• Korean Management Science Review
• /
• v.26 no.1
• /
• pp.183-196
• /
• 2009

Customer retention has been a pressing issue for companies to get and maintain the loyal customers in the competing environment. Lots of researchers make effort to seek the characteristics of the churning customers and the loyal customers using the data mining techniques such as decision tree. However, such existing researches don't consider relationships among customers. Social network analysis has been used to search relationships among social entities such as genetics network, traffic network, organization network and so on. In this study, a customer network is proposed to investigate the differences of network characteristics of churning customers and loyal customers. The customer networks are constructed by analyzing the real purchase data collected from a Korean cosmetic provider. We investigated whether the churning customers and the loyal customers have different degree centralities and densities of the customer networks. In addition, we compared products purchased by the churning customers and those by the loyal customers. Our data analysis results indicate that degree centrality and density of the churning customer network are higher than those of the loyal customer network, and the various products are purchased by churning customers rather than by the loyal customers. We expect that the suggested social network analysis is used to as a complementary analysis methodology with existing statistical analysis and data mining analysis.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.34 no.4
• /
• pp.57-72
• /
• 2009

As development of information technologies, customer retention has been an important issue in the competing environment. A lot of researches focus on prediction of the churning customers and seeking their characteristics. However, relationships among customers or products have not been considered in existing researches. In this study, product networks are proposed and analyzed to investigate the differences of network characteristics of products purchased by potential churning customers and those of loyal customers. The product networks are constructed from real product purchase data collected from a Korean department store. We investigated the characteristic differences, such as the degree centrality, degree centralization, and density, of two product networks constructed by potential churning customers and the loyal customers. The results indicate that degree centrality, density and degree centralization of the product network of the loyal customers are higher than those of the potential churning customers. And the promotional products of the department store are resulted to be effective in attracting the loyal customers.

• Information Systems Review
• /
• v.8 no.3
• /
• pp.125-134
• /
• 2006

This article adopts a decision tree algorithm(C5.0) to predict customer churning in online auto insurance environment. Using a sample of on-line auto insurance customers contracts sold between 2003 and 2004, we test how decision tree-based model(C5.0) works on the prediction of customer churning. We compare the result of C5.0 with those of logistic regression model(LRM), multivariate discriminant analysis(MDA) model. The result shows C5.0 outperforms other models in the predictability. Based on the result, this study suggests a way of setting marketing strategy and of developing online auto insurance business.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.19 no.5
• /
• pp.51-57
• /
• 2011

Parametric studies based on analysis of lubrication system of a four cylinder gasoline engine are illustrated system in this paper. In development process of engine lubrication system, parts of failure cases are related with oil pull over and oil churning phenomenon. The crankcase & head system pressure by oil churning phenomenon are gradual increased. It cause oil pull over phenomenon at engine breather line and oil over-consumption. In order to improve oil reduction and oil pull over phenomenon are also considered in the developing state. For this study, the characteristics of engine lubrication system are measured at various tilting angle and drain hole sizes. In addition, the oil flow & oil quantity are tested by blow by meter and catch jar. Results are presented to stabilize the oil supply system at sever driving condition. The data from present study are available for the engine lubrication system.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.11
• /
• pp.1441-1446
• /
• 2012

An axial-piston-type hydraulic motor involves friction and leakage losses at the sliding parts, contact loss at the mechanism assembly parts, volumetric loss caused by the pressure drop, housing oil churning loss and compressibility from the hydraulic oil pipe resistance, etc. the friction and volumetric loss at the hydrostatic bearing between the piston shoe and the swash plate rotating at high speed and having an oil film gap of 8-15 ${\mu}m$ strongly affects the total efficiency of the hydraulic motor. In this study, a variable swash-plate-type hydraulic piston motor operating under a maximum pressure of 35 MPa, maximum speed of 2,500 rpm, and displacement of 320 cc/rev is tested to verify the optimal ratio of the hydrostatic bearing which is closely related to the hydraulic motor performance.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.1
• /
• pp.1-10
• /
• 2007

In this paper, we focus on churn analysis for the first successful candidates in the entrance examination on 2006 year using Clementine, data mining tool. The goal of this study is to apply decision tree including C5.0 and CART algorithms, neural network and logistic regression techniques to predict a successful candidate churn. And we analyze the churning and nochurning successful candidates and why the successful candidates churn and which successful candidates are most likely to churn in the future using data from entrance examination data of K university on 2006 year.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2000.10a
• /
• pp.310-313
• /
• 2000

