By Topic

Management Science and Engineering, 2006. ICMSE '06. 2006 International Conference on

Date 5-7 Oct. 2006

Filter Results

Displaying Results 1 - 25 of 442
  • [Front cover]

    Save to Project icon | Request Permissions | PDF file iconPDF (443 KB)  
    Freely Available from IEEE
  • Copyright page

    Page(s): nil1
    Save to Project icon | PDF file iconPDF (426 KB)  
    Freely Available from IEEE
  • Proceedings contents

    Page(s): nil2
    Save to Project icon | PDF file iconPDF (258 KB)  
    Freely Available from IEEE
  • Conference Committee

    Page(s): nil3 - nil5
    Save to Project icon | PDF file iconPDF (2013 KB)  
    Freely Available from IEEE
  • Plenary and Invited Speakers

    Page(s): nil6 - nil7
    Save to Project icon | Request Permissions | PDF file iconPDF (1441 KB)  
    Freely Available from IEEE
  • Technical Co-Sponsors

    Page(s): nil8
    Save to Project icon | PDF file iconPDF (184 KB)  
    Freely Available from IEEE
  • Contents

    Page(s): I - XXII
    Save to Project icon | Request Permissions | PDF file iconPDF (24422 KB)  
    Freely Available from IEEE
  • Customer Sample Difference-oriented Bayes Segmentation Algorithm

    Page(s): 3 - 7
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (5157 KB) |  | HTML iconHTML  

    Nowadays, population features differ from place to place in China. The differences between population and customer samples, which are called "spatial population drift", are caused by economic, social and cultural reasons. Prediction model adaptability of customer segmentation is weakened by spatial population drift. A Bayesian network can effectively combine prior knowledge and sample data information. This paper proposes a method of a Bayesian network to improve model adaptability for different samples while keeping its high accuracy. It sets model structure without parameters as general form on population or large samples with good data quality, and then trains model parameters by local sample. By this way, the prediction model for special customer instance is built. It can solve the uncertainty of customer segmentation based on customer data in China to some extent View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Web Mining Model for Real-time Webpage Personalization

    Page(s): 8 - 12
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (5240 KB) |  | HTML iconHTML  

    Determining the size of the World Wide Web is extremely difficult. The Web can be viewed as the largest data source available and presents a challenging task for effective design and access. One proposed Web mining approach to handling the problem of effective design and access is personalization. With personalization, Web access or the contents of a Web page are modified to better fit the desires of the user. This may involve dynamically creating Web pages that are unique per user or using the desires of a user to determine what Web documents to retrieve. This paper presents a Web mining model based on dynamic clustering and hidden Markov model. The output of the model is some information for dynamically creating a Web page which can best meet the user's desires. The assumption of the dynamic clustering is that if a group of users who have the same interest trend, those pages they have visited are probably related. We propose that human should be the authority to judge the correlation of two pages. First, the model statistic a user's Web browsing records in the log file; find a group of users who have the same interest trend with the user; collect all the pages in which this group of users are interested; calculate the correlation between pages; and cluster the pages into several categories according to a predetermined threshold. Each Web page category is considered as a stochastic state variable. In the second phase, our model based on hidden Markov model is further constructed to mine the latent desires of a user given an observed sequence of Web pages that the user have browsed. In order to get the optimal parameters (transition probability matrix, the conditional probability and the initial state) in the model, we applied the Baum-Welch parameter estimation method in EM algorithm to train the model on the data set. Experimental results show that the model is practicable and efficient View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Study on Evaluation Items and Its Application for B2C E-commerce Trust

    Page(s): 13 - 18
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (6722 KB) |  | HTML iconHTML  

    E-commerce trust has becoming the bottleneck of the development of e-commerce in China, which attracts much attention of many researchers. However, the empirical researches of e-commerce trust are very few, so most of research productions lack of persuasion. This text presents an evaluation system of B2C e-commerce trust, which may promote the development of empirical research in China. And then, this text gives an example of empirical research of B2C e-commerce trust, demonstrates how to do empirical research, which may direct the empirical research in China View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Customer's Evaluation Process of Service Recovery in Online Retailing

    Page(s): 19 - 24
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (7797 KB) |  | HTML iconHTML  

    Online retailing in China has developed rapidly in recent years, but related researches lag far behind. Based on the integration of justice theory and expectancy-disconfirmation theory, this study gets a thorough understanding of service recovery management in online retailing by using scenarios and factorial design methods. Results show that the three justice dimensions and disconfirmation explain a large percentage of variation in customer's satisfaction of service recovery in online retailing. Furthermore, the effectiveness of specific recovery tactics on customer's satisfaction, post-purchase attitude and behavior in Internet environment were also tested in this study. It is found that when service failure happens, compensation and quick response significantly influence customer's satisfaction, trust and repurchase intention, whereas apology alone is ineffective to regain satisfaction in cyberspace. However, apology used as recovery tactic can intensify the effect of compensation or quick response on customer's overall evaluation toward online retailers View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Study on the Impact of Cognitive Variables of Organization Members on Information System Benefits

