• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 컴퓨터소사이어티 추계학술대회논문집
• /
• pp.175-178
• /
• 2003

Two defects have been pointed out in existing user-based collaborative filtering such as sparsity and scalability, and the research has been also made progress, which tries to improve these defects using item-based collaborative filtering. Actually there were many results, but the problem of sparsity still remains because of being based on an explicit data. In addition, the issue has been pointed out. which attributes of item arenot reflected in the recommendation. This paper suggests a recommendation method using nave Bayesian algorithm in hybrid user and item-based collaborative filtering to improve above-mentioned defects of existing item-based collaborative filtering. This method generates a similarity table for each user and item, then it improves the accuracy of prediction and recommendation item using naive Bayesianalgorithm. It was compared and evaluated with existing item-based collaborative filtering technique to estimate the accuracy.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2006년도 춘계학술대회
• /
• pp.344-353
• /
• 2006

Nowadays many people participate in online communities for information sharing. But most recommender systems are designed for personalization of individual user, so it is necessary to develop a recommendation procedure for group users, such as participants in online communities. This paper proposes a group recommender system to recommend books for group users in online communities. For such a purpose, we suggest a group recommendation procedure consisting of two phases. The first phase is to generate recommendation list for 'big user' using collaborative filtering, and the second phase is to remove irrelevant books among previous list reflecting the preference of each individual user. The procedure is explained step by step with an illustrative example. And this procedure can potentially be applied to other domains, such as music, movies and etc.

• 한국콘텐츠학회논문지
• /
• 제13권11호
• /
• pp.11-20
• /
• 2013

최근 SNS(Social Network Service)의 사용이 급격히 증가함에 따라 추천 기법에 대한 연구가 활발히 진행되고 있다. 추천 기법은 사용자들이 좋아하거나 필요할만한 다양한 서비스들을 실시간으로 제공하는 기법이다. 그 중 그룹 추천은 사용자의 성향 정보를 기반으로 적합한 그룹을 제공해 주는 기법이다. 본 논문에서는 소셜 네트워크 환경에서 사용자 프로필 및 협업 필터링을 이용한 그룹 추천 기법을 제안한다. 제안하는 기법은 사용자의 최근 그룹 활동 정보를 수집하여 프로필 정보를 갱신하기 때문에 기존의 정적프로필 기반의 그룹 추천 기법의 최근 사용자의 성향을 고려하지 못하는 문제점을 해결한다. 또한, 협업 필터링을 통해 그룹 내 자신의 성향과 비슷한 사용자들의 프로필 데이터를 활용하여 그룹을 추천함으로써 사용자에게 좀 더 다양한 그룹을 제공한다. 성능 평가 결과 제안하는 기법이 기존 기법에 비해 사용자의 변화하는 성향이 충분히 반영된 다양한 그룹 추천이 이루어지는 것을 확인 할 수 있었다.

• 한국의류학회지
• /
• 제47권4호
• /
• pp.711-728
• /
• 2023

This study aims to validate the user experience associated with the personalized recommendation systems of fashion vertical platforms. The investigation focused on women aged 18 to 30 with prior experience using personalized fashion recommendation systems. The collected data were analyzed using SPSS 26.0 and AMOS 26.0, and the outcomes can be summarized as follows. Firstly, the diversity and usefulness of information quality exerted a positive effect on use satisfaction. Secondly, the affirmative impact of the reliability of system quality on user satisfaction was established, although stability was not confirmed. Thirdly, the study identified a favorable connection between ease-of-use of service quality and user satisfaction, while the influence of tangibles was unsubstantiated. Fourthly, the degree of self-reference was found to have a positive effect on user satisfaction. Fifthly, a constructive relationship emerged between user satisfaction and both continuous-use intention and recommendation intention. Lastly, there was a significant difference in the magnitude of the effect of ease-of-use on satisfaction according to self-regulatory focus. The findings of this study hold the potential to enhance the explanatory and predictive power of the field of consumer behavior within the novel shopping landscape of fashion vertical platforms.

• 한국콘텐츠학회논문지
• /
• 제17권2호
• /
• pp.404-414
• /
• 2017

스마트폰의 보급과 온라인 소셜 네트워크 서비스의 발전으로 사용자들은 많은 콘텐츠를 생산하거나 서로 공유한다. 이로 인해 사용자는 자신이 원하지 않는 콘텐츠를 받아보거나 소비함으로써 많은 시간을 소요하게 된다. 이와 같은 문제를 해결하기 위해 소셜 네트워크 사용자에게 적합한 콘텐츠를 추천하기 위한 기법들이 활발하게 연구되고 있다. 본 논문에서는 온라인 소셜 네트워크 사용자에게 협업 필터링을 이용하여 적합한 콘텐츠를 추천하는 기법을 제안한다. 제안하는 기법은 추천의 정확성을 낮추는 사용자의 데이터를 제거하기 위해서 사용자 신뢰도를 고려한다. 사용자의 신뢰도는 온라인 소셜 네트워크의 사용자 행위를 분석해서 도출한다. 사용자의 신뢰도를 다양한 관점에서 평가하기 위해서 기존기법에서 사용하지 않았던 사용자 행위들을 수집해서 사용한다. 다양한 성능평가를 통해 제안하는 기법이 기존 기법보다 우수함을 보인다.

