Kwiseok Kwon

Collaborative Filtering Using Dual Information Sources

Conventional collaborative-filtering methods use only one information source to provide recommendations. Using two sources - similar users and expert users - enables more effective, more adaptive recommendations. Conventional CF methods suffer from a few fundamental limitations such as the cold-start problem, data sparsity problem, and recommender reliability problem. Thus, they have trouble dealing with high-involvement, knowledge-intensive domains such as e-learning video on demand. To overcome these problems, researchers have proposed recommendation techniques such as a hybrid approach combining CF with content-based filtering. Because e-commerce Web sites for e-learning often have various product categories, extracting the many attributes of these categories for content-based filtering is extremely burdensome. So, it might be practical to overcome these limitations by improving the CF method itself.

How to design personalization in a context of customer retention: Who personalizes what and to what extent?

Personalization is a strategic tool for product or service differentiation, especially when competition is keen in the market. Many personalization strategies have been developed and realized with this in mind. Little is known about the impact of different personalization strategies, regarding different personalization dimensions on customer retention, however. This has resulted in a lack of consensus on how best to design personalization strategies. To address the related issues, this study identifies the dimensions of personalization, and investigates the effect of each dimension on customer retention. It does so by implementing actual personalization systems corresponding to two factorial design experiments involving 372 participants. Multiple analysis of covariance reveals the effectiveness of each dimension and interactions among them. This study consequently proposes the optimal combination of personalization dimensions that leads to customer satisfaction and loyalty.

How to best characterize the personalization construct for e-services

Abstract During the past few decades, the importance of personalization has been emphasized frequently in the field of e-services. Since there are various dimensions in the implementation of personalization, a variety of personalization strategies have been developed and embodied. Yet, little is known about the impact of different personalization dimensions on customer retention, which is the fundamental objective of personalization. This results in a lack of consensus about how best to characterize the personalization construct. In order to solve this problem, this study empirically investigates the effect of each classified personalization strategy and proposes the most highly recommended combination of personalization dimensions.

An empirical test to forecast the sales rank of a keyword advertisement using a hierarchical Bayes model

Online advertising (ad) is a form of promotion that uses the Internet and World Wide Web for the expressed purpose of delivering marketing messages to attract customers. Not surprisingly, how to predict the effectiveness of online advertising has gained lots of research attention. This study introduces the hierarchical Bayesian analysis to the online advertising effect model involving competition with other products. It developed a competition model with a time-decaying effect that is applicable for the sales-rank data in the online marketplace. The proposed model formalizing the hierarchical structure has performed better than the reduced model without having random effect components. It captures the heterogeneous advertising responses across the products as well as search keywords. Our results have implications for online advertising effect measurement, and may help guide advertisers in decision-making.

Design and Implementation of Multi-functional Java Card for AMR

AMR(Automatic Meter Reading), which means that it reads the meter of electricity, gas, or water, etc at a remote place automatically through wired or wireless communication, has been studied in terms of Power Line Communication method and Local Area Wireless Communication method, etc. In this paper, we designed and implemented JCA(Java Card for AMR) capable of AMR, which is based on java Card technology indispensable to the ubiquitous world. In this paper, JCA follows standard transactional procedures offered by power supply company and manages power usage log and billing data, and is designed in order to satisfy EMV multi-functional specifications. Because JCA is a multi-functional smart card capable of post-issuance applets as an open platform, it is installed into other applications of affiliated concerns as well as credit card and traffic card applications. Not only the proposed JCA is a low cost system, compared to other AMR systems, but is capable of paying rates in advance or later by applying authentication and security function of java Card. In addition the proposed JCA system can create value added services such as affiliated services with corporate alliance.

Increasing Customer Lifetime Value by Encouraging Customers to Pay Less in a Competitive Electricity Market

The electrical power industry has been recognized as a natural monopoly industry for its technological and industrial characteristics. However, a competitive market system has been introduced to that industry in Europe, North America and Australia to overcome the inefficiencies originated from the monopolistic system for decades. In Korea, the power industry is expected to be placed in a competitive market system within several years after separation and privatization of vertically integrated industry in progress. Hence, there is a need for a research on the increase of customer value in that industry, however, existing studies have little dealt with that problem and there is no research on the price policy to consider churn and retention of customers. Therefore, this study provides a methodology for increasing customer loyalty and lifetime value by presenting the lowest pricing plan which leads to diminishing customers` cost. It is verified through an empirical examination that firms can enhance customer loyalty using a price element in that industry and maximize their profit by finding out customers whose lifetime values would increase.