Web personalization: is it effective?

By knowing their customers' needs better, firms can offer products and services at the right price, in the right context, and at the right time. Web personalization enables this sort of interaction. Firms can implement personalization by integrating independent packages such as data mining and collaborative filtering tools with the Web server; or personalization could take the form of a package solution. In general, Web personalization serves three main objectives: It draws attention to a company and its products and services; implants messages; and attempts to persuade. The study presented provides empirical support that Web personalization can motivate users to consider agent-recommended items.     

Transformation of smart-card-based single-purpose e-micropayment scheme to multi-purpose scheme: A case study

Micropayment is common in retail outlets and public transport systems. This paper considers the situation where smart-card-based e-micropayment scheme starts off as single-purpose scheme and is progressing to be a multi-purpose scheme. User deciding whether to use such a scheme is a multiple criteria decision-making (MCDM) problem and depends on factors such as transaction cost, availability of discount, ease of use, convenience, reliability, and participation by transport-based companies, retail outlets, large organizations, as well as whether others are using it. Through a case study of successful smart-card-based single-purpose e-micropayment schemes in Taiwan and from the user’s perspective, the dynamic picture of the progression is obtained to analyze how different factors interact and collectively contribute to the successful transformation and diffusion of the scheme. Since this is a MCDM problem, Decision Making Trial and Evaluation Laboratory, a MCDM method, is used. Hence, this paper contributes to extending practical applications of DEMATEL to the field of electronic payment system. It is found that the dynamic picture of the progression of single-purpose smart-card-based e-micropayment scheme to multi-purpose scheme is indeed complex. The factors are definitely not independent of one another and they interact with one another. Ease of use, discount and participation by retail outlets are net causer factors. Top-up locations, reliability of the scheme, participation by transport companies and large organizers are net receiver factors. Factors related to participants of the scheme (such as user base, retail-outlet and transport companies) also exhibit the presence of network effect. The scheme operator faces a chicken and egg situation but the operator has to start somewhere to kick-start the process, end the waiting game, and hopefully to achieve the bandwagon effect. A possible starting point is to focus a lot of the energy on getting more retail outlets onboard. To further accelerate the progression to multi-purpose scheme, a multi-pronged approach to manage the transformation is also advised. To attract more users and to push them to use the scheme to make payment at the participating retail outlets, discount can be offered.     

Quality of service for workflows and web service processes

Workflow management systems (WfMSs) have been used to support various types of business processes for more than a decade now. In workflows or Web processes for e-commerce and Web service applications, suppliers and customers define a binding agreement or contract between the two parties, specifying quality of service (QoS) items such as products or services to be delivered, deadlines, quality of products, and cost of services. The management of QoS metrics directly impacts the success of organizations participating in e-commerce. Therefore, when services or products are created or managed using workflows or Web processes, the underlying workflow engine must accept the specifications and be able to estimate, monitor, and control the QoS rendered to customers. In this paper, we present a predictive QoS model that makes it possible to compute the quality of service for workflows automatically based on atomic task QoS attributes. We also present the implementation of our QoS model for the METEOR workflow system. We describe the components that have been changed or added, and discuss how they interact to enable the management of QoS.     

Combining global and local matching of multiple features for precise item image retrieval

With the fast-growing of online shopping services, there are millions even billions of commercial item images available on the Internet. How to effectively leverage visual search method to find the items of users’ interests is an important yet challenging task. Besides global appearances (e.g., color, shape or pattern), users may often pay more attention to the local styles of certain products, thus an ideal visual item search engine should support detailed and precise search of similar images, which is beyond the capabilities of current search systems. In this paper, we propose a novel system named iSearch and global/local matching of local features are combined to do precise retrieval of item images in an interactive manner. We extract multiple local features including scale-invariant feature transform (SIFT), regional color moments and object contour fragments to sufficiently represent the visual appearances of items; while global and local matching of large-scale image dataset are allowed. To do this, an effective contour fragments encoding and indexing method is developed. Meanwhile, to improve the matching robustness of local features, we encode the spatial context with grid representations and a simple but effective verification approach using triangle relations constraints is proposed for spatial consistency filtering. The experimental evaluations show the promising results of our approach and system.     

Ensemble Learning Models for Classification and Selection of Web Services: A Review

This paper presents a review of the ensemble learning models proposed for web services classification, selection, and composition. Web service is an evolutionary research area, and ensemble learning has become a hot spot to assess web services’ earlier mentioned aspects. The proposed research aims to review the state of art approaches performed on the interesting web services area. The literature on the research topic is examined using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) as a research method. The study reveals an increasing trend of using ensemble learning in the chosen papers within the last ten years. Naïve Bayes (NB), Support Vector Machine’ (SVM), and other classifiers were identified as widely explored in selected studies. Core analysis of web services classification suggests that web services’ performance aspects can be investigated in future works. This paper also identified performance measuring metrics, including accuracy, precision, recall, and f-measure, widely used in the literature.     

