• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1561-1566
• /
• 2017

Due to the advances in machine learning and artificial intelligence technologies, many new services have become available. Among such services, recommendation systems have already been successfully applied to commercial services and made profits as in online shopping malls. Most recommendation algorithms in commercial services are based on content analysis or explicit feedback rates as in movie recommendations. However, many online shopping malls have difficulties in content analysis or are lacking explicit feedbacks on their items, which results in no recommendation system for their items. Even for such service systems, user log data is easily available, and if recommendations are possible with such log data, the quality of their service can be improved. In this paper, we extract implicit feedback like click information for items from log data and provide a recommendation system based on the implicit feedback. The proposed system is applied to a real in-service online shopping mall.

• Information Systems Review
• /
• v.18 no.2
• /
• pp.59-77
• /
• 2016

Although various recommendation techniques have been applied to the e-commerce market, few studies compare the intent to use these techniques from the customer's perspective. In this paper, we conduct a comparative analysis of customers' intention to use five recommendation techniques widely adapted by online shopping malls and focus on the differences in purchasing electronic goods and apparel products. The recommendation techniques are as follows: best-seller recommendation, merchandiser recommendation, content-based recommendation, collaborative filtering recommendation, and social recommendation. Additionally, we examine which factors influence customer intent to use the recommendation services. Data were collected through a survey administered to 220 e-commerce users with prior experience with recommendation services. Collected data were examined using analysis of variance and regression analysis. Results indicate statistically significant differences in customers' intention to use recommendation services according to the recommendation technique. In particular, the best-seller recommendation technique is preferred when purchasing electronic goods, whereas the content-based recommendation technique is preferred for apparel purchases. Factors such as personal characteristics and personality, purchasing tendency, as well as perception of the product or recommendation service affect a customer's intention to use a recommendation service. However, the influence of these factors varies depending on the recommendation technique. This study provides guidelines for companies to adopt appropriate recommendation techniques according to product categories and personal characteristics of customers.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.05a
• /
• pp.258-265
• /
• 2005

전자상거래의 확산에 따라 인터넷 쇼핑몰에서의 구매활동은 일반적인 현상이 되었다. 그 결과, 유사한 업종이나 업태의 인터넷 쇼핑몰이 범람하게 되었고 업체들 간의 경쟁도 심화되어 차별화된 서비스를 제공하지 않는 업체는 도태되기 쉬운 상황이다. 본 연구에서는 치열한 경쟁환경 하에서 인터넷 쇼핑몰의 차별화된 마케팅 서비스의 수단으로써 이용되고 있는 상품추천시스템의 개선된 모형을 제시하고자 한다. 본 연구에서 제안하는 모형은 전역 최적화 기법 중의 하나인 유전자 알고리즘을 데이터 마이닝의 도구로 활용한 인터넷 쇼핑몰에서의 개인화된 상품추천시스템 모형이다. 유전자 알고리즘은 추출하기가 어려운 소비자의 성향을 데이터를 통해 추출하고 이에 맞는 상품군을 선택할 수 있도록 해주는 최적화 기법으로 상품추천시스템의 추천엔진으로써 유용할 것으로 기대된다. 본 연구에서는 제안한 유전자 알고리즘에 기반한 추천 규칙들이 장착된 웹 기반의 개인화된 상품추천시스템의 프로토타입을 개발하고 이에 대한 실제 사용자들의 이용 만족도를 확인함으로써 본 연구에서 제안한 방법론의 유용성을 확인하고자 한다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.514-518
• /
• 2019

기존의 교차 도메인 추천은 일반적으로 서로 다른 도메인 데이터의 지식 결합이나 지식 공유를 바탕으로 진행된다. 이러한 방식들은 최소 한 개 이상의 도메인 데이터가 필요해서 모든 도메인의 피드백 데이터가 없는 실제 서비스 초기 상황에는 적합하지 않을 수 있다. 따라서 본 논문에서는 서비스 초반 모든 도메인의 피드백 데이터가 없고 콘텐츠 데이터만 존재하는 상황에서 교차 도메인 추천 시스템을 효과적으로 시작하기 위해 텍스트 임베딩, 클러스터링, 프로파일링 및 콘텐츠 기반 필터링을 활용한 추천 시스템 구성을 제안하고자 한다. 평가를 위해 여행지, 지역 축제, 공연을 포함하는 문화 관광 데이터와, 이에 대한 사용자 프로파일링 결과를 바탕으로 추천을 진행하였다. 그 결과, 콘텐츠 임베딩에 대한 유사도를 시각화하여 교차 도메인 아이템 간 유사성을 확인할 수 있었고, 사용자별 추천 결과를 통해 제안한 교차 도메인 추천 시스템이 유의미하게 동작함을 보였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.95-101
• /
• 2012

As the influence of social networking services across the societies becomes greatly higher, many of the domestic agencies are trying to communicate with users through the introduction of social networking services. In this paper, we present a reliable exhibition-related contents recommendation service to combine social networking service concept with the customized contents recommendation method we previously proposed. The proposed service may effectively and reliably recommend its users exhibition-related contents by exploiting their relationships in the social networks compared with the existing ones.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.526-527
• /
• 2020

