effects into the effects of the alliance product on the partner brands (brand alliance effects) and the effects between partner brands (brand contrast effects), while also noting the potential moderating impact of perceived attitude- and product-based fit between partner brands on resulting spillover effects. Two experimental studies consistently reveal the existence of brand contrast effects; furthermore, the partner brand’s attitude-based fit reduces undesired brand contrast effects and positively moderates spillover effects in brand alliances, whereas product-based fit does not. Therefore, a third study identifies relevant drivers of partner brand’s attitude-based fit for different brand alliances (i.e., co-branding, ingredient branding, and joint advertising). The findings have notable implications for the design and management of brand alliances.     

The Impact of Alliance Management Capabilities on Alliance Attributes and Performance: A Literature Review

The literature on alliances has identified a variety of inter‐firm antecedents of performance, including information and knowledge sharing between partners, shared partner understanding, and a focus on collective objectives. Recent studies have focused on alliance management capabilities (AMC) – firms' abilities to capture, share, store and apply alliance management knowledge – as an important antecedent of performance. This paper reviews 90 studies on AMC and makes two important contributions to the literature. First, the review provides an overview of and classification scheme for the different types of AMC to better organise the diverse empirical findings that have been presented in the literature. The novel classification distinguishes between general and partner‐specific AMC and between AMC stored within the firm and within the alliance. Second, consistent with the dynamic capabilities perspective, this paper offers a more detailed understanding of why AMC improve performance, by highlighting the intermediate impact of AMC on alliance attributes. In particular, the review demonstrates how the different categories of AMC influence alliances in terms of information and knowledge‐sharing between partners, shared partner understanding and the pursuit of collective goals. The review also demonstrates that these attributes improve performance. The authors note promising avenues for future empirical research that involve combining the classification scheme with research on the impact of AMC on alliance attributes and performance.