    Page(s): 25 - 29
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (6381 KB) |  | HTML iconHTML  

    This study is based on the theory of organizational behavior and from the perspective of the organization overall information system benefits. Reviewing the studies of technology acceptance model, innovation diffusion theory and self-efficacy, this study summarizes the major contributions and limitations, establishes the new direction. From the perspective of cognition and behavior, this study introduces the intermediate information system benefits, designs a theoretical model, collects data with questionnaires, checks up reliability and validity with structural equation models, and analyzes the methods. The results of the study give some guidance theoretically and practically View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ontology-Driven Information Retrieval System for Customers' Complaints of Mobile Communication Services

    Page(s): 30 - 35
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (6190 KB) |  | HTML iconHTML  

    Ontology has been one of the hottest topic issues in artificial intelligence, knowledge engineering, especially in information process. In this paper, we propose an ontology-driven information retrieval (IR) system used for mining the interesting patterns in the domain of customers' complaints of mobile communication services. As the primary research of ontology model itself is about concept, properties of concept, relations between concepts etc, out of question ontology model considers the semantic relationships of the rich document content. Therefore ontology-driven information retrieval system can conform to the thought mode of human being unlike the keyword-based system that ignores the semantic relationships between words. Applying the proposed IR system to the given domain can make the managers of mobile communication companies retrieve the customers' complaints information more precisely and hence make decisions more reasonably View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mapping of Logistics Distribution Knowledge for E-commerce in GIS

    Page(s): 36 - 40
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (5511 KB) |  | HTML iconHTML  

    An ever-increasing trend in today's logistics firms is to set up intelligent scheduling system. This paper focuses on enhancing the intelligence and science of real-time optimizing scheduling of logistics distribution for e-commerce based on GIS, and discusses how to process logistics distribution knowledge visually in GIS. A model and mapping solution of logistics distribution knowledge in GIS is presented, and the uniform mapping relations between knowledge bases and spatial databases are kept through XML relational mapping documents. This research is an interaction among artificial intelligence, knowledge engineering and geographical information system, and shows by means of system simulation that the mapping solution is very well suited for establishing the intelligent optimising scheduling system of logistics distribution based on GIS faced with dynamic environment. Finally, potential issues for future research are presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • E-equity: An Empirical Study on Brand Equity Model of Web Portal

    Page(s): 41 - 45
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (6155 KB) |  | HTML iconHTML  

    Based on Keller's study on brand equity, this paper proposes a new model to evaluate Web Portal's brand equity - e-equity. Web awareness and Web image are conceptualized in the model as two dimensions of e-equity. Factors affecting these two dimensions are well defined and the relationships between these factors are discussed thoroughly. With data collecting in Chinese Web portals, the model is tested using structural equation model. The results obtained in this study would provide insights for the managers of Chinese Web portals to develop more user-oriented marketing strategies and to gain differential competitive advantages in online environment View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Automatic Business Process Modeling Method Based on Markov Transition Matrix in BPM

    Page(s): 46 - 51
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (5577 KB) |  | HTML iconHTML  

    Recently a novel process modeling method is presented in the field of business process management, which is called as process mining. Process mining technology can automatically deduce process models based on given mining algorithm from large numbers of process logs. The new modeling technology makes modeling efficiency, objectivity and quality be greatly improved than before. However the research of this new modeling technology is currently on primary stage. And the known process mining algorithms are not enough perfect. Therefore a new process mining algorithm is designed in this paper. In the algorithm a Markov transition matrix is set up based on process logs. And according to the matrix the eight mining rules of process logical relations are designed. This new mining algorithm can not only effectively reduce the effect of logs quality on process mining but also greatly enhance the automatic process modeling capability View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Customer Value Prediction Model Based on Markov Chain in B2C

    Page(s): 52 - 55
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (4035 KB) |  | HTML iconHTML  

    According to the flexibility and predictive features of Markov chain model and the analysis of customers' historical behavior of RFM (recency, frequency, monetary), this paper employs these two models into the customer value prediction in B2C context. By refining the conventional RFM model, the prediction of the customer's value becomes more precise. Such method helps to make effective customer marketing and relationship management polices. The article also describes a case study that demonstrates its accuracy View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated Task Negotiation in Multi-agent Based Virtual Enterprise

    Page(s): 56 - 61
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (6618 KB) |  | HTML iconHTML  

    To cooperate effectively in virtual enterprise (VE), principal enterprise and member enterprises usually employ negotiation. With regard to the feature of VE, this paper presented a formal negotiation model for multi-agent negotiation for task allocation in VE. Then, constructed probability function as offer and counter offer strategies of agents and taken the expected price of both sides in the next turns and their reserved price into account, a contract-net based price negotiation algorithm is proposed. The algorithm considered the preference of agents and the restriction of time etc. By employing this algorithm, agent can modify its bid zone dynamically and learn about the opponent's bid price. In this way, the algorithm can reflect the attitude of the two negotiation parties and simulate the iteration of offering price very well in reality, which may promote the efficiency of negotiation and attain better negotiation result. Finally, a simple example is used to validate the approach's availability View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis on the Model of Digital Divide & the Demonstration Research in Narrowing the Digital Divide with ICT