This paper develops a model of customer satisfaction in the mobile telecommunication services. We examine the relationships among customers'overall satisfaction and underlying dimensions； perceived service quality, service value, and brand image. Variables related to customer satisfaction and dissatisfaction are derived from customer critical incidence survey. The model is estimated with multi-variate data analysis. Results indicate that the (1) technical service quality is the main driver of customer overall satisfaction, (2) some peripheral services are rapidly evolving into the core services of mobile telecommunications, and (3) the current policy of service providers does not focus on customer satisfaction but on establishing churning barrier by increasing switching costs.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.06a
• /
• pp.421-444
• /
• 2001

최근 데이터 마이닝 기법이 주목받고 있는 이유 중의 가장 큰 이유는 자사가 보유하고 있는 고객의 특성을 파악함으로써 기존의 고객을 효과적으로 유지·관리할 수 있도록 지원하기 때문이다. 특히 고객 보유율 5% 신장이 수익률 120% 증대를 가져오는 것으로 보고되고 있는 신용카드 업계에서는 신규고객을 확보하는 것 만큼 기존 고객을 유지·관리하는 것이 중요하다. 특히, 신용카드를 발급 받고 거의 사용하지 않은 고객이나 쉽게 이탈하는 고객을 판별하는 것은 신용카드사의 입장에서는 비용절감 차원에서 매우 중요하다. 그러나 아직까지 어떠한 속성을 보유하고 있는 고객이 쉽게 이탈하는지를 판별할 수 있는 연구는 거의 진행되지 않았다. 이에 본 인구에서는 데이터마이닝 기법 중 널리 알려진 인공신경망, 로지스틱 회귀분석, C5.0 방법을 이용하여 신용카드 시장에서의 고객현황에 대하여 분석하고자 한다. 이를 위하여 본 연구에서는 모 신용카드사의 최근 4년간 (97넌 3월 이후) 가입고객 및 이탈고객을 대상으로 실증분석을 실시하였다. 분석결과 신용카드 시장에서 카드를 지속적으로 보유하고 있는 고객과 이탈하는 고객을 구분하는 속성이 존재함을 발견하였고, 이를 바탕으로 신용카드사가 수립해야 할 마케팅 전략을 제시하였다.

• Industrial Engineering and Management Systems
• /
• v.13 no.4
• /
• pp.454-462
• /
• 2014

Retention of possible churning customer is one of the most important issues in customer relationship management, so companies try to predict churn customers using their large-scale high-dimensional data. This study focuses on dealing with large data sets by reducing the dimensionality. By using six different dimension reduction methods-Principal Component Analysis (PCA), factor analysis (FA), locally linear embedding (LLE), local tangent space alignment (LTSA), locally preserving projections (LPP), and deep auto-encoder-our experiments apply each dimension reduction method to the training data, build a classification model using the mapped data and then measure the performance using hit rate to compare the dimension reduction methods. In the result, PCA shows good performance despite its simplicity, and the deep auto-encoder gives the best overall performance. These results can be explained by the characteristics of the churn prediction data that is highly correlated and overlapped over the classes. We also proposed a simple out-of-sample extension method for the nonlinear dimension reduction methods, LLE and LTSA, utilizing the characteristic of the data.

• The Journal of Industrial Distribution & Business
• /
• v.13 no.2
• /
• pp.45-57
• /
• 2022

Purpose: This paper examines whether or not universal banking operating in the asset management business tend to IPO underpricing when they are hosting IPOs in favor of their private interests. Previous studies suggest evidence which indicates that the universal banking operating in the asset management business tend to underestimate offering prices. This paper compares and analyzes the data before and after June 2007 to examine the influence of put-back option on IPO underpricing. Research design, data, and methodology: This paper compares the underwritten prices of IPOs of universal banking with and without asset management business in Korea in order to test such tendency actually exists. Result: We can find that such tendency is not correlated with first-day stock returns but correlated with put-back options. Our paper concludes that the hypothesis that "the universal banking's subsidiary asset management business influences the IPO underpricing" is found to be statistically insignificant. Conclusion: According to our analysis, it cannot be concluded that the interests of operating asset management do not conflict with the ones of underwriting business. However, it is so possible that the asset management companies try to harm the customers' interests, for instances churning and stuffing, it is necessary to scrutinize their behaviors and review the related regulations.