본 연구는 대중교통 활용도를 높이고자 효율적인 버스 환승지 추천 서비스를 설계한다. 제주데이터 허브에서 입수한 승하차데이터를 처리하여 승객수와 버스의 정류장 도착시간 등을 예측함은 물론 인터넷 연결을 통해 버스정보시스템과 연동하여 현재의 교통상황을 실시간으로 입수하여 효율적인 환승지를 추천한다. 승객은 변동되는 교통상황에 따라 이동중에도 더 좋은 환승 노선으로 변경할 수 있으며 데이터센터 관점에서는 축적되고 있는 버스 데이터의 활용도도 높일 수 있다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.3
• /
• pp.407-413
• /
• 2020

Participating in exhibitions is one of the major activities for tourists. When selecting their next travel destination after participating in an event, they use map services and social network services, such as blogs, to obtain information about tourist attractions. The map services are location-based recommendations, because they can easily retrieve information regarding nearby places. Blogs contain informative content about tourist attractions, thereby providing content-based recommendations. However, few services consider both location and content. In location-based recommendations, tourist attractions that are not related to the content of the event attended might be recommended. Content-based recommendation has a disadvantage in that events located at a distance might get recommended. We propose an algorithm that considers both location and content, based on information from the Korea Tourism Organization's Linked Open Data (LOD), Wikipedia, and a Korean dictionary. By extracting nouns from the description of a tourist attraction and then comparing them with nouns about other attractions, a content-based relationship is determined. The distance to the event is calculated based on the latitude and longitude of each tourist attraction. A weight selected by the user is used for linear combination with the content-based relationship to determine the preference order of the recommendations.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.15-28
• /
• 2015

As personal devices and pervasive technologies for interacting with networked objects continue to proliferate, there is an unprecedented world of scattered pieces of contextualized information available. However, the explosive growth and variety of information ironically lead users and service providers to make poor decision. In this situation, recommender systems may be a valuable alternative for dealing with these information overload. But they failed to utilize various types of contextual information. In this study, we suggest a methodology for context-aware recommender systems based on the concept of contextual boundary. First, as we suggest contextual boundary-based profiling which reflects contextual data with proper interpretation and structure, we attempt to solve complexity problem in context-aware recommender systems. Second, in neighbor formation with contextual information, our methodology can be expected to solve sparsity and cold-start problem in traditional recommender systems. Finally, we suggest a methodology about context support score-based recommendation generation. Consequently, our methodology can be first step for expanding application of researches on recommender systems. Moreover, as we suggest a flexible model with consideration of new technological development, it will show high performance regardless of their domains. Therefore, we expect that marketers or service providers can easily adopt according to their technical support.

• The KIPS Transactions:PartD
• /
• v.14D no.7
• /
• pp.707-718
• /
• 2007

Recently, much studies for providing mobile users with suitable and useful content services, LBS(Location Based Service) corresponding to the change of users' location, are actively going on. First and foremost, this is basically owing to the progress of location management technologies such as GPS, mobile communication technology and the spread of personal devices like PDA and the cellular phones. Besides, the research scope of LBS has been changed from vehicle tracking and navigation services to intelligent and personalized services considering the changing information of conditions or environment where the users' are located. For example, it inputs the information such as heavy traffic, pollution, and accidents. The query languages which effectively search the stored vehicle and environment information have been studied depending on the increase of the information utilization. However, most of existing moving object query languages are not enough to provide a recommendation service for a user, because they can not be tested and evaluated in real world and did not consider changed environment information. In order to retrieve not only a vehicle location and environment condition but also use them, we suggest a moving object query language for recommendation service and implement a moving object query process system for supporting a query language. It can process a nearest neighbor query for recommendation service which considers various attributes such as a vehicle's location and direction, environment information. It can be applied to location based service application which utilizes the recommended factors based on environmental conditions.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.11a
• /
• pp.281-282
• /
• 2014

본 연구의 목적은 과학기술정보서비스에 대한 고객만족도를 기반으로 하여 충성고객을 예측할 수 있는 모델을 구축하는 것이다. 이를 위해 정보서비스를 경험한 최근 1년이내 한국가과학기술전자도서관(NDSL : National Digital Science Library)사이트를 이용한 회원을 대상을 조사를 하였으며, 조사목적은 NDSL 서비스의 추천지수 측정을 통하여 추천, 비추천 사유를 파악하기 위함이다. 조사방법은 전화조사(Telephone Interview)로 진행하고 표본 수는 500명의 의사결정자를 대상으로 측정하였다. 고객충성도는 NPS(Net Promoter Score, 순고객추천지수) 이론에 근거하여 하였다. 연구결과 고객만족도 수준에 따라 비추천고객, 추천고객을 예측할 수 있는 모델을 구축하였다. 이와 같은 연구결과는 인터넷 등 정보의 발달로 고객의 긍정적 또는 부정적인 구전이 급속도로 노출되는 환경에서 고객의 만족도를 관리함으로써 충성고객을 확보하는데 사전 예측자료로 활용될 수 있다.