A decision support tool for evaluating customer intentions

It is crucial for any manager to keep a close watch on customer satisfaction, customer loyalty and the customer’s intention to recommend the company. In this article, a new decision support tool is developed to support a manager with this task. This tool has been developed with companies in mind that posses limited customer satisfaction data. It uses model-based knowledge discovery to extract the customer’s expectation and the expectation-performance compatibility from the data. Two hypotheses are formulated which posit that compatibility between product performance and customer expectation have a positive influence on the customer’s intentions. Both hypotheses are supported by the data. Finally, a decision support tool is developed which visualizes the impact of customer satisfaction, product performance and expectation-performance compatibility on the customer’s intentions. The decision support tool contains three views which offer the manager important information at a glance.     

Influences of customer preference development on the effectiveness of recommendation strategies

Most previous studies on recommendation agents have been restricted to the problems of uncovering customer preferences during the process of understanding customers. However, studies on consumer psychology have indicated that customer preferences are often unstable and developed over time. Therefore, we assert that it is necessary to observe the degree to which customer preferences are developed since effectiveness of recommendations is affected by customers’ preference development. This study presents a scheme to identify the status of customers’ preference development and analyzes the influences of customer preference development on the effectiveness of various recommendation strategies.     

Assessing the determinants of internet banking adoption intentions: A social cognitive theory perspective

Internet banking adoption is one area that has received attention from scholars. The extant studies have mainly used technology acceptance models and behavioural theories which do not account for changes in human behaviour. This study seeks to ascertain the determinants of Internet banking adoption intentions using the social cognitive theory, which accounts for changes in human behaviour. The study selected the sample from bank customers in Ghana through an intercept approach using structured questionnaires. A two stage-approach of confirmatory factor analysis and a structural equation modelling were used in analysing the data. The findings show that websites' social feature, trust, compatibility with lifestyle and online customer services have a significant effect on customers' intentions to adopt Internet banking. However, ease of use did not have a significant relationship with customers' intentions to adopt Internet banking. The significance of the study as well as recommendations for theory, practice and future studies have been discussed.     

An examination of the determinants of customer loyalty in mobile commerce contexts

While the importance of customer loyalty has been recognized in marketing literature for at least three decades, the development and empirical validation of a customer loyalty model in a mobile commerce (m-commerce) context had not been addressed. The purpose of our study was to develop and validate such a customer loyalty model. Based on IS and marketing literature, a comprehensive set of constructs and hypotheses were compiled with a methodology for testing them. A questionnaire was constructed and data were collected from 255 users of m-commerce systems in Taiwan. Structural modeling techniques were then applied to analyze the data. The results indicated that customer loyalty was affected by perceived value, trust, habit, and customer satisfaction, with customer satisfaction playing a crucial intervening role in the relationship of perceived value and trust to loyalty. Based on the findings, its implications and limitations are discussed.     

Exploring the role of customer relationship management (CRM) systems in customer knowledge creation

This study explores how customer relationship management (CRM) systems support customer knowledge creation processes [48], including socialization, externalization, combination and internalization. CRM systems are categorized as collaborative, operational and analytical. An analysis of CRM applications in three organizations reveals that analytical systems strongly support the combination process. Collaborative systems provide the greatest support for externalization. Operational systems facilitate socialization with customers, while collaborative systems are used for socialization within an organization. Collaborative and analytical systems both support the internalization process by providing learning opportunities. Three-way interactions among CRM systems, types of customer knowledge, and knowledge creation processes are explored.     

