• 한국조리학회지
• /
• 제12권2호
• /
• pp.73-87
• /
• 2006

The purpose of this study is to investigate if recommendation selling (methods of recommendation selling, a key word used for recommendation, and employee attitude) influences the customers' menu decision. The results of the study are as follows: 'Menu picture' and 'explanation by word' among the tools used by employees for recommendation were found to influence customers' menu decision. The words such as 'new menu' and 'special only today' used by employees for recommendation were found to influence customers' menu decision. Employees' attitude elements such as 'interesting explanation', 'dressed up tidy', 'strong intention', and 'patience' were found to influence customer's menu decision. 'Recommendation selling' in the food and beverage industry means 'employees help customers make a good decision on food and beverage service'. This study makes an important contribution to the food industry in terms of providing substantial marketing strategies.

• 복식문화연구
• /
• 제17권3호
• /
• pp.367-382
• /
• 2009

The aim of the current study was to investigate the impact of store attribute satisfaction on intentions of revisit and recommendation among clothing consumers. The data were collected from 319 consumers through survey and frequency analysis, reliability analysis, factor analysis, and multiple regression analysis were used to obtain results. The findings were as follows: 1. From factor analysis, seven factors were distracted: Fact 1(brand and price), Fact 2(store's facility and environment), Fact 3(product), Fact 4(transportation convenience and access), Fact 5(selling and advertisement), Fact 6(store's atmosphere), and Fact 7(salesman's service). 2. Four factors had statistically significant influence on overall satisfaction of clothing consumers. The most influential factor was Fact 2(store's facility and environment) and Fact 5(selling and advertisement), Fact 1(brand and price), and Fact 4(transportation convenience and access) showed their effects on overall satisfaction in an hierarchical rank-order following Fact 2. 3. Four factors such as Fact 2(store's facility and environment), Fact 1(brand and price), Fact 4(transportation convenience and access) and Fact 5(selling and advertisement) in an hierarchical rank-order from Fact 1 had statistically significant impact on intentions of revisit. 4. Six factors such as Fact 1(brand and price), Fact 2(store's facility and environment), Fact 3(product), Fact 5(selling and advertisement), Fact 6(store's atmosphere), and Fact 7(salesman's service) in an hierarchical rank-order from Fact 1 had statistically significant influence on the intention of recommendation. 5. The results further showed that among seven factors, Fact 1(brand and price), 'Fact 2(store's facility and environment), and Fact 5(selling and advertisement) had impact on both the intention of revisit and the intention of recommendation.

• 정보처리학회논문지D
• /
• 제11D권7호
• /
• pp.1537-1542
• /
• 2004

디지털콘텐트는 복제가 용이하고 원본과 복사본이 동일하다는 특성 때문에 불법적인 복제와 유통의 방지를 통한 저작권의 보호에 어려움이 있다. 근래에는 웹을 기반으로 한 각종 디지털콘텐트 서비스 시스템이 상용화되고 있으며, 이것이 안정된 수익 모델로서 발전하기 위하여 적절한 저작권 보호 기술이 요구된다. 일반적으로 웹 기반의 저작권 보호를 위해서는 디지털 콘텐트의 암호화를 통한 안전한 전송 방법을 사용한다. 이때 암호화된 디지털 콘텐트의 크기는 증가하여 실행과정에 필요한 시간을 증가시킨다. 따라서 실행시간과 안전성을 고려한 시스템의 설계가 필요하다. 본 연구에서는, 디지털콘텐트의 저작권 관리 기술을 기반으로 부분 암호화를 통해 수행시간과 안전성을 고려한 디지털콘텐트 전송 시스템을 설계하였다. 또한 분석을 통해 제안시스템의 성능을 평가하였다.

• 한국컴퓨터정보학회논문지
• /
• 제15권12호
• /
• pp.227-235
• /
• 2010

이 논문은 RFM 기법과 연관성 분석을 이용한 개인화된 전자상거래 추천 시스템을 제안한다. 제안된 전자상거래 추천시스템은 사용자의 평가 자료에 의존하지 않고 묵시적인(Implicity)방법을 이용하여 고객정보와 구매이력 정보를 기반으로 RFM(Recency, Frequency, Monetary) 기법을 이용한 고객 세분화와 교차판매(cross-sell)관계를 찾는 연관성 분석을 이용한 개선된 시스템이다. 또한 고객군별 구매특성 분석을 통하여 효율적인 마케팅 전략과 고객관계관리(CRM: Customer Relationship Management)방법을 제시한다. 현업에서 사용하는 데이터 셋을 구성하여 실험 및 평가를 통해서 효용성을 입증 및 평가하여 일대일 웹 마케팅을 실현하였다.

