改进的RBF神经网络对期货价格的预测分析

针对非线性变化的期货价格,建立了基于主成分分析的RBF神经网络模型。首先利用主成分分析法从8个原始变量中提取主成分,最后利用选定的3个主成分作为径向基神经网络的输入。通过对比,该方法较一般的径向基神经网络有更好的预测结果。     

基于粗集和神经网络的BPR风险评价

在构建风险因素指标集的基础上,采用粗集与神经网络串行结合对业务流程重组风险进行评价。通过粗集减少指标的数量,提取主要特征指标,降低神经网络构成系统的复杂性及计算时间,并给出实证。     

基于粗集和神经网络的BPR风险评价

在构建风险因素指标集的基础上,采用粗集与神经网络串行结合对业务流程重组风险进行评价。通过粗集减少指标的数量,提取主要特征指标,降低神经网络构成系统的复杂性及计算时间,并给出实证。     

基于BP神经网络和相关系数结合的股票价格预测

股票价格预测一直是困扰投资者的难题,为了提高股票价格的预测精度,本文提出一种基于BP神经网络和相关系数结合的股票价格预测方法。从股票数据中选取10个影响股票价格的因素,计算它们与股票价格的相关系数,从中提取关键因素,利用BP神经网络预测未来股票价格。将此方法用于华谊兄弟(300027)预测股票收盘价,结果表明,相对于未提取关键因素的BP神经网络,此方法提高了股票价格的预测精度。     

基于主成分分析法的区域经济资源位建模讨论

<正>一、使用主成分分析法计算各个区域的资源位本文的目的是建立经济系统的神经网络模型,因此需要实验数据对神经网络进行训练。这些数据是通过使用主成分分析法计算各个区域的资源位数据获得的。本文采用主成分分析法度量区域系统的资源位,资源位是系统经济学中提出的一个非常重要的概念,即在广义资源位空间中,能够被经济系统实际和潜在利用、占据或适应的部分称     

基于BP神经网络的电力系统负荷预报

研究了基于BP网络在中电力负荷预测中的应用,通过神经网络对训练样本的学习,自动提取影响中长期电力负荷的诸多因素。从训练速度、预测误差等方面分析对比了两种神经网络预测能力,仿真和实例数据表明了两种神经网络在中长期电力负荷预测方面的可行性和良好效果。     

一种基于神经网络提取旋波材料参数的新方法

提出了一种从测试的S参数中提取旋波材料参数的新方法——神经网络法。针对旋波材料参数的自由空间测试方法，本文采用BP神经网络来构建映射模型，利用不同算法对网络进行训练，从而获得所需的网络。结果表明，该方法计算速度快、精度高，解决了求解非线性方程组解的模糊性问题，确保了测试结果的可靠性。该方法所构建的网络可用于材料测试后旋波材料参数的快速提取。     

基于责任不对等的电子政务系统外包开发风险评价

本文通过专家调查法确定责任不对等情况下,电子政务系统外包开发过程中多个风险因素的影响程度。运用主成分分析对收集到的数据进行预处理,并将处理结果作为BP神经网络的输入,构建BP神经网络风险评价模型,对政府、供应商双方责任不对等情况下的电子政务系统外包开发风险进行评价,并得出相关结论。     

基于灰色模型与BP神经网络的青岛旅游需求预测模型

本文主要研究青岛市旅游需求预测的有关问题。本文首先对搜集的数据进行无量纲化处理,利用主成分分析得到影响旅游需求的主成分,以旅游人口建立GM(1,1)模型,进而将模型推广到GM(1,N)模型,并进行残差检验确保其可靠性;其次,对影响旅游需求的因素进行GM(1,1)灰度预测,并利用预测数据建立BP神经网络模型对GM(1,1)模型进行优化改进,最后,分析得到运用BP神经网络模型进行预测的结果更为准确。     

农村人力资源流动动因的理论分析和实证研究

对农村人力资源流动的动因进行了理论分析。根据实际调查数据,采用主成分分析法进行了因素提取,用方差(Varimax)最大法进行了因子旋转,从14个变量提取了4个因素,分别命名为经济型、发展型、教育型和盲目型流动动因。利用T检验、单因素方差分析法等方法讨论了影响江苏省农村人力资源流动动因的因素。     

Do We Fully Understand the Critical Success Factors of Customer Satisfaction with Industrial Goods? - Extending Festge and Schwaiger’s Model to Account for Unobserved Heterogeneity

This paper extends Festge and Schwaiger’s (2007) model of customer satisfaction with industrial goods by accounting for unobserved heterogeneity. The application of a novel response-based segmentation approach in partial least squares path modeling (PLS-PM) - the finite mixture partial least squares (FIMIX-PLS) methodology - opens the way for the effective identification of distinctive customer segments. In comparison to previous studies in this field, group-specific path model estimates reveal each customer segment’s particular characteristics as well as other differentiated findings. Hence, this contribution demonstrates that structural equation modeling studies on the aggregate data level can be seriously misleading and makes a strong case for segment-specific customer satisfaction analyses.     

Customer Relationship Management (CRM)'s Impact on B to B Sales Professionals' Collaboration and Sales Performance

Purpose: Sales literature has traditionally considered technology adoption from acceptance and diffusion perspectives. This article examines the impact of customer relationship management (CRM) technology on business-to-business (B2B) sales professionals' ability to collaborate with internal stakeholders and also assesses the relationship between CRM utilization and sales performance. The study moves from assuming that CRM utilization positively impacts salesperson effectiveness and performance to assessing this outcome from the perspective of the salesperson.