A recommendation framework for remote sensing images by spatial relation analysis

In recent years, Remote Sensing Images (RS-Images) are widely recognized as an essential geospatial data due to their superior ability to offer abundant and instantaneous ground truth information. One of the active RS-Image approaches is the RS-Image recommendation from the Internet for meeting the user's queried Area-of-Interest (AOI). Although a number of studies on RS-Image ranking and recommendation have been proposed, most of them only consider the spatial distance between RS-Image and AOI. It is inappropriate since both of the RS-Image and AOI not only have the spatial information but also the cover range information. In this paper, we propose a novel framework named Location-based rs-Image Finding Engine (LIFE) to rank and recommend a series of relevant RS-Images to users according to the user-specific AOI. In LIFE, we first propose a cluster-based RS-Image index structure to efficiently maintain the large amount of RS-Images. Then, two quantitative indicators named Available Space (AS) and Image Extension (IE) are proposed to measure the Extensibility and Centrality between RS-Image and AOI, respectively. To our best knowledge, this is the first work on RS-Image recommendation that considers the issues of extensibility and centrality simultaneously. Through comprehensive experimental evaluations, the experiment result shows that both indicators have their own distinguished ranking behaviors and are able to successfully recommend meaningful RS-Image results. Besides, the experimental results show that the proposed LIFE framework outperforms the state-of-the-art approach Hausdorff in terms of Precision, Recall and Normalized Discounted Cumulative Gain (NDCG).     

Managing information technology (IT) for one-to-one customer interaction

A one-to-one marketing paradigm has emerged that suggests organizations will be more successful if they concentrate on obtaining and maintaining a share of each customer rather than a share of the entire market, with information technology (IT) being the enabling factor. This paper presents four key elements that provide the necessary steps that allow an organization to position its people, business processes, and information systems to establish and take advantage of this emerging paradigm. The key elements are: (1) business process analysis, (2) integration and redesign of customer data, (3) IT-enabled customer interaction, and (4) accessibility/transmission of organizational information. Further, this paper discusses the importance of integrating these four IT elements for achieving effective customer interaction.     

Product recommendation for e-commerce business by applying principal component analysis (PCA) and K-means clustering: benefit for the society

Innovations in Systems and Software Engineering - Recommender system is a computer-based intelligent technique which facilitates the customers to fulfill their purchase requirements. In addition to...     

A forward displacement analysis of a class of stewart platforms

A closed-form forward displacement analysis is performed for a Stewart Platform-type of parallel mechanism, whose six legs meet in a pair-wise fashion at three points in the top and base platforms. The six legs and two platforms of this mechanism together form an octahedron. An eighth-degree polynomial in the square of the tan-half-angle that measures the elevation of a triangular face of the octahedron relative to the base triangle is derived. Each of three vertices of the base triangle of the octahedron is modeled by a spherical four-bar mechanism, and the polynomial is obtained by eliminating a pair of tan-half-angular displacements from the displacement equations of the three spherical four-bar mechanisms. The result are verified numerically by performing a reverse displacement analysis and displaying real solutions on a graphic system. It is clear that there are a maximum of eight reflected pairs of real assembly configurations of the octahedral form of the Stewart Platform.     

Intelligent customer complaint handling utilising principal component and data envelopment analysis (PDA)

In this study, we consider customer to be a company's crucial asset. In order to have a fast, efficient decision-making process, it is vital that a customer relationship management (CRM) decision-maker condenses and abstracts the existing information. A questionnaire survey was conducted among respondents in order to obtain the required data. The questionnaire contains nine categories of satisfaction variables. To perform the analysis, we used principal component analysis (PCA) and data envelopment analysis (DEA). PDA has been utilised as an abbreviation for the integration of these two methods. To effectively analyse the procedure, PCA was utilised to assign a number to each category of questions related to each satisfaction variable. To achieve optimal precision, DEA was applied to the three categories of customers (‘most important’, ‘important’ and ‘ordinary’ customers) in order to determine the strengths and weaknesses of customer services from these customers’ perspectives. Customers were clustered and then DEA was used to determine their viewpoints. Using DEA, we have optimised our recognition of customers’ complaints and then provided recommendations and remedial actions to resolve the current issues in logistics and transport industry in general, and at Fremantle port in particular.SignificanceThe current study integrates soft computing and optimisation technique in order to build the CRM recommender system. It demonstrates the hybrid soft computing strengthens in area of CRM as the relevance solution. The significance of the proposed algorithm is three fold. First, it integrates soft computing and optimisation technique in order to build the CRM recommender system. Second, it utilises the most standard CRM variables in its decision making process. Third, it is an optimising algorithm because it integrates DEA with PCA technique.     

