• 한국IT서비스학회:학술대회논문집
• /
• 2003.05a
• /
• pp.571-576
• /
• 2003

보험시스템은 상품 및 보험 종류에 따라서 결정되는 요소들이 많고 이에 대한 예외 사항이 많이 존재하는 특성을 가지고 있다. 기존 시스템에서의 상품속성 반영은 테이블을 통한 값 정의와 어플리케이션에서의 예외처리 로직(if then else)을 병행하여 사용함으로 인해, 상품변경과 신상품 개발에 대한 비용이 증가하고 신속한 시장 대응이 어려웠다. 본 논문에서는 보험상품 속성의 비즈니스 로직을 데이터화로 가능하게 하는 Well Formed Rule Base 시스템을 제시하고 실제 프로젝트 적용을 통한 효과를 설명한다.

• The KIPS Transactions:PartD
• /
• v.14D no.5
• /
• pp.491-500
• /
• 2007

In order to classify and manage on-line trading goods, the product classification scheme must be maintained. In most systems for handling product information, the classification scheme is managed manually by experts, which in general incurs a lot of time and cost. Effective management of classification system becomes more important as rapid development of industry expedites diversity and convergence of goods and services. There have been many researches on developing classification scheme, and continuing in this line of research, this paper proposes a new method for automatic generation of product classification scheme. Our main idea starts from the concept that a product is a set of attributes, and we propose a novel algorithm for automatically creating hierarchical classification scheme by utilizing inclusive relationships between products. We then prove the effectiveness of proposed algorithm by conducting an experiment.

• The Journal of the Korea Contents Association
• /
• v.15 no.5
• /
• pp.66-77
• /
• 2015

The main objective of this study was to identify the difference in the perceptions of the product attributes and the expected benefits for consumers and professionals in the performing arts industry. First, the Delphi method by using email and telephone was used to explore the professionals' perceptions of the attributes of performing arts and the expected benefits. Second, on-line consumer survey was used to explore the consumer perceptions of the attributes of performing arts and the expected benefits. Finally, this study tried to draw some difference of perceptions from both professionals and consumers. Contents of the arts, location of a theater, ticket price, relief of stress, and improvement of lifestyle were found to be commonly important factors for both parties. Among them, statistical differences between two groups were confirmed in the factors such as the reputations of the cast members and theatres, locations of theatres, and time duration of a performance.

• Journal of Distribution Research
• /
• v.13 no.4
• /
• pp.47-70
• /
• 2008

The purpose of this study is to find out characteristic of a product which has the most influence when consumer makes a purchase, and analyze if actual consumers make a purchase with recognition of the brand difference between PB and NB brands using conjoint analysis. As a result, the main factor which consumers consider when they purchase a product is the quality but the factor for brands (NB or PB) do not have an effect on their purchasing. The reason why consumers little consider a factor for PB or NB is that they do not have much knowledge of PB and they recognize the PB as a "me-too" product of NB. Therefore, retailers should develop more differentiated product in order to be recognized by consumers.

• KIISE Transactions on Computing Practices
• /
• v.22 no.5
• /
• pp.209-217
• /
• 2016

As smartphone usage increases, the number of consumers who refer to review data of e-commercial products using web sites and SNS is also explosively multiplying. However, reading review data using traditional websites and SNS is time consuming. Also, it is impossible for consumers to read all the reviews. Therefore, a system that collects review data of products and conducts sentiment word analysis of the review is required to provide useful information. The majority of systems that provide such information inadequately reflect the properties of the product. In this study, we described a system that provides analysis and evaluation of e-commerce products through review sentiment words as reflected properties of the product. Furthermore, the system enables consumers to access processed information about reviews quickly and in visual format.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.1
• /
• pp.49-62
• /
• 2022

Online customer review data can be easily collected on the Internet and also they describe sentimental evaluation of a product in different aspects. Previous sentiment analysis studies evaluate the degree of sentiment with review data, which may have multiple sentences describing different product aspects. Since different aspects of a product can be described in a sentence, the proposed method suggested analyzing a sentence to build a pair of a product aspect terms and sentimental terms. Bidirectional LSTM and CRF algorithms were used in this paper. A pair of aspect terms and sentimental terms are evaluated by pre-defined evaluation rules. The paper suggested using the result of evaulation as inputs of QFD, so that the quantified customer voices effect on the requirements of a new product. Online reviews for a hair dryer were used as an example showing that the proposed approach can derive reasonable sentiment analysis results.

