• Journal of Korean Library and Information Science Society
• /
• v.34 no.1
• /
• pp.111-129
• /
• 2003

These days, libraries are faced with necessity f3r the systems to solve various and heterogeneous customers' needs. It is efficient through market segmentation to understand customers' needs and the use behaviors, to select the target markets, and to establish the proper marketing strategy for them. This study examines the necessity for library marketing, the importation for Internet marketing and the plans for the application, and suggests for plans of strategy for market segmentation In libraries.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06c
• /
• pp.88-90
• /
• 2006

최근 정보 통신기술의 발전으로 인하여 전자상거래가 확산되고 있는 실정이며, 이용하는 고객 또한 상당히 증가하고 있다. 고객의 활발한 구매 거래 활동으로 하루에도 아주 많은 양의 데이터가 생성되고 있는 실정이다. 이에 전자상거래의 웹 사이트 관리자나 경영자는 고객의 구매형태나 패턴의 특징을 파악하여 보다 효율적인 서비스를 고객에게 제공하기 위하여 현재까지 유사그룹의 고객 세분화를 적용하는 연구가 이루어지고 있다. 본 논문에서는 전자상거래에서 고객들의 정보를 분석하여 개인화하기 위한 방법으로 사용되는 고객 프로파일을 이용하여 고객세분화 하는데 적용을 하고자 한다. 기존 고객세분화의 통계적인 분석이 아닌 XML 기반의 고객 정보를 XPath를 이용하여 고객세분화에 필요한 규칙을 생성하고, 그 규칙을 바탕으로 고객 프로파일을 생성하는 방법과 프로파일을 이용한 군집에 따른 분석 결과 및 추천서비스를 소개하고자 한다.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2004.06a
• /
• pp.65-67
• /
• 2004

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.549-554
• /
• 2002

As the rate of housing supply is increased and consummer's diversified demand is changed. the direction of management of construction company is changed into marketing-based and the development of distinguished product. Therefore, this study purpose to establish the marketing strategy of apartment by the method of market segmentation. This study purpose to (1) analyze general methodology of apartment market-segmentation and positioning, (2) propose an alternative plan of apartment positioning for the effective marketing strategy. The method which was proposed in this study will be applied in strengthening the popularity of construction companies and the development of distinguished products.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.8
• /
• pp.1007-1013
• /
• 2010

A new local refinement scheme for spline finite element method has been proposed; this scheme involves the use of hierarchical B-spline. NURBS has been widely used in CAD; however, the local refinement of NURBS is difficult due to its tensor-product property. In this study, we attempted to use hierarchical B-splines as local refinement strategy in spline FEM. The regions of high gradients are overlapped by hierarchically-created local meshes. Knot vectors and control points in local meshes are extracted from global meshes, and they are refined using specific schemes. Proper compatibility conditions are imposed between global and local meshes. The effectiveness of the proposed method is verified on the basis of numerical results. Further, it is shown that by using a proposed local refinement scheme, the accuracy of the solution can be improved and it could be higher than that of the solution of a conventional spline FEM with relatively lower degrees of freedom.

• Information Systems Review
• /
• v.12 no.2
• /
• pp.75-88
• /
• 2010

This paper proposed a method that segmented customers utilizing SOM(Self-organizing Map) and predicted the customers' response of a marketing promotion for each customer's segments. Our proposed method focused on predicting the response of customers dividing into customers' segment whereas most studies have predicted the response of customers all at once. We deployed logistic regression, neural networks, and support vector machines to predict customers' response that is a kind of dichotomous classification while the integrated approach was utilized to improve the performance of the prediction model. Sample data including 45 variables regarding demographic data about 600 customers, transaction data, and promotion activities were applied to the proposed method presenting classification matrix and the comparative analyses of each data mining techniques. We could draw some significant promotion strategies for segmented customers applying our proposed method to sample data.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.85-91
• /
• 2018

Most banks use only demographic information such as gender, age, occupation and address to segment customers, but they do not reflect financial behavior patterns of customers. In this study, we aim to solve the problems by using various big data in a bank and to develop customer segmentation method which can be widely used in many banks in the future. In this paper, we propose an approach of segmenting clustering blocks with bottom-up method. This method has an advantage that it can accurately reflect various financial needs of customers based on various transaction patterns, channel contact patterns, and existing demographic information. Based on this, we will develop various marketing models such as product recommendation, financial need rating calculation, and customer churn-out prediction based on this, and we will adapt this models for the marketing strategy of NH Bank.