Choosing among weight-estimation methods for multi-criterion analysis: A case study for the design of multi-purpose offshore platforms

Application of the sustainability concept to environmental projects implies that at least three feature categories (i.e., economic, social, and environmental) must be taken into account by applying a participative multi-criterion analysis (MCA). However, MCA results depend crucially on the methodology applied to estimate the relative criterion weights. By using a logically consistent set of data and methods (i.e., linear regression [LR], factor analysis [FA], the revised Simos procedure [RSP], and the analytical hierarchy process [AHP]), the present study revealed that mistakes from using one weight-estimation method rather than an alternative are non-significant in terms of satisfaction of specified acceptable standards (i.e., a risk of up to 1% of erroneously rejecting an option), but significant for comparisons between options (i.e., a risk of up to 11% of choosing a worse option by rejecting a better option). In particular, the risks of these mistakes are larger if both differences in statistical or computational algorithms and in data sets are involved (e.g., LR vs. AHP). In addition, the present study revealed that the choice of weight-estimation methods should depend on the estimated and normalised score differences for the economic, social, and environmental features. However, on average, some pairs of weight-estimation methods are more similar (e.g., AHP vs. RSP and LR vs. AHP are the most and the least similar, respectively), and some single weight-estimation methods are more reliable (i.e., FA > RSP > AHP > LR).     

Mobile payment: Understanding the determinants of customer adoption and intention to recommend the technology

Mobile payment is receiving growing attention globally, from consumers to merchants, as an alternative to using cash, check, or credit cards. The potential of this technology is enormous. This study aims to identify the main determinants of mobile payment adoption and the intention to recommend this technology. We advance the body of knowledge on this subject by proposing an innovative research model that combines the strengths of two well-known theories; the extended unified theory of acceptance and use of technology (UTAUT2) with the innovation characteristics of the diffusion of innovations (DOI), with perceived security and intention to recommend the technology constructs. The research model was empirically tested using 301 responses from an online survey conducted in a European country, Portugal. Data was analyzed using the structured equation modeling (SEM). We found compatibility, perceived technology security, performance expectations, innovativeness, and social influence to have significant direct and indirect effects over the adoption of mobile payment and the intention to recommend this technology. The relevance of customer's intention to recommend mobile payment technology in social networks and other means of communication was also confirmed, supporting the recommendation to include it in social marketing campaigns and in future technology adoption studies. For researchers this study provides a basis for further refinement of individual models of acceptance. For practitioners, understanding the key constructs is crucial to design, refine, and implement mobile payment services, applications, and products that achieve high consumer acceptance, value, and high rates of positive recommendations in social networks.     

Implementing an analytic model for customer information control systems (CICS)

In most installations, it is important that response time consistently meets negotiated service levels for online, interactive systems. As a result, the capacity planning and performance management disciplines have become important functions to these installations. This paper discusses one of the tools used in capacity planning. Initial methods of capacity planning ranged from “seat of the pants” analysis to complex trending techniques. Because it is often necessary to take into account not only the growth pattern of various capacity indicators, but also the interrelationship of these indicators, analytic queuing models have become an accepted method of analysis in the computer measurement arena. The analytic queuing model discussed in this paper is a mathematic representation of the physical parts of a computer system. It is important to note that such an analytic model can only evaluate a finite number of elements or pieces of the system. As a result, when actual measured values are compared with those calculated by the model (the process of model validation) discrepancies can result because of elements that are not explicitly represented in the model. Many of the influences that are not represented by the mathematic model can be removed by tuning the system to remove bottlenecks. When using a model for capacity planning, it is assumed that the data used to develop the model are derived from a system that is “moderately tuned.” A moderately tuned system is one in which the majority of the bottlenecks or other influences not represented by the model have been removed. When the model is used to predict the responsiveness and throughput of the system into the future, it is assumed that any negative influences not represented in the model will be removed in a timely fashion. In this paper, we will review the impact of such tuning issues on attempts to validate the model against actual data. The analytic model discussed in this paper is for IBMs Customer Information Control System (CICS). The model was published in 1982 in the IBM Systems Journal. In the following sections, we will review the model that was presented in the IBM Systems Journal, present extensions required to implement the model for MVS systems, and discuss the aspects of CICS performance that are not represented by analytic models based on traditional SMF and RMF data.     