• 한국IT서비스학회:학술대회논문집
• /
• 2002.11a
• /
• pp.467-472
• /
• 2002

전자상거래의 급속한 발달로 인하여 많은 상품이 거래가 되로 있다. 기업은 상품들 가운데서 적절한 상품을 고객에게 추천하기 위해서 추천시스템을 개발을 하였다. 그러나 사용자와 고객의 수가 급증하면서 추천을 위해서 많은 시간과 비용이 들게 되었다. 본 논문에서는 이러한 확장성의 문제점을 해결하기 위해서 속성추출방법을 추천시스템에 적용하여 추천의 시간을 단축하여 확장성의 문제를 해결하고자 개선된 추천시스템을 개발했다. 개선된 추천시스템의 추천속도는 기존의 추천시스템에 비하여 빠른 추천이 가능하게 되었다. 이로 인해 확장성의 문제를 해결할 수 있게 되었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.91-93
• /
• 2004

B2B Marketplace상에서의 거래에서 나타나는 주요한 특징은 다품종 및 대량의 물품 거래가 n：n거래 관계에 놓여있다는 점과 거래자가 원활한 거래 및 기업 내 관리를 위해 각자의 전자 카탈로그를 이용한 거래를 원한다는 정이다. 하지만 개별적인 전자 카탈로그 사용과 미흡한 표준안은 전자 카탈로그 상호 연계의 걸림돌이 되어 시장 형성의 걸림돌이 되고 있다. B2B Marketplace는 표준 분류체계를 중심으로 거래 대상 상품을 재분류하여 구매 당사자간의 거래 대상 물품에 대한 상호 애핑을 지원하는 방법 등으로 이를 충족시키려 하고 있다. 하지만 요청되는 다량의 물품에 대해 매번 분류를 수행해야 하는 고비용의 작업이라는 문제점이 있다. 본 논문에서는 이를 극복하기 위하여 기계학습 기법을 이용한 전자 카탈로그 상품 자동분류기를 모델링하고 이를 구현하는 것에 초점을 두었다. 상품의 속성별로 분류에 끼치는 영향력이 다론 것이라는데 착안하여 전자 카탈로그를 상품 단위로 재 모델링 하였으며 속성별 정보가 풍부하지 못한 정물 극복하기 위하여 속성값을 어휘 단위로 구분한 데이터를 추가 하는 확장 모델을 정의하였다. 또한 해당 모델을 학습시키기 위한 알고리즘으로는 속성별로 다른 가중치를 부여 할 수 있도록 확장된 Naive Bayesian Classifier를 고안하였다. 그리고 이론 B2B Market Place상의 실 데이터에 적용하여 고안된 모델의 유효성을 검증하였다.

• Journal of the Korean Society of Floral Art and Design
• /
• no.40
• /
• pp.125-136
• /
• 2019

This study aims to examine the important factors of flower shops' store attributes influencing the repurchase intention for people who buy flowers for themselves with a hedonic shopping motivation. This study was verified by empirical survey and the results are summarized as follow. First, it was found that price, salesperson's professionalism, store accessibility had a significant positive impact on the repurchasing intention of flowers. Second, it was found that price is the first important factor influencing the repurchasing intention of flowers, and next salesperson's professionalism is the second important one, and lastly store accessibility is the third important one. For implications of this study, this study investigated the cause-and-effect relationship between flower shops' store attributes and the repurchasing intention of flowers for people who buy flowers for themselves with a hedonic shopping motivation, so it provides a theoretical foundation for further studies.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.10
• /
• pp.2886-2892
• /
• 2009

This research focuses on searching primary factors in accessing internet shopping sites. In this research we have derived primary factors such as the order factors, the product factors, and the delivery factors by factor analysis approach. We have done AHP analysis on these derived primary factors. The results of AHP analysis show that the most important factor is the product factors and the most important sub factor among the product factors is the after service factor including guaranteed returns and refunds, and product exchangeability. The next important factor is the incentive provision in which discount coupons, mileage accumulation policies are the main sub factors included.