• 한국멀티미디어학회논문지
• /
• 제7권4호
• /
• pp.592-600
• /
• 2004

전자 상거래 환경에서 e-CRM의 한 응용분야인 추천 시스템은 사용자 개개인의 요구를 충족하는 개인화된 품 추천 서비스를 제공한다. 일반적으로 기존 추천 시스템들은 응용 영역에 대한 방대한 과거 사용자 정보를 요로 한다. 그러나, 과거 정적인 사용자 정보 기반의 추천 방식은 다양한 사용자를 포함하는 영역 혹은 간에 민감하게 빠르게 변화하는 사용자 요구에 유연하게 대처하는 추천 방법이 필요하다. 또한, 해당영역의 존 사용자로부터 분류될 수 없는 새로운 사용자에 대한 추천을 어렵게 한다. 이러한 한계를 극복하고 유연한 추천 서비스를 위해 본 논문에서는 고객성향분석과 필터관리를 지원하는 CPAR (Customer Preference Analysis Recommender) 시스템을 설계하고 구현한다. 본 시스템의 필터 관리 능력은 기존 시스템의 방대한 초기 사용자 정보 필요 문제를 경감한다. 또한, CPAR 시스템은 플랫폼에 독립적이고 시간과 장소에 구애받지 않는 추천 서비스를 위해 XML 기반 무선 인터넷 환경에서 구현되었다.

• 한국의류학회지
• /
• 제27권9_10호
• /
• pp.1060-1071
• /
• 2003

This study was intended to identify customer's response to CRM of fashion business.488 questionnaires were distributed to male and female respondents aged 16 to 55, and then analyzed by descriptive statistics, oneway-ANOVA, chi-square test, and factor analysis. As a result of customer information management, respondents evaluated taste, interest and demographic informations as most valuable. But they did not value personal and credit information. For CRM concept, 4 factors were determined: continuous care and suggestion, particular service to important customer, customer management program development, and customer convenience consideration. For CRM activity, 3 factors were determined: customization, information offering, and programmed service strategies. Respondents were having positive attitude toward CRM concept and activity of fashion business. Among customer loyalty programs, they affected by immediate and direct programs most. The preference of customer contact methods was differentiated by sex and age groups. Males and teenagers preferred e-mail, and females preferred catalog and telephone connection.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 춘계학술발표대회
• /
• pp.1073-1074
• /
• 2017

In this paper, we present a customer preference analysis system using the Bluetooth Low Energy technology. Compared to Classic Bluetooth, Bluetooth Low Energy provides considerably reduced power consumption, and cost, as well as some unique characteristics while maintaining a similar communication range. The customer preference analysis system collects nearby Bluetooth Low Energy devices using an Android mobile device via Bluetooth Low Energy. In addition, the system is capable of suggesting, and advertising products that are related to these Bluetooth Low Energy devices based on the name of their manufacturer. This feature aims to attract potential customers to purchase these products.

• 대한지역사회영양학회지
• /
• 제14권5호
• /
• pp.545-555
• /
• 2009

School foodservice customers are likely to be tired of repeated cycle menus and their satisfaction for meals offered in school is inclined to be low. The menu variety is an important factor in increasing customer satisfaction. The purpose of this study was to investigate customer perspectives for applying rice based bread menus in order to add menu variety and promote using rice processed products in school foodservice. The questionnaire was distributed to 760 parent samples in elementary schools and 520 student samples in middle/high schools and a total of 665 and 387 usable data were collected, respectively. Food habits such as preference for cooking method, menu preference, food allergy and nutritional perspectives for menu and customer perception for rice based bread like quality, reliability, price, and purchasing convenience were investigated using 7 Likert scale. Also expected menu types applying rice based bread and offering frequency of rice bread menu were examined. Preference level for bread-based meals were moderate and students' preferences were slightly higher than parents. Menu types applying rice bread expected by middle/high school students were western food (49.4%), spaghetti (28.4%), set menu (13.7%), noodle (17.6%), Korean food (11.1%), Chinese food (10.9%) and porridge (4.5%). The most occupied rate was once in a week for expected offering frequency. Most respondents perceived that rice bread was more nutritive and qualitative than the wheat based one.