A semantic recommendation algorithm for the PaaSport platform-as-a-service marketplace

Platform as a service (PaaS) is one of the Cloud computing services that provide a computing platform in the Cloud, allowing customers to develop, run, and manage web applications without the complexity of building and maintaining the infrastructure. The primary disadvantage for an SME to enter the emerging PaaS market is the possibility of being locked into a certain platform, mostly provided by the market's giants. The PaaSport project focuses on facilitating SMEs to deploy business applications on the best-matching Cloud PaaS offering and to seamlessly migrate these applications on demand, via a thin, non-intrusive Cloud-broker, in the form of a Cloud PaaS Marketplace. PaaSport enables PaaS provider SMEs to roll out semantically interoperable PaaS offerings, by annotating them using a unified PaaS semantic model that has been defined as an OWL ontology. In this paper we focus on the recommendation algorithm that has been developed on top of the ontology, for providing the application developer with recommendations about the best-matching Cloud PaaS offering. The algorithm consists of: a) a matchmaking part, where the functional parameters of the application are taken into account to rule out inconsistent offerings, and b) a ranking part, where the non-functional parameters of the application are considered to score and rank offerings. Τhe algorithm is extensively evaluated showing linear scalability to the number of offerings and application requirements. Furthermore, it is extensible upon future semantic model extensions, because it is agnostic to domain specific concepts and parameters, using SPARQL template queries.     

Analysing complaint intentions in online shopping: the antecedents of justice and technology use and the mediator of customer satisfaction

Complaint behaviours are the key to the competition in an online market when service quality is a major concern of consumers. An understanding of complaint intentions can provide insight into a negative service experience and in turn, effectively redress consumer's problems. It is our purpose to examine the determinants of complaint intentions in the online shopping. When online consumers essentially involve the purchase of products/services and the use of web-based technologies, two major issues particularly arise in this context, exchange behaviour and technology use. This study thus integrates justice perception and expectation–confirmation model (ECM) of information system continuance to understand customer satisfaction and in turn, complaint intentions. Data were collected for online consumers with negative service experiences. The results of testing the structural model indicated that distributive and interactional justices significantly contribute to customer satisfaction and complaint intentions, but procedural justice does not. ECM-based features, such as perceived usefulness, are all important in determining customer satisfaction and complaint intentions. The implications for managers and scholars are further discussed.     

一种优化组合相似度的协同过滤推荐算法

为了进一步提高相似度计算的准确性,提出了一种优化组合相似度的协同过滤推荐算法。首先,建立用户-项目评分时间矩阵,根据用户对共同评分项目的评分时间先后顺序,计算用户之间的影响力;其次,根据用户对共同评分项目的评分差异,计算评分差异的加权信息熵;最后,将时序行为影响力融入到基于加权信息熵的相似度中,其中融合参数α由随机粒子群优化算法选择。通过与其他相似度计算方法比较,该算法降低了标准平均绝对误差和流行度,在一定程度上降低了数据稀疏性的影响,能更准确地计算相似度,从而提高了推荐质量。     

Qualitative analysis of user-based and item-based prediction algorithms for recommendation agents

Recommendation agents employ prediction algorithms to provide users with items that match their interests. In this paper, several prediction algorithms are described and evaluated, some of which are novel in that they combine user-based and item-based similarity measures derived from either explicit or implicit ratings. Both statistical and decision-support accuracy metrics of the algorithms are compared against different levels of data sparsity and different operational thresholds. The first metric evaluates the accuracy in terms of average absolute deviation, while the second evaluates how effectively predictions help users to select high-quality items. The experimental results indicate better performance of item-based predictions derived from explicit ratings in relation to both metrics. Category-boosted predictions lead to slightly better predictions when combined with explicit ratings, while implicit ratings, in the context that have been defined in this paper, perform much worse than explicit ratings.