Yin Bai

A New Approach to Forecast Crude Oil Price Based on Fuzzy Neural Network

A new oil price forecasting model based on fuzzy neural network, which combings RBF neural network, Markov chain based semi parametric model and wavelet analysis is proposed in this paper. The high degree of prediction accuracy confirms the performance of the model in accurate forecasts, reinforcement learning properties and mapping capabilities.

The Study of Customer Complaints Management Based on System Dynamics: Modeling and Simulation

In this paper, based on the relationships among customer satisfaction, repeated purchases, customer loyalty, complaint-voicing rate and complaint-dealing ability, a model is built to analysis customer flow resulting from the complaint management with the system dynamics method. Applying Vensim 5.0, customer flow is simulated with the data from Chinas mobile market. Through analyzing the simulation results we can identify the key factors of system. Finally we obtain the high-point of the system running by adjusting the key factors effectively and continuously. We have also studied how to adjust the factors according to the experimental datum which provides guidance to managers making decisions

A New Approach to Hierarchical Clustering Using Partial Least Squares

We here propose a methodology to improve hierarchical cluster analysis using partial least squares (PLS). Two problems are addressed by this methodology, these are (1) when, as usually, Euclidean distance is used for hierarchical cluster analysis, but Euclidean distance is defined only in Euclidean space. If Euclidean distances are computed in other spaces, the distances are hard to make sense. On the other hand, since the variables in the data set do not have equal variance, they do not have comparable scales. (2) Traditional clustering methods are based on single data table, but the application of PLS makes it possible to deal with multiply data tables problems. In addition, the proposed method can reduce the dimension of classification variables in a reasonable way. That makes it possible to demonstrate the relationship of multiply dimension data

Fuzzy Influence Diagrams: An Approach to Customer Satisfaction Measurement

This paper proposes a contribution on the application of fuzzy influence diagrams (FID) to the measurement of customer satisfaction. While structural equation modeling has been extensively used for this purpose and is still highly useful, FID outperforms it in solving the problems of nonlinearity, validity and causality. The paper describes algorithm of FID and takes emporiums customer satisfaction measurement as an example. This is the first time FID has been used for customer satisfaction measurement, and the results have been quite encouraging.

Effects of class size and attendance policy on university classroom interaction in Taiwan

Classroom interaction experience is one of the main parts of students’ learning lives. However, surprisingly little research has investigated students’ perceptions of classroom interaction with different attendance policies across different class sizes in the higher education system. To elucidate the effects of class size and attendance policy on classroom interaction, we administered a survey to 1304 undergraduates in Taiwan. The questionnaire consisted of six dimensions: classmate supportiveness, classmate pressure, teacher encouragement, teacher supportiveness, study preparedness and class participation. The results indicated that attendance policy and class size have an interaction effect only on the teacher trait. Students in a small class with a never-taking attendance policy feel more supported and encouraged by their teacher compared with those in larger classes with the same attendance policy. When class size is larger, students in classes employing an occasionally taken attendance policy feel more supported from their instructors than those in the never-check attendance policy class. Attendance policy doesn’t influence the student or the classmate trait, but class size does. Larger classes lower classmate supportiveness, student preparedness, and class participation compared with smaller classes.

Risk Analysis for Oil and Gas Exploration Project

In this paper, based on the characteristics of the oil and gas exploration project, the risk analysis method is a systematically studied. Firstly we analyze the shortcomings of existing risk analysis methodologies, set forth the further research direction in this field. Then the influence diagram algorithms are presented based on fuzzy theory. At last, the risks of a certain oil and gas exploration project are analyzed. The procedures and contents to structure and evaluate profit influence diagram are studied in the light of the reality. By means of the practical application, the effectiveness and feasibility of the methods are verified.

Why SMEs in emerging economies are reluctant to provide employee training: Evidence from China:

In this article, we investigate CEO motivations, intentions and actions in providing training to their employees in Chinese small and medium-sized enterprises (SMEs), exploring the gap between training intentions and actual provision. Drawing on the theory of planned behaviour and using a sample of 533 SMEs, we find training intention mediates the effects of motivations on training provision; CEOs are more concerned with returns to the firm from training rather than employee benefits. In addition, external constraints negatively moderate the training intention–provision relationship in China, whereas internal constraints have been shown to be more important in other countries. Our findings suggest a number of theoretical and managerial implications.

Using DEA and Grey Markovian Model to Measure the Goal Cost of Petroleum Enterprise

With the longstanding development of Chinese petroleum enterprises, the control of discovery and exploitation goal cost is becoming a essential problem. Data Envelopment Analysis (DEA) is a linear programming method for measuring the relative efficiency of decision making units where the presence of multiple inputs and outputs makes comparisons difficult. Grey Markovian model has the merits of both grey model and Markov transition probability matrix model. In this paper, DEA and Grey Markovian model are combined to measure the discovery and exploitation goal cost of petroleum enterprise. This method is applied to the cost analysis of Huabei Oil Company of PetroChina, which gives strong support to the feasibility and availability of the study in this paper.

A CPLS-based customer satisfaction model

Traditional PLS path modeling based customer satisfaction model could only handle continuous or Likert scale like variables. This study proposed an algorithm called categorical partial least squares (CPLS) to handling categorical variables in customer satisfaction model. Both categorical and numerical variables can be jointly analyzed in the same model and the proposed algorithm is suitable for both Mode A (reflective measurement model) and Mode B (formative measurement model). This algorithm was illustrated empirically in the context of a household appliance brands customer satisfaction study. A complete process of using CPLS path modeling including model development, model assessment and the applications of the results was demonstrated. Moreover, the authors concluded with the limitations of their study and suggestions for future research.

A research on customer satisfaction with household appliances industry service

With the rapid development of Chinas economy, the service industry in China plays an important role in the domestic economy. Competition among enterprises is gradually transformed into the competition on quality of services. Customers are the final recipients of products or services, but also an important resource for the development of enterprises, customer satisfaction and customer loyalty are the fundamentals of enterprise development. Taking sales and service center of a household electrical appliance enterprise for example, through surveys of customer satisfaction on sales and service, modeling the path of the factors which influence sales and service quality, and using partial least squares method, the thesis analyzes the aspects and factors which influence the satisfaction of this sales and service center, identify the strategies to enhance sales and service sectors of this enterprise, thereby enhancing its competitiveness in the market.