Methodology: A survey that was comprised of four scales was sent to 115 B2B sales professionals and usable surveys were received from 70 respondents. The data were analyzed using partial least squares regression to test the hypothesized paths. Partial least squares regression has been shown to work for small sample sizes.

Findings: There is empirical evidence that CRM adoption and utilization positively impacts sales performance, sales effectiveness, and collaboration. As a partial mediator, collaboration positively influenced CRM utilization's effect on sales performance. However, collaboration did not positively influence sales process effectiveness. Explanations of the findings are offered.

Managerial Implications: Sales managers can use CRM technology to make their sales team more effective and efficient. Second, increased collaboration across the firm positively mediates sales performance. Lastly, to increase collaboration, sales managers should stress that CRM leads to higher performance for both the sales team and the entire firm.     

The impact of external environmental on business process management and organizational performance

The external business environment as a variable for explaining the impact of business process management (BPM) on organization performance is investigated. The developed model is tested using partial least squares, using a survey on human resource/information technology managers in Malaysia. Statistical results show that dynamism and hostility influence the degree of implementation of BPM. The extent of BPM also has an impact on organization performance. The model can be used by organizations to assess their level of BPM success depending on specific environmental characteristics. This research also contributes to understanding an environment–BPM–performance interface in a developing economy, not previously examined.     

The impact of individualism on buyer–supplier relationship norms,trust and market performance: An analysis of data from Brazil and the U.S.A.

This study focuses on the impact of the cultural dimension of individualism, face-to-face communication and the effect of relational norms such as supplier involvement and trust on the market performance of buyer firms. We use the culture literature and social exchange theory to test hypotheses using a sample of Brazilian and US manufacturing firms. The data were analyzed using variance-based structural equation modeling, employing nonlinear partial least squares regression. Our findings indicate that individualism is negatively related to the involvement of suppliers in the production process but is not associated with trust in suppliers. In addition face-to-face communication seems to have a positive effect on supplier involvement and trust.     

Customers focus and impulse buying at night markets

This study conducted a survey on impulse buying at several international night markets in Taiwan and obtained 1053 responses. The data were analysed by partial least squares structural equation modelling. The model was composed of several constructs: attitude towards impulse buying, impulse buying tendency, and variables of customer focus, including insight ability (vendors’ insight into customer needs), customer information, response and feedback, and vendor enthusiasm. The analytical results revealed that insight ability, customer information, response and feedback, and enthusiasm have direct and significant positive effects on attitude towards impulse buying. Additionally, multi-group comparisons in partial least squares analysis revealed partial but statistically significant differences in the path relationships between male customers (568) and female customers; (485); foreign (465) and domestic (588) customers, among night market visitors. This study contributes to the literature by providing a more precise overview of the influence of customer focus on impulse buying tendency within a limited time frame and a crowded space.     

An entrepreneurial cognition perspective on the internationalization of SMEs

Drawing from entrepreneurship, cognition, and international business theory, this paper develops a model integrating individual-level and firm-level characteristics to provide an entrepreneurial cognition perspective on the internationalization of small and medium size ventures. The model is tested on a sample of Spanish ventures using structural equation modeling techniques (partial least squares). Support is found for the central role of cognition and risk perception of CEOs in explaining the implementation of international expansion strategies for their firms.     

A cross cultural study of gender differences in omnichannel retailing contexts

This research examines gender difference in omnichannel experience in modern shopping malls, combining personal, physical and virtual encounters. It proposes a new theoretical model: the gender-based shopping mall omnichannel experience model. Data was collected using 1139 questionnaires completed by millennial shoppers in the United Kingdom and United Arab Emirates. Data was analysed using partial least squares. The results showed a shift in males shopping behaviour as they pay more attention to peer interaction on social platforms, service excellence, convenience, diversity and personalisation in shopping malls than female shoppers, while aesthetics and privacy are more important for female shoppers.     

A comparison of job analytic and conventional economic variables as explanations of occupational earnings differentials

Occupational carnings are analyzed in order to determine the relative importance of micro-oriented job analytic variables vis-a-vis more conventional market variables as explanatory factors of earnings differentials. Earnings functions are constructed in order to determine the extent to which these variables can explain occupational earnings differentials. These functions are analyzed by means of both ordinary least squares and ridge regression techniques. Job analytic variables were obtained from the Position Analysis Questionnaire (PAQ), which measures job characteristics that are similar to many job evaluation systems. When these approaches are combined, a comprehensive model can be estimated that reflects the responsibilities, experience, training, skills, job environment, and work regularity characteristics of different occupations as well as conventional economic factors. Although the job analytic variables measure potentially important differences between jobs, the conventional economic variables have greater explanatory power.     

Fathers' participation in infant-care

Ordinary least squares multiple regression was used to model time spent in child-care by 107 fathers of infants, 3–10 months of age. Time in both physical and non-physical care activities was reported by fathers for a weekday. Number of years married, hours employed for pay the previous week, and fathers' stress score in the child domain were negatively related to time spent in infant-care.     

Loyalty toward online food delivery service: the role of e-service quality and food quality

This study assesses the direct influence of food quality and e-service quality on customer loyalty toward online food delivery (OFD) service and its indirect influence through the mediation of customer satisfaction and perceived value. This study uses a survey of 405 OFD service customers from Bandung, Indonesia. By applying variance-based partial least squares to evaluate the proposed model, this study confirms the direct effect of food quality on online loyalty, but not e-service quality. Further, this study discloses the partial mediation role of customer satisfaction and perceived value on the relationship between both food quality and e-service quality on online loyalty toward OFD services.