    Page(s): 62 - 67
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (6465 KB) |  | HTML iconHTML  

    Digital divide appears when China coordinates the development of traditional industry and informatization. The main reason is the asymmetric information caused by regional informatization difference. The study uses Keith Griffin's model that is about the generation and diffusion of agricultural green technology revolution, and uses the ideas of information economics to draw an information and communications technology (ICT) diffusion model containing an isoquant. The ICT model can analyze user's different choices in communication technologies in different stages of informatization, and we can identify an ICT gap by crossing the isoquant of different stages and the ratio between different user's capital and laboring. The ICT gap can describe the size of the digital divide. A demonstration analysis is made on the informatization level of Liaoning province by informatization index measuring. The results show that ICT is an efficient way to narrow digital divide and also give suggestions in how to further develop ICT and narrow digital divide View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research on Changes of E-shopper Behavior in the Internet Environment

    Page(s): 68 - 73
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (6766 KB) |  | HTML iconHTML  

    In the Internet shopping environment, changes of customer's needs grow increasingly outstanding. For discovering the changes, the paper mines the transaction databases of different time periods by using association rule discovery, and extracts the association rules and discovers the changes in network customer behavior by comparison and analysis between the two sets of association rules. This paper presents a new algorithm that contains the first support, the second support and Rel-confidence. The algorithm solves the problem of the present algorithms cannot discover association rules with infrequent data items. And according to the changes of network customer's behavior, robust pattern, appearing pattern and unexpected change are presented to measure the changes View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Does Material Incentive Really Improve the Response Rate in Web-based Survey? - A Classification Model of the Potential Respondents

    Page(s): 74 - 77
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (4882 KB) |  | HTML iconHTML  

    To strive to uncover the incentive role in the Web-based survey, this paper inspects the correlations of material incentive, data quality, attitude, preference, and preceding experience from the participant perspective. Based on four statistical test findings, the potential respondents are classified into four groups: "loyalist", "trader", "stager", and "speculator". A model based on four quadrants is constructed. To use the incentive effectively, incentive should be given to those who belong to the group of "trader", otherwise, the incentive is ineffective View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Gender-Based Differences in the Effect of Web Advertising in E-business

    Page(s): 78 - 83
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (7768 KB) |  | HTML iconHTML  

    Previous research suggests males and females exhibit different attitudes toward traditional advertising along with different advertising stimulated consumer behaviors. However, little is known about gender differences in the relationship between the effect of Web advertising and online consumer's behavior. Survey results indicate males and females differ significantly on several dimensions with attitude psychology and buying behavior. Data support the hypothesis through analyzing, and future research is discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Multi Agent Hierarchy Managerial Model of Business Enterprise Based on Roles

    Page(s): 84 - 88
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (5009 KB) |  | HTML iconHTML  

    The paper proposes a multi-agent hierarchy managerial model of business enterprise based on roles to express the relationship of agents in the cooperation and communication. Thus, the knowledge, protocol and relation can be easily described by the role, which corresponds to each agent. The model can improve the flexibility of the system and strengthen the sensitivity to the surroundings. At last, an application in finding the best sale products was introduced. The results show that the role system is practically efficient and interactive View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adding Risk in Measuring Customer Value Using Bivariate Hierarchical Bayesian Approach

    Page(s): 89 - 93
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (6080 KB) |  | HTML iconHTML  

    Hierarchical Bayesian approach to predict changes in individual customer behavior is deemed successful, but often assume that the irrelevance between purchase interval and money. In many situations, this assumption may not be valid. In this paper we proposed bivariate hierarchical Bayesian approach, which allows correlation between them, and can educe conditional probability density function of purchase interval or money. The model is applied to medical instruments sale data to predict customer changes and shows more precise than traditional models. Based on distribution of customer behavior, the concept of customer risk is brought out, including churn risk, decline risk and fluctuating risk, which can be calculated using probability density curve. This value prediction considering risk can be used managerially as a signal for the firm to use some type of intervention to keep that customer View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Heuristic Search Algorithm for Vehicle Routing Problems and the GIS-based Vehicle Routing System Onboard

    Page(s): 94 - 99
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (6406 KB) |  | HTML iconHTML  

    Focusing on a specific vehicle routing problem that is used in onboard and embedded equipments and incorporates road condition and its change, traffic rules and several different destinations, this paper divides the vehicle routing problem into two parts, local routing and global routing, describes the heuristic search algorithm for routing problems onboard, and defines evaluation functions for local routing and global routing respectively. Embedded development platform - eSuperMap is applied to the construction of vehicle routing system and key techniques of the system are researched. Furthermore, based on embedded GIS, the vehicle routing system is designed and realized View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.