Victoria Y. Yoon

Assessing the impact of internet agent on end users' performance

Intelligent software agents that can perform tasks on the users behalf independently of direct control of the user themselves, promise to evolutionize the way in which we use the Internet to conduct business. Research on how these agents will change the nature of Internet-based e-commerce and what its impact will be on consumers and businesses is only just beginning. To assess the impact of agent usage in a retail online shopping environment, an empirical study was conducted to determine what impact, if any, the use of Shopbots, a form of Internet agent, had on consumers looking to purchase a DVD player online via the World Wide Web [WWW]. Of particular interest was the Internet agents impact on the users task performance and task outcomes. These included the time spent on shopping activities, the shoppers confidence in their purchase decision, the quality of the purchase decision made by the shopper and the amount of cognitive effort required to select a product for purchase.

Assessing the impact of recommender agents on on-line consumer unplanned purchase behavior

Recommendation agents (RAs) have been used by many Internet businesses such as Amazon and Netflix. However, few authors have studied how consumer behavior is affected by those that make suggestions to online consumers based on their recent shopping behavior. Fewer still have examined the role that RAs play in influencing impulse purchasing decisions online. Our study developed a theoretical model to illustrate the impact of RAs on online consumer behavior. The model was tested through an online shopping simulation which used a collaborative filtering based product RA. Particular attention was paid to the effects of an RA on consumer behavior; we found that it increased promotion and product search effectiveness, user satisfaction with the website, and unplanned purchases. Results showed that our model provided insights into the impact of an RA on online consumer behavior and thus provided suggestions for implementing effective systems.

Assessing the moderating effect of consumer product knowledge and online shopping experience on using recommendation agents for customer loyalty

Social media technologies have greatly facilitated the creation of many types of user-generated information, e.g., product rating information can be used to generate preference-based recommendation. As a decision support tool, a Recommendation Agent (RA) has been widely adopted by many e-commerce websites. The impact of RAs on online shopping has been extensively examined in the IS literature. However, from Marketing and Social Media perspectives, the widely adopted cognitive-affect-conative-action framework of customer loyalty has not been tested in the presence of RAs. Moreover, there has been little research assessing the impact of increasing consumer knowledge about specific product domains on customer satisfaction and loyalty. Based on these important constructs, this study proposes and empirically tests a parsimonious model assessing the moderating effect of consumer product knowledge and online shopping experience on using RA for customer loyalty. The results show that consumer product knowledge relationship between RAs recommendations negatively impacts the recommendation quality and customer satisfaction, however, consumer online shopping experience does not have a significant effect on the relationship between customer satisfaction and customer loyalty. The results make a significant contribution to a better understanding of the constructs in our research model and provide evidence useful for the management of websites using RAs for product recommendations.

Applications of wavelet data reduction in a recommender system

Memory-based collaborative filtering (CF) recommender systems have emerged as an effective technique for information filtering. CF recommenders are being widely adopted for e-commerce applications to assist users in finding and selecting items of interest. As a result, the scalability of CF recommenders presents a significant challenge; one that is particularly resilient because the volume of data these systems utilize will continue to increase over time. This paper examines the impact of discrete wavelet transformation (DWT) as an approach to enhance the scalability of memory-based collaborative filtering recommender systems. In particular, a wavelet transformation methodology is proposed and applied to both synthetic and real-world recommender ratings. For experimental purposes, the DWT methodologys effect on predictive accuracy and calculation speed is evaluated to compare recommendation quality and performance.

A semantic approach to monitor business process

Finding an effective method for managing and evaluating the performance of business processes is a key element for e-business success.

Agent learning in the multi-agent contracting system [MACS]

This paper presents a Bayesian learning approach for a multi-agent system, called multi-agent contracting system [MACS]. The system learns to identify an appropriate agent to answer free-text queries and keyword searches for defense contracting. This research builds on past work by some of the authors by extending MACS to a truly intelligent multi-agent system with the ability to learn from and adapt to its environment. The efficacy of MACS is determined by analyzing the accuracy and degree of learning in the system. This is accomplished by testing the system against historical data.