耦合辅助信息的矩阵分解推荐模型

近十年来，协同过滤（CF）推荐系统成功地为用户提供了个性化的产品和服务。然而，用户—物品矩阵的稀疏性、推荐精度不高等问题仍然是一个挑战。针对这些问题，在矩阵分解模型基础上，提出了耦合用户和物品辅助信息的矩阵分解混合协同过滤框架；然后，基于此框架又提出了耦合物品属性信息相似度（COS）的过滤模型。大规模真实数据集上的实验表明，该模型不但可以有效解决物品相似度度量问题，而且相比传统方法，尤其是在物品特征非常稀疏的情况下，推荐准确性得到有效改进。     

Improving the prediction accuracy of recommendation algorithms: Approaches anchored on human factors

Recommender systems are a special class of personalized systems that aim at predicting a user's interest on available products and services by relying on previously rated items or item features. Human factors associated with a user's personality or lifestyle, although potential determinants of user behavior are rarely considered in the personalization process. In this paper, we demonstrate how the concept of lifestyle can be incorporated in the recommendation process to improve the prediction accuracy by efficiently managing the problem of limited data availability. We propose two approaches: one relying on lifestyle alone and another integrating lifestyle within the nearest neighbor approach. Both approaches are empirically tested in the domain of recommendations for personalized television advertisements and are shown to outperform existing nearest neighborhood approaches in most cases.     

Incentivized provision of metadata, semantic reasoning and time-driven filtering: Making a puzzle of personalized e-commerce

e-Commerce recommender systems select potentially interesting products for users by looking at their purchase histories and preferences. In order to compare the available products against those included in the user’s profile, semantics-based recommendation strategies consider metadata annotations that describe their main attributes. Besides, to ensure successful suggestions of products, these strategies adapt the recommendations as the user’s preferences evolve over time. Traditional approaches face two limitations related to the aforementioned features. First, product providers are not typically willing to take on the tedious task of annotating accurately a huge diversity of commercial items, thus leading to a substantial impoverishment of the personalization quality. Second, the adaptation process of the recommendations misses the time elapsed since the user has bought an item, which is an essential parameter that affects differently to each purchased product. This results in some pointless recommendations, e.g. including regularly items that the users are only willing to buy sporadically. In order to fight both limitations, we propose a personalized e-commerce system with two main features. On the one hand, we incentivize the users to provide high-quality metadata for commercial products; on the other, we explore a strategy that offers time-aware recommendations by combining semantic reasoning about these annotations with item-specific time functions. The synergetic effects derived from this combination lead to suggestions adapted to the particular needs of the users at any time. This approach has been experimentally validated with a set of users who accessed our personalized e-commerce system through a range of fixed and handheld consumer devices.     

Reform of government and the future performance of national surveys

The assumption of this paper is that Governments pursue the following strategic objectives with respect to geospatial information, as produced by National Surveys (including Cadastres):

• 1.for its own purposes, i.e. to govern, it must be assured of unlimited and efficient access to National Survey material;
• 2.society should have the broadest possible “free”, but not “cost free”, access to the products and services of National Surveys because this increases “positive externalities” for society as a whole; and
• 3.the products and services of National Surveys, including Cadastres, should, in a planned fashion, become independent of government subsidies.

The article argues that under the constraints of those objectives, the regulatory environment of the Public Service (in parliamentary democracies), is counterproductive to the requirements for economic efficiency in pricing and distribution of national survey products and services. Because National Surveys and Cadastres are natural monopolies, the arguments are based on economic theory of the regulation of natural monopolies. Due to the introduction of Information and Communications Technology (ICT), the client community has ubiquitous access to survey and geospatial data processing technology, as well as a growing supply of commercially available substitutes for the products and services of the conventional natural monopolies. Hence, the paper first defines the product and services content of the natural monopoly in the modern ICT and Geospatial Data Infrastructure dominated environment for the case of a National Mapping Agency (NMA) which includes, in this case, the Cadastral Surveying and Mapping. Having defined the products and services in the natural monopoly, all other (value-added) products and services are by definition placed in the free competitive market. The paper goes on to demonstrate that it is in the interest of society that the NMA or Cadastre competes in this market in order to realize economies of scope. The “parity-principle formula for bottleneck service pricing” (Baumol, Ordover & Willig, 1997. Parity pricing and its critics: a necessary condition for efficiency in the provision of the bottleneck services to competitors. Yale Journal of Regulation) provides the necessary and sufficient condition under which a level playing field can be created for all competitors that require the monopolist's (NMAs) assets for the value-added production in the free market. However, an independent regulator must supervise the application of this principle. Next, the issue of pricing is dealt with in light of meeting the policies on maximum output and diminishing subsidy. As the government has set the broadest possible distribution as a strategic goal, the NMA will have to act as an output maximiser as opposed to a profit maximiser. Output will therefore have to be set at a point where economic profit is not negative, and this will determine the unit price. These criteria lead to a set of management objectives and an accountability framework for NMAs. It is only at that point that the discussion on the desirability of more independence from the Public Service regulations, of which privatisation is the extreme form, becomes meaningful. The article concludes that outright privatisation, that is, placing the assets of the NMA and all decision-making power over them in the hands of private individuals, is in conflict with the first strategic objective. Furthermore that a regulated monopoly and output maximisation are unattractive conditions for potential franchisers, concessionaires or management contractors. Hence an appropriate solution would be to put the organization at arms-length from government within the accountability framework developed but established in commercial law and without tax benefits. A Cabinet level Minister must be the politically accountable regulator of the “level playing field” and the pricing policy.     