• Asia pacific journal of information systems
• /
• 제16권4호
• /
• pp.217-238
• /
• 2006

In this study, we propose a virtual community recommendation model based on user behavioral models. It is designed to recommend optimal virtual communities for an active user by applying case-based reasoning (CBR) using behavioral factors suggested in the technology acceptance model (TAM) and its extensions. Also, it is designed to filter its case-base by considering the user's needs type before applying CBR. To test the usefulness of our model, we conduct two-step validation - experimental validation for the collected data, and survey validation for investigating the actual satisfaction level. Experimental results show that our model presents effective recommendation results in an efficient way. In addition, they also show that the information on the user's needs type may generate opportunities for cross-selling other commercial items.

• Journal of Information Processing Systems
• /
• 제16권2호
• /
• pp.494-507
• /
• 2020

This study proposed the movie recommendation system based on the user's personal information and movies rated using the method of k-clique and normalized discounted cumulative gain. The main idea is to solve the problem of cold-start and to increase the accuracy in the recommendation system further instead of using the basic technique that is commonly based on the behavior information of the users or based on the best-selling product. The personal information of the users and their relationship in the social network will divide into the various community with the help of the k-clique method. Later, the ranking measure method that is widely used in the searching engine will be used to check the top ranking movie and then recommend it to the new users. We strongly believe that this idea will prove to be significant and meaningful in predicting demand for new users. Ultimately, the result of the experiment in this paper serves as a guarantee that the proposed method offers substantial finding in raw data sets by increasing accuracy to 87.28% compared to the three most successful methods used in this experiment, and that it can solve the problem of cold-start.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 추계학술발표대회
• /
• pp.1042-1045
• /
• 2014

Recently several recommender systems have been developed in a variety of applications, but providing accurate recommendations that match the preferences and constraints of various users is quite challenging. This paper presents a method of recommending digital products based on the past preference of a user on the price, rating and selling volume of a product. Experimental results of the method with actual data of Amazon showed that the average accuracy of the recommendations made by the method is 85%. Although the results are preliminary, the method is potentially capable of making more accurate personalized recommendations than existing methods.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2004년도 추계학술대회
• /
• pp.203-210
• /
• 2004

Due to the explosion of e-commerce, recommender systems are rapidly becoming a core tool to accelerate cross-selling and strengthen customer loyalty. There are two prevalent approaches for building recommender systems - content-based recommending and collaborative filtering. Collaborative filtering recommender systems have been very successful in both information filtering domains and e-commerce domains, and many researchers have presented variations of collaborative filtering to increase its performance. However, the current research on recommendation has paid little attention to the use of time related data in the recommendation process. Up to now there has not been any study on collaborative filtering to reflect changes in user interest. This paper proposes dynamic fuzzy clustering algorithm and apply it to collaborative filtering algorithm for dynamic recommendations. The proposed methodology detects changes in customer behavior using the customer data at different periods of time and improves the performance of recommendations using information on changes. The results of the evaluation experiment show the proposed model's improvement in making recommendations.

• Asia pacific journal of information systems
• /
• 제12권3호
• /
• pp.71-88
• /
• 2002

In this paper, intelligent marketing and merchandising methods utilizing data mining and Web mining techniques are proposed for online retailers to survive and succeed in gaining competitive advantage in a highly competitive environment. The first part of this paper explains the procedures of one-to-one marketing based on customer relationship management(CRM) techniques and personalized recommendation lists generation. The second part illustrates Web merchandising methods utilizing data mining techniques, such as association and sequential pattern mining. We expect that our Web marketing and merchandising methods will both provide a currently operating Internet shopping mall with more selling opportunities and give more useful product information to customers.

• Journal of information and communication convergence engineering
• /
• 제17권1호
• /
• pp.41-48
• /
• 2019

In recent years, sentiment analysis research has become popular. The research results of sentiment analysis have achieved remarkable results in practical applications, such as in Amazon's book recommendation system and the North American movie box office evaluation system. Analyzing big data based on user preferences and evaluations and recommending hot-selling books and hot-rated movies to users in a targeted manner greatly improve book sales and attendance rate in movies [1, 2]. However, traditional machine learning-based sentiment analysis methods such as the Classification and Regression Tree (CART), Support Vector Machine (SVM), and k-nearest neighbor classification (kNN) had performed poorly in accuracy. In this paper, an improved kNN classification method is proposed. Through the improved method and normalizing of data, the purpose of improving accuracy is achieved. Subsequently, the three classification algorithms and the improved algorithm were compared based on experimental data. Experiments show that the improved method performs best in the kNN classification method, with an accuracy rate of 11.5% and a precision rate of 20.3%.