• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.9
• /
• pp.835-840
• /
• 2008

This paper proposes an enhanced recommendation technique for personalized e-commerce portal analyzing various attitudes of customer. The attitudes are classifies into three types such as "purchasing product", "adding product to shopping cart", and "viewing the product information". We implicitly track customer attitude to estimate the rating of products for recommending products. We classified user groups which have similar preference for each item using implicit user behavior. The preference similarity is estimated using the Cross Correlation Coefficient. Our recommendation technique shows a high degree of accuracy as we use age and gender to group the customers with similar preference. In the experimental section, we show that our method can provide better performance than other traditional recommender system in terms of accuracy.

• The Journal of the Korea Contents Association
• /
• v.11 no.3
• /
• pp.440-448
• /
• 2011

This study is to investigate the impact of hotel service quality and voluntary behavior upon behavior intentions by the actual analysis of four deluxe hotels in Seoul and Incheon. As a research methodology, a statistical package of SPSS 15.0 for window & Path Analysis 7.0 were used with 124 respondents. The empathy of service quality affects the voluntary behavior of the customers composed of three factors. Cooperation out of the voluntary behavior has an effect on the behavioral intentions and the rest of voluntary behavior only influences revisit. Accordingly it suggests that hotel employees should serve the customers with individual care and concern. In addition, it reveals significantly that the empathy is the main factor resulting in voluntary behavior and behavior intentions of the hotel customers.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.6
• /
• pp.237-244
• /
• 2022

In this paper, we present VAE-based recommendation using online behavior log and purchase history to overcome data sparsity and cold start. To generate a variable for customers' purchase history, embedding and dimensionality reduction are applied to the customers' purchase history. Also, Variational Autoencoders are applied to online behavior and purchase history. A total number of 12 variables are used, and nDCG is chosen for performance evaluation. Our experimental results showed that the proposed VAE-based recommendation outperforms SVD-based recommendation. Also, the generated purchase history variable improves the recommendation performance.

• The Journal of Society for e-Business Studies
• /
• v.17 no.1
• /
• pp.91-110
• /
• 2012

Recently the effort of retailers improving the efficiency of store operations by using the information technology (IT) is increasing. Among them, the analysis of the shoppers' flow in retail stores is one of the critical tasks since it is an essential part in optimizing store layout and item grouping, and in developing the customized services specialized to shoppers' classification. Agent-Based Modeling and Simulation (ABMS) is one of the most promising methods which support analyzing the shoppers' flow. In this paper, we suggested a shopper's behavior model and developed an agent-based simulator for optimizing the operations of retail stores. In order to model the shoppers' behavior, we analyzed the behavioral characteristics of shoppers based on their shopping lists, suggesting BDI-based agent models of the shoppers' behavior. The shopping agent model were suggested, which has an additional mental state, the shopper's behavioral characteristic, as well as the original mental states of the BDI theory which has beliefs, desires and Intentions. The result of this study can be used in as a preliminary study for modeling and simulation of retail stores congestion and in the end the optimization of item grouping and store layout.

• Journal of Distribution Research
• /
• v.16 no.2
• /
• pp.25-56
• /
• 2011

A shifting of marketing paradigms from transaction to relationship has shown in many studies. Although there are many researches about relationship marketing, few of them focuses on relationship marketing combined with retail mix. This study define and measure customer relationship, and find the antecedents and consequences of the customer relationship. For the research, data were collected from 540 persons who are currently customers of five branches of E-mart and Homeplus in Seoul, Korea. Data analysis was performed under the AMOS 6.0. The results are summarized as following; Firstly, the relationship among elements of retail marketing mix and the relationship quality appears significant except communication program. This finding means that communication effect decreases at some point when communication program is excessive. Secondly, the relationship of customer relationship and three factors (frequent shopping intention, up-buying intention and recommend intention) are significant. Thus, this result supports the reasoning why discount stores make an effort to improve customer relationship. Thirdly, the relationship between share of wallet and two factors (frequent shopping intention and recommend intention) appears insignificant. Fourthly, the relationship between share of wallet and up-buying intention is significant. This result implies that up-buying intention is an important factor for discount stores, because up-buying intention is directly linked to financial performance of discount stores. Finally, the direct path between customer relationship and share of wallet is significant relation. For this reason, customer relationship should be managed consistently by discount stores.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.53-62
• /
• 2020

Product recommendation services that have been researched recently are only recommended through the customer's product purchase history. In this paper, we propose the digital signage service through customers' behavior pattern analysis that is recommending through not only purchase history, but also behavior pattern that customers take when choosing products. This service analyzes customer behavior patterns and extracts interests about products that are of practical interest. The service is learning extracted interest rate and customers' purchase history through the Wide & Deep model. Based on this learning method, the sparse vector of other products is predicted through the MF(Matrix Factorization). After derive the ranking of predicted product interest rate, this service uses the indoor signage that can interact with customers to expose the suitable advertisements. Through this proposed service, not only online, but also in an offline environment, it would be possible to grasp customers' interest information. Also, it will create a satisfactory purchasing environment by providing suitable advertisements to customers, not advertisements that advertisers randomly expose.