• Journal of The Korean Association of Information Education
• /
• v.23 no.4
• /
• pp.329-341
• /
• 2019

Computer education in universities has been expanded and specialized from ICT-based education in recent years to software education such as computational thinking and programming. Especially, as the 4th Industrial Revolution is emphasized in all fields of society, software education, which is its core, is being applied as an essential liberal arts course in universities. In the case of basic SW education for all students, it is necessary to provide differentiated education that is suitable for students because their special characteristics are different. In this study, we conducted a basic SW course for general liberal arts at A-university in Seoul and analyzed the survey data from 4,927 students for about 3 years, and classified the major series and searched the appropriate education method for each subdivided group. Through the analysis, we were able to find characteristic groups such as business and commerce, art and sports major. Finally, six groups for basic-SW education are presented. Educational directions such as programming language and level of difficulty setting suitable for differentiated education are presented for each group.

• Journal of the Korean association of regional geographers
• /
• v.12 no.5
• /
• pp.614-630
• /
• 2006

Improved estimates of populations at risk for quick and effective response to natural and man-made disasters require spatial disaggregation of zonal population data because of the spatial mismatch problem in areal units between census and impact zones. This paper implements a dasymetric surface model to facilitate spatial disaggregation of the population of a census block group into populations associated with each constituent pixel and evaluates the performance of the surface-based spatial disaggregation model visually and statistically. The surface-based spatial disaggregation model employed geographic information systems (GIS) to enable dasymetric interpolation to be guided by satellite-derived land use and land cover data as additional information about the geographic distributor of population. In the spatial disaggregation, percent cover based empirical sampling and areal weighting techniques were used to objectively determine dasymetric weights for each grid cell. The dasymetric population surface for the Atlanta metropolitan area was generated by the surface-based spatial disaggregation model. The accuracy of the dasymetric population surface was tested on census counts using the root mean square error (RMSE) and an adjusted RMSE. The errors related to each census track and block group were also visualized by percent error maps. Results indicate that the dasymetric population surface provides high-precision estimates of populations as well as the detailed spatial distribution of population within census block groups. The results also demonstrate that the population surface largely tends to overestimate or underestimate population for both the rural and forested and the urban core areas.

• Journal of Korean Society of Transportation
• /
• v.33 no.6
• /
• pp.575-583
• /
• 2015

The Korea Transport Institute (KOTI) builds the origin and destination(O-D) trip data with relatively smaller zone size such as Eup, Myeon, Dong administration unit districts in metropolitan area. Otherwise, O-D trip data was built by bigger size of traffic analysis zone(TAZ) such as Si, Gun, Gu administration unit districts for rural area. In some cases, it is needed to divide a zone into several sub-zones for rural area in order to analyze travel distribution pattern in detail for a certain highway and rail project. The study suggested a method to estimate O-D trips for sub-zones in the larger-size zones in rural area. Two different distribution models, direct demand model and gravity model, were calibrated for sub-zone's intra-zonal O-D trip pattern with metropolitan area O-D data which has smaller zone-size (sub-zone) data categorized by low, middle and high population density. The calibration results were compared between the two models. The gravity model with impedance function of power functional form was selected with better explanation for all groups in the metropolitan area. The adjusted $R^2$ was 0.7426, 0.6456 and 0.7194 for low, middle and high population density group, respectively. The suggested O-D trip estimating method is expected to produce enhanced trip patterns with sub-divided small zones.