• 한국컴퓨터정보학회논문지
• /
• 제15권8호
• /
• pp.141-148
• /
• 2010

모바일 단말기에서 사용자의 상황을 고려하고 사용자의 취향이나 특성을 반영하여 정보를 찾아주거나 추천하는 서비스 시스템은 개념적인 정보만을 제한적으로 추천한다. 또한 사용자의 특성에 따른 정보 선호도를 제공하지 않으므로 정확한 정보 추천의 어려운 단점이 있다. 따라서 본 논문에서는 사용자 특성에 따른 선호도를 고려하여 정확한 상황 정보를 추천 할 수 있는 개선된 k-means 알고리즘을 적용하여 사용자 특성에 따른 선호도 추천 시스템을 제안하였다. 본 연구에서는 사용자 특성에 따른 선호도를 상관 계수를 이용하여 구하고 사용자의 특성 선호도를 개선된 k-means 알고리즘을 이용하여 추천하였다. 제한적인 개념의 정보만을 제공하던 시스템에서 사용자의 특성에 따른 정보 선호도를 제공하여 정확한 정보를 추천하므로 제한된 정보 추천의 단점을 해결하였다. 성능 실험은 기존의 서비스 시스템들과 비교하여 정확도와 재현율로 대변되는 효과성을 측정하였으며, 성능 실험 결과 정확도는 85%, 재현율은 68%로 나타났다.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.599-614
• /
• 2021

This paper proposes a digital signage system based on an intelligent recommendation model. The proposed system consists of a server and an edge. The server manages the data, learns the advertisement recommendation model, and uses the trained advertisement recommendation model to determine the advertisements to be promoted in real time. The advertisement recommendation model provides predictions for various products and probabilities. The purchase index between the product and weather data was extracted and reflected using correlation analysis to improve the accuracy of predicting the probability of purchasing a product. First, the user information and product information are input to a deep neural network as a vector through an embedding process. With this information, the product candidate group generation model reduces the product candidates that can be purchased by a certain user. The advertisement recommendation model uses a wide and deep recommendation model to derive the recommendation list by predicting the probability of purchase for the selected products. Finally, the most suitable advertisements are selected using the predicted probability of purchase for all the users within the advertisement range. The proposed system does not communicate with the server. Therefore, it determines the advertisements using a model trained at the edge. It can also be applied to digital signage that requires immediate response from several users.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권11호
• /
• pp.3050-3063
• /
• 2023

Recommendation systems provide personalized products or services to online users by mining their past preferences. Collaborative filtering is a popular recommendation technique because it is easy to implement. However, with the rapid growth of the number of users in recommendation systems, collaborative filtering suffers from serious scalability and sparsity problems. To address these problems, a novel collaborative filtering recommendation algorithm is proposed. The proposed algorithm partitions the users using affinity propagation clustering, and searches for k nearest neighbors in the partition where active user belongs, which can reduce the range of searching and improve real-time performance. When predicting the ratings of active user's unrated items, mean deviation method is used to impute values for neighbors' missing ratings, thus the sparsity can be decreased and the recommendation quality can be ensured. Experiments based on two different datasets show that the proposed algorithm is excellent both in terms of real-time performance and recommendation quality.

• 대한인간공학회지
• /
• 제23권3호
• /
• pp.1-12
• /
• 2004

In recent years, with the advent of e-Commerce the need for personalized services and one-to-one marketing has been emphasized. To be successful in increasingly competitive Internet marketplace, it is essential to capture customer loyalty. In this paper, we provide an intelligent agent approach to incorporate human sensibility into an one-to-one recommendation service in cyber shopping mall. Our system exploits human sensibility ergonomics and on-line preference matching technologies to tailor to the customer the suggestion of goods and the description of store catalog. Customizing the system`s behavior requires the parallel execution of several tasks during the interaction （e. g., identifying the customer`s emotional preference and dynamically generating the pages of the store catalog）. The recommendation agent system composed of five modules including specialized agents carries on these tasks. By presenting goods that are consistent with user interests as well as user sensibility, the accuracy and satisfaction of the recommendation service may be improved.

• Journal of Information Technology Applications and Management
• /
• 제26권5호
• /
• pp.57-65
• /
• 2019

Recommendation Systems are information technologies that E-commerce merchants have adopted so that online shoppers can receive suggestions on items that might be interesting or complementing to their purchased items. These systems stipulate valuable assistance to the user's purchasing decisions, and provide quality of push service. Traditionally, Recommendation Systems have been designed using a centralized system, but information service is growing vast with a rapid and strong scalability. The next generation of information technology such as Cloud Computing and Big Data Environment has handled massive data and is able to support enormous processing power. Nevertheless, analytic technologies are lacking the different capabilities when processing big data. Accordingly, we are trying to design a conceptual service model with a proposed new algorithm and user adaptation on dynamic recommendation service for big data environment.