基于工作过程系统化重构营销专业课程体系研究

本文按工作过程系统化模式，在分析中职营销专业课程体系现状基础上，打破学科体系、知识体系的框架，做颠覆性改革，形成不同的学习领域，以超市营销等9项产品或服务的营销为载体、为课程，每门课程里均反复训练4类15项中8—10项典型工作任务。文中拟制新营销专业课程体系框架，并对教法、学法，支持系统、教学工具等进行了设计。     

Facilitating cross-selling in a mobile telecom market to develop customer classification model based on hybrid data mining techniques

As the competition between mobile telecom operators becomes severe, it becomes critical for operators to diversify their business areas. Especially, the mobile operators are turning from traditional voice communication to mobile value-added services (VAS), which are new services to generate more average revenue per user (ARPU). That is, cross-selling is critical for mobile telecom operators to expand their revenues and profits. In this study, we propose a customer classification model, which may be used for facilitating cross-selling in a mobile telecom market. Our model uses the cumulated data on the existing customers including their demographic data and the patterns for using old products or services to find new products and services with high sales potential. The various data mining techniques are applied to our proposed model in two steps. In the first step, several classification techniques such as logistic regression, artificial neural networks, and decision trees are applied independently to predict the purchase of new products, and each model produces the results of their prediction as a form of probabilities. In the second step, our model compromises all these probabilities by using genetic algorithm (GA), and makes the final decision for a target customer whether he or she would purchase a new product. To validate the usefulness of our model, we applied it to a real-world mobile telecom company’s case in Korea. As a result, we found that our model produced high-quality information for cross-selling, and that GA in the second step contributed to significantly improve the performance.     

The impact of a computerized conferencing system on the productivity of scientific research communities

Researchers and practitioners in the field of information and communication technologies (ICT) have for a while been embracing the concepts of user and consumer experience as well as emotions in design, encouraging the industry to emphasise hedonic and symbolic qualities of products and services, over and beyond their utilitarian characteristics. However, the idea that mobile phone users, for instance, seek increasingly experience-rich, personalised products can not be taken for granted. Therefore, it is valuable to investigate the degree to which users really share designers' increasingly socio-emotional stances. The presented longitudinal study investigated users' mobile phone-related product meaning, particularly its development from 2004 to 2008. Product meaning was conceptualised in terms of an affective-cognizant choice mode dimension complemented by items capturing utilitarian, hedonic, and symbolic facets of the construct. The findings provide grounds for raising an important discussion about a possible pragmatic shift in product meaning, away from emotional and holistic, towards piecemeal and rational valuation. This would obviously challenge current design maxims. Linking these results to users' personality and mobile phone ownership history, subgroups with notably dissimilar product meaning development could be distinguished mainly with regard to levels of neuroticism, extraversion and brand loyalty – however, not gender.     

基于隐性反馈的自适应推荐系统研究

介绍个性化自适应推荐系统的整体架构与设计方法。阐述用户兴趣模型的建立,包括对用户个性化信息的收集、精炼处理、模糊语意处理、解模糊化及满意度计算。引入模糊自适应共振理论网络进行项目聚类分析,并进行推荐处理,实现自适应推荐服务。实验结果表明,系统对用户兴趣判断比较准确,能及时掌握用户兴趣偏移,推荐效果良好,且基本稳定。     

碳税下多周期闭环混合系统的补贴策略模型

在考虑新产品和再制造品碳排放差异的情况下,建立了制造商回收模式下的多周期混合制造/再制造系统的最优运作及补贴策略模型。假设回收品质量水平服从指数分布,回收成本、回收率和再制造成本是回收品质量水平的负指数函数,建立包含碳税的平均总成本函数,并采用遗传算法（GA）和粒子群算法（PSO）验证模型的信度和效度。结果表明：无补贴情况下,企业可对回收品质量水平为0.28~0.84的产品进行再制造;考虑补贴情况下,政府可对回收品质量水平为0.28~0.42的产品采取补贴机制,达到引导企业回收再制造的目的。该研究为政府制定合理的补贴政策及企业权衡碳排放因素降低总成本提供理论依据。     