• Culinary science and hospitality research
• /
• v.17 no.3
• /
• pp.47-64
• /
• 2011

This research try to find the strategic implication through the importance-performance analysis for the customers who visited local Jeonju-Bibimbap restaurants. It also investigates the effect of the selection attribute of the restaurants on customer satisfaction and behavior intention as well as how customer satisfaction affects behavior intention. The survey was conducted targeting those who visited the local restaurants in Jeonju and had Jeonju-Bibimbap, and 251 copies of the questionnaire were used for the final analysis. As a result, the properties 'Environmental cleanliness' and 'Convenience of reservations' in IPA are probed as 'improvement needed as soon as possible'; the 'food(p<0.01)' and 'service(p<0.05)' factors significantly affect customer satisfaction; the 'physical environment(p<0.01)' and 'service(p<0.05)' factors have significant effect on behavior intention; lastly, it has also been found true that customer satisfaction significantly influences behavior intention(p<0.001).

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.6
• /
• pp.143-158
• /
• 2020

This study examines the effect of VMD (Visual merchandising) of unmanned stores and the affordance of unmanned systems on a customer's value and intention of revisit. The proposed research model and developed hypotheses were tested using structural equations modeling based on data collected from 297 customers with experience in unmanned stores. The results of the study confirm the positive effects of the unmanned system's affordance and unmanned stores' VMD on customer value. In addition, there is a positive relationship between a customer's value and intention of revisit. The study provides valuable insights into the sustainability of unmanned stores after post-COVID 19 and the importance of developing unmanned stores' VMD and affordance.

• Proceedings of the Korea Contents Association Conference
• /
• 2011.05a
• /
• pp.245-246
• /
• 2011

본 연구의 목적은 스크린골프장 이용고객의 라이프스타일이 선택속성과 고객만족 및 재구매행동과의 인과관계를 규명하고자 하는 것이다. 본 연구의 연구대상은 2010년 3월 1일부터 2010년4월 30일까지 약 2개월간 부산 경남지역에 소재하고 있는 스크린골프장 10곳의 이용고객을 모집단으로 선정하였으며, 한 곳당 40부씩 총 400부를 직접 업체를 방문하여 배포하고 최종 332명을 표집하였으며, 표본 추출방법은 편의표본추출법을 사용하였고 설문에 대한 응답은 자기평가기입법을 채택하였다. 이들 설문지 중 신뢰성이 떨어진다고 판단되는 42명의 설문지를 제외하고 총 290명을 유효 표본으로 선정하여 본 연구의 자료로 이용하였다. 본 연구에서는 SPSS Window 12.0 통계 패키지를 이용하여 요인분석과 신뢰도분석, 빈도 분석, 회귀분석을 실시하였다. 연구결과를 보면 다음과 같다. 첫째, 스크린골프장 이용고객의 라이프스타일이 선택속성에 유의한 영향을 미치는 것으로 나타났다. 둘째, 스크린골프장 이용고객의 선택속성은 고객만족에 유의한 영향을 미치는 것으로 나타났다. 셋째, 스크린골프장 이용고객의 선택속성은 재구매행동에 유의한 영향을 미치는 것으로 나타났다.

• Proceedings of the EASDL Conference
• /
• 2003.04a
• /
• pp.74-75
• /
• 2003

1988년 서울올림픽 이후로 외국계열 패스트푸드(Fast Food: FF)와 패밀리레스토랑(Family Restaurant: FR)브랜드들의 국내시장 진출이 가속화됨에 따라 외식업체 유형별 고객들의 외식행동 특성에 대해 연구하는 것은 의미 있는 일이라 하겠다. 본 연구는 고객들의 인구통계학적 특성에 따라 4가지 유형의 외식업체별 고객들의 외식행동에 차이가 있는지를 비교하는 것을 목적으로 했다. 모집단은 전국의 국내 및 해외브랜드 외식업체를 이용한 경험이 있는 고객들 314명을 대상으로 해외브랜드 2가지 유형[FF와 FR]과 국내브랜드 2가지 유형[프랜차이즈(FC) 업체와 일반대중식당(GR)]을 구분하여 외식행동에 관해 자기기입방식으로 설문을 실시하였고 수집된 자료는 빈도분석과 교차분석을 실시하였다.(중략)