• 한국항해항만학회지
• /
• 제28권3호
• /
• pp.193-198
• /
• 2004

본 연구에서는 항만의 주요고객인 선사를 대상으로, 국외선사와 국내선사로 세분화하여 속성의 중요도와 항만 선호도 차이를 비교분석하였다. 컨조인트 분석 결과 국내선사와 국외선사 간의 항만선호도에서 분명한 차이를 보였으며, 이러한 차이는 기항지와 환적항에서 동시에 나타났다. 국외선사들은 환적항으로서 상하이항을 가장 높게 평가했지만, 국내선사들은 부산항을 상하이항보다 높게 평가했다. 또한, 기항지 선호도 비교에서도 비슷한 결과를 나타냈다. 이러한 연구결과는 국내외 선사에 따라 항만 선호도가 다르기 때문에 집단별로 구분하여 평가할 필요가 있음을 의미한다. 또한, 이를 바탕으로 타항만에 비해 경쟁위위에 있는 부산항의 선호도를 유지하기 위해서는 지속적인 목표(Target) 마케팅이 필요하며, 주요 목표(Target)는 항만의 주요 고객인 선사임을 암시한다.

• 한국IT서비스학회지
• /
• 제8권2호
• /
• pp.205-228
• /
• 2009

This paper examines how online product information changes the customers' purchase intentions from subjectivity-objectivity dichotomy perspective. Quality and Preference are proposed as product evaluation criteria and their marginal changes with product information differentiation are hypothesized. An experimental survey was conducted to 57 subjects and the hypotheses were partially supported through PLS path comparison method. The study contributes to IS research by proposing a simple and effective product evaluation framework and by abstracting the impact of product information from other factors. Finally, we suggest the utilization of product information with the optimization of the cost-benefit structure between information and purchase intention.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 C
• /
• pp.1481-1483
• /
• 1999

Power distribution system planning for maximum customer satisfaction and system efficiency requires accurate forecast of future demand in service area. Spatial load forecasting method provides a more accurate estimation of both magnitudes and location of future electrical load. This method considers the causes of load growth due to addition of customers and per capita consumption among customers by land use (residential, commercial and industrial). So the land-use study and it's preference for small area is quite important. This paper proposes land-use preference estimation method based on fuzzy logic. Fuzzy logic is applied to computing preference scores for each land-use and by these scores the customer growth is allocated in service area. An simulation example is used to illustrate the proposed method.

• ETRI Journal
• /
• 제37권2호
• /
• pp.317-327
• /
• 2015

A reliable analysis of consumer preference from a large amount of purchase data acquired in real time and an accurate customer characterization technique are essential for successful direct marketing campaigns. In this study, an optimal segmentation of post office customers in Korea is performed using a subspace projection-based clustering method to generate an accurate customer characterization from a high-dimensional census dataset. Moreover, a traditional temporal mining method is extended to an algorithm using the MapReduce framework for a consumer preference analysis. The experimental results show that it is possible to use parallel mining through a MapReduce-based algorithm and that the execution time of the algorithm is faster than that of a traditional method.

• 대한인간공학회지
• /
• 제23권3호
• /
• pp.1-12
• /
• 2004

In recent years, with the advent of e-Commerce the need for personalized services and one-to-one marketing has been emphasized. To be successful in increasingly competitive Internet marketplace, it is essential to capture customer loyalty. In this paper, we provide an intelligent agent approach to incorporate human sensibility into an one-to-one recommendation service in cyber shopping mall. Our system exploits human sensibility ergonomics and on-line preference matching technologies to tailor to the customer the suggestion of goods and the description of store catalog. Customizing the system`s behavior requires the parallel execution of several tasks during the interaction （e. g., identifying the customer`s emotional preference and dynamically generating the pages of the store catalog）. The recommendation agent system composed of five modules including specialized agents carries on these tasks. By presenting goods that are consistent with user interests as well as user sensibility, the accuracy and satisfaction of the recommendation service may be improved.

• 한국정보시스템학회지:정보시스템연구
• /
• 제8권2호
• /
• pp.91-110
• /
• 1999

Recently, searching agent systems to help purchase of products between business and customer have been actively studied in Electronic Commerce(EC). However, the most of comparative searching agent systems are only provided customers with searching results by the keyword-based search, and is not support the efficient decision models to be selected products considering the customer's requirements. This paper proposes the decision agent system applied decision model as well as searching functions based on the keyword-input to be selected useful products in EC. The proposed decision agent system is consist of the user interface, provider interface, decision model. Especially, as the example of the decision model, this paper is designed and implemented the prototype of decision agent system which is normalized the searching data and value of customer's preference weight as to each attribute, and orderly provided customers with computed results. This agent system is also carried out sensitive analysis according to the reflection ratio of the each attribute.