Recommendation agent impact on consumer online shopping

Highlights? This study assesses the impact of a recommendation agent (RA) on customer shopping. ? The results indicate that RA affects product promotion effectiveness. ? Product promotion effectiveness influences consumer satisfaction with the website. ? Consumer satisfaction with the website is a determinant of consumer loyalty. ? The paper discusses the study implications for system developers and managers. A simulated online shopping environment with a recommender system based on collaborative filtering data has been developed to empirically test the impact of recommendation agents in an online retail environment. The report provides some background for the most widely used types of recommender system based on collaborative filtering. The Movie Magic system developed for this study is described, as well as the experiment assessing the impact of such an agent on product promotion effectiveness, customer satisfaction with the website, and customer loyalty to the website. Finally, the report discusses the implications of the results for system developers and managers interested in using Intelligent Agent technology for enhancing e-commerce. By corroborating the proposed relationships between the use of the recommender agent and improved product promotion, customer satisfaction and loyalty, the results should aid online businesses in further understanding the benefits and limitations of using a recommender agent to support e-commerce.

Managing Organizational Data Resources: Quality Dimensions

Little guidance has been available to organizations interested in addressing the necessary dimensions of data resources management to ensure data quality in increasingly encountered situations when data usage crosses system boundaries. The basic concept of metadata quality as a foundation for data quality engineering is proposed, as well as an extended data life cycle model consisting of eight phases: metadata creation, metadata structuring, metadata refinement, data creation, data utilization, data assessment, data refinement, and data manipulation. This extended model will enable further development of life cycle phase-specific data quality engineering methods. The paper also expands the concept of applicable data quality dimensions, presenting data quality as a function of four distinct components: data value quality; data representation quality; data model quality; and data architecture quality. Each of these, in turn, is described in terms of specific data quality attributes.

Ontology based integration of XBRL filings for financial decision making

In 2008, the US Securities and Exchange Commission (SEC) mandated all tier-1 public companies to report their financial statements in eXtensible Business Reporting Language (XBRL). XBRL has the potential to improve the efficiency and accuracy of financial disclosures, and thereby reduce costs. However, semantic heterogeneity across XBRL filings poses a challenge for individual (non-institutional) investors seeking to make inter-firm comparisons using XBRL data. In order to extend the benefits of XBRL to individual investors, this paper presents a design artifact, Ontology-based Framework for XBRL-mapping and Decision-making (OFXD), which provides interoperability between different XBRL filings. Specifically, OFXD resolves the semantic heterogeneity of the element and context definitions in various XBRL filings and generates an XBRL ontology - XBRLOnt. The results of this study show that the proposed design artifact is capable of addressing semantic heterogeneities between different XBRL filings. Using the concepts of the information value chain, this paper discusses the implications of XBRL interoperability on financial decision-making. We address the semantic heterogeneity issue and thereby improve the usability of XBRL data.We propose an Ontology-based Framework for XBRL-mapping and financial decision-making (OXFD).OXFD maps semantic heterogeneous XBRL elements and provides rules to calculate financial ratios.The results show the generalizability of our artifact for different XBRL filings.

Applying Semantic Web Technologies to Ontology Alignment

Ontologies are the backbone of intelligent computing on the World Wide Web but also crucial in many decision support situations. Many sophisticated tools have been developed to support working with ontologies, including prominently exploiting the vast array of existing ontologies. A system called ALIGN is developed that demonstrates how to use freely available tools to facilitate ontology alignment. First two ontologies are built with the ontology editor Protege and represented in OWL. ALIGN then accesses these ontologies via Javas JENA framework and SPARQL queries. The efficacy of the ALIGN prototype is demonstrated on a drug-drug interaction problem. The prototype could readily be applied to other domains or be incorporated into decision support tools.