Lessons learned – Review of LCAs for ICT products and services

Application of information and communication technology (ICT) is often expected to result in decreased environmental impacts. Several studies have, however, also addressed the possibilities of negative impacts. It is therefore important to assess environmental impacts of ICT products and services. Life Cycle Assessment (LCA) is a tool for assessing the potential impacts of a product or service over the whole life-cycle, i.e. from raw material acquisition to waste management via production and use phases. The aim of this paper is to review LCA studies of ICT products and services, including a few Social Life Cycle Assessment (S-LCA) studies. Many of the studies have considered consumer products, such as computers and TVs. Other consumer products, such as game consoles and TV peripherals, as well as business products, e.g. related to networks, are however more rarely assessed. Manufacturing and use phase have the highest impact in the life cycle. Use phase seems to be the predominant in energy consumption and global warming for some ICT products but for others, especially energy efficient, low weight products, manufacturing may dominate. Rapid technological development is stressed by several authors as a source of variability of results, impacting the production processes and suppliers as well as the content and energy performance of the actual devices. In the future, conducting LCA on ICT, the research community needs to consider the limitations found in the studies conducted so far. It encompasses, among others, the need to address a broad spectrum of environmental impacts, including human and ecotoxicological impacts; modeling actual e-waste management, covering informal management when relevant; and considering user behavior in a realistic way, accounting for rebound and other indirect effects.     

Processing k-skyband,constrained skyline,and group-by skyline queries on incomplete data

The skyline operator has been extensively explored in the literature, and most of the existing approaches assume that all dimensions are available for all data items. However, many practical applications such as sensor networks, decision making, and location-based services, may involve incomplete data items, i.e., some dimensional values are missing, due to the device failure or the privacy preservation. This paper is the first, to our knowledge, study of k-skyband (kSB) query processing on incomplete data, where multi-dimensional data items are missing some values of their dimensions. We formalize the problem, and then present two efficient algorithms for processing it. Our methods introduce some novel concepts including expired skyline, shadow skyline, and thickness warehouse, in order to boost the search performance. As a second step, we extend our techniques to tackle constrained skyline (CS) and group-by skyline (GBS) queries over incomplete data. Extensive experiments with both real and synthetic data sets demonstrate the effectiveness and efficiency of our proposed algorithms under various experimental settings.     

Intelligent e‐government services with personalized recommendation techniques

Information overload is becoming one of the problems that hinder the effectiveness of e‐government services. Intelligent e‐government services with personalized recommendation techniques can provide a solution for this problem. Existing recommendation approaches have not entirely considered the influences of attributes of various online services and may result in no guarantee of recommendation accuracy. This study proposes a new approach to handle recommendation issues of one‐and‐only items in e‐government services. The proposed approach integrates the techniques of semantic similarity and the traditional item‐based collaborative filtering. A recommender system named Smart Trade Exhibition Finder has been developed to implement the proposed recommendation approach. The recommender system can be applied in e‐government services to improve the quality of government‐to‐business online services. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 401–417, 2007.     

Ontologies and electronic commerce

Ontologies are the first step toward realizing the full power of online e-commerce. Ontologies enable machine-understandable semantics of data, and building this data infrastructure will enable completely new kinds of automated services. Software agents can search for products, form buyer and seller coalitions, negotiate about products, or help automatically configure products and services according to specified user requirements. The combination of machine-processable semantics of data based on ontologies and the development of many specialized reasoning services will bring the Web to its full power. The authors discuss: taxonomies; information sources; future issues; business viewpoints; the e-marketplace; and B2B e-commerce standardisation and integration.     

Distributed middleware architectures for scalable media services

The fusion of Multimedia and Internet technology has introduced an ever-increasing demand for large-scale reliable media services. This exposes the scalability limitations of current middleware architectures, as they traditionally operate on either very large-server configurations or on tightly coupled distributed systems. On the other hand, the wide availability of high-speed networks and the widespread deployment of powerful personal computing units by end users, has emphasized the advantages of the peer-to-peer (P2P) computing model. In this paper, we evaluate a number of different middleware architectures that facilitate the timely and reliable delivery of media services in P2P networks. Our evaluated architectures exploit features including availability of high-performance links, replication and caching of popular items and finally state-of-the-art search techniques proposed in the context of structured and unstructured P2P overlay networks. Through detailed simulation we investigate the behavior of the suggested P2P architectures for video provision and examine the involved trade-offs. We show that under realistic assumptions, the evaluated architectures are resilient to multiple peer-failures, are scalable with respect to dropped requests when the number of messages in the network increases and provide good response times to the user requests.