• Journal of Convergence Society for SMB
• /
• v.6 no.3
• /
• pp.79-83
• /
• 2016

The purpose of this study is to provide customized information to student which study and live in a university campus. In this study, we collect internal data of campus and external data on the Internet such as the blog or SNS and, then store and process them. After that, we propose a system for providing individual students one-to-one marketing by analyzing these data in detail. This system analyzes purchase history information and the attendance of the building, and then transmits the coupon and information individually according to the pattern to the student's mobile phone.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.139-141
• /
• 2002

본 논문에서는 인터넷 컨텐츠 사이트에서 개인별로 컨텐츠를 효과적으로 추천하기 위한 개인화 시스템모델을 제안하였다. 제안한 모델은 묵시적인 평가정보를 이용한 사례기반추론 기법으로서 협동적필터링 기법과 달리 유사집단의 평가정보를 이용하지 않고 개인별 속성에 대한 가중치와 속성 값을 이용하여 추천하는 기법이다. 이 기법은 각 사용자의 상품 추매 속성을 추천에 반영할 수 있는 장점이 있으며 사용자 프로파일을 이용하여 개인화된 추천이 가능하다. 제안한 기법이 Recall, Precision, F-measure의 평가 방법을 통해 실험한 결과 협동적필터링 기법 보다 모든 부분에서 더 좋은 결과가 나왔음을 볼 수 있다. 그러므로 제안 시스템이 유사 사용자의 평가정보를 이용한 협동적필터링 기법보다 효율적인 개인화 전략이 가능하다고 말 수 있다. 본 제안 모델을 이용하여 일대일 마케팅을 위한 eCRM 시스템 개발이 가능하리라 예상된다.

• Proceedings of the Korean DIstribution Association Conference
• /
• 1999.11a
• /
• pp.307-325
• /
• 1999

본 논문은 최근 관심이 집중되고 있는 PC통신 및 인터넷에 의한 사이버 쇼핑행동을 이해하기 위해서 사이버 쇼핑경험자와 비경험자간의 차이를 비교하였다. 인터넷 및 PC통신 사용자를 대상으로 일대일 면접과 전자메일 설문방식을 병행하여 426명으로부터 설문응답을 얻었다. 주요설문내용은 인터넷 및 PC통신 사용실태, 사이버쇼핑 사용실태, 사이버 쇼핑에 대한 지각된 위험요인(perceived risks), 그리고 인구통계적 변수 등이었다. 응답자를 인터넷과 PC통신을 통해 제품이나 서비스를 구매한 경험이 있는 집단(182명)과 없는 집단(242명)으로 나누어 분산분석(ANOVA)과 판별분석(discriminant analysis)을 실시하였다. 그 결과 사이버 쇼핑구매 경험자와 무경험자간에는 인터넷 및 PC통신 행태, 인구통계변수, 사이버 쇼핑에 대한 지각위험, 사이버 쇼핑 중요속성 평가에서 통계적으로 유의미한 차이를 나타냈다. 본 연구결과를 토대로 효과적인 사이버 마케팅전략을 제시하였다.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2004.11a
• /
• pp.340-348
• /
• 2004

온라인상점의 상품추천시스템은 일대일마케팅의 대표적 실현수단으로써의 가치를 인정받고 있다. 대부분의 상품추천시스템은 시시각각 변화하는 소비자의 기호에 따라 상품을 어떻게 추천할 것인가에 대한 문제에 직면해 있다. 본 연구에서는 급변하는 온라인상점 환경에 탄력적으로 대응하기 위하여 데이터마이닝과 다중모형조합기법을 이용한 상품추천시스템 모형을 제안하고자 한다. 제안하는 상품추천시스템은 현재 운영중인 온라인상점 데이터로 프로토타입을 구축하고 실제 소비자에 대한 적용가능성을 검증하였으며, 그 결과 실제 유용할 것으로 확인되었다.

• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.153-177
• /
• 2001

Nowadays, product recommendation is one of the important issues regarding both CRM and Internet shopping mall. Generally, a recommendation system tracks past actions of a group of users to make a recommendation to individual members of the group. The computer-mediated marketing and commerce have grown rapidly and thereby automatic recommendation methodologies have got great attentions. But the researches and commercial tools for product recommendation so far, still have many aspects that merit further considerations. To supplement those aspects, we devise a recommendation methodology by which we can get further recommendation effectiveness when applied to Internet shopping mall. The suggested methodology is based on web log information, product taxonomy, association rule mining, and decision tree learning. To implement this we also design and intelligent Internet shopping mall support system based on agent technology and develop it as a prototype system. We applied this methodology and the prototype system to a leading Korean Internet shopping mall and provide some experimental results. Through the experiment, we found that the suggested methodology can perform recommendation tasks both effectively and efficiently in real world problems. Its systematic validity issues are also discussed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.699-702
• /
• 2003

Most of current shopping malls do not satisfy everyone because they present arrangements of goods and suggestions uniformly and comprehensively according to the thinking of their managers. On the other hand not the standard of selection but the comparison of price plays a decisive role of the purchase of goods as similar form each other. When classifying into groups according to generations, gender, income, job, hobby, etc. the propensity of purchase is showed differently and the interest and real purchasing power of the individual is different in shopping malls. It also will maximize the purchasing power of customers to make and implement the sales strategy more quickly as the basis of fashion and season of environmental factors and natural calamity of environmental variable according to the economic principle. This paper concentrates on the design and implementation of intelligent shopping mall that is added the sales strategy according to environmental variable and can not only analysis, update and classify the propensity of purchase continuously but also construct optimal goods automatically.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.12
• /
• pp.227-235
• /
• 2010

This paper proposes the recommendation system which is advanced using RFM method and Association Rules in e-Commerce. Using a implicit method which is not used user's profile for rating, it is necessary for user to keep the RFM score and Association Rules about users and items based on the whole purchased data in order to recommend the items. This proposing system is possible to advance recommendation system using RFM method and Association Rules for cross-selling, and also this system can avoid the duplicated recommendation by the cross comparison with having recommended items before. And also, it's efficient for them to build the strategy for marketing and crm(customer relationship management). It can be improved and evaluated according to the criteria of logicality through the experiment with dataset collected in a cosmetic cyber shopping mall. Finally, it is able to realize the personalized recommendation system for one to one web marketing in e-Commerce.

• Journal of Digital Convergence
• /
• v.10 no.8
• /
• pp.119-133
• /
• 2012

Recent rise of social media channel is changing social and economic paradigm and is being used as an effective communication in marketing. The following research analyzes the most employed social marketing tools such as portal advertisement, blogs, and SNS channels to effectively execute social media marketing from performance indicator and ICSI perspective, analyzes each channel's characteristics and results based on Korea distribution companies' case studies and suggests a framework to effectively use each channel. Portal site advertisements are the most effective channel to draw customers with new information and are thus linked to profit by corporations with excessive budget and workforce. Blogs target a specific range of customers providing quality information and knowledge thus improving a corporation's and its product's trustworthiness, spread the word by allowing customers to scrap the information, form social groups and synthesize ideas, events, new contents and social involvement with loyal customers. SNS channels allow customers to get involved in real time information and events, grow through network by the power of customers, react immediately to customers' needs, and execute real-time market and customer reports. Though national corporations currently rely heavily on portal site advertisements, insightful marketing professionals are showing financial results with blog and SNS. In the future, based on a precise understanding of each channel's benefits and expected results, and with a focus on flexibility, timeliness and integrated use of each channel, a portfolio of dynamic marketing as a maximizing strategy could be synthesized.

• Journal of the Korean Society for Library and Information Science
• /
• v.47 no.4
• /
• pp.169-186
• /
• 2013

The purpose of this study is to analyze the benefits of library assisted instruction. A survey was conducted along with in-depth interview with students who have experienced library assisted instructions. As a result, 18 different domains of benefits of library assisted instruction have been identified through the students with the experience of the instruction. The benefits include 'increasing efficiency in learning', 'building the habits of reading', etc. The benefits of library assisted instruction are expected to be applied in the strategies to operation of library service.

• The KIPS Transactions:PartD
• /
• v.11D no.7 s.96
• /
• pp.1537-1542
• /
• 2004

Various studies to increase customer satisfaction of a web based system are performed actively. Also in recent days an interest about the personalization that supporting a order type service on customer's viewpoint was raised. So the studies supporting the personalization is required in a web-based marketing system. In this study, we designed an intelligent recommendation system which supporting one to one web marketing using cross selling. The proposed system used an intelligent data mining method as a concurrent cross selling and a sequential cross selling. Also, In experiment on the prototype, we show a proposed system was usable in an practical system applying the mining result.