• 한국인터넷방송통신학회논문지
• /
• 제12권2호
• /
• pp.61-68
• /
• 2012

최근 디지털 컨텐츠와 컨텐츠 사용자의 기하 급수적인 증가와 함께 recommender 시스템이 주목을 받으며 많은 응용 프로그램에 적용되고 있는 가운데, recommender 시스템의 확장성과 대체적으로 이와 반비례하는 정확성이 이슈가 되고 있다. 본 논문에서는 recommender 시스템 모델 중 하이브리드 모델의 매트릭스를 제거하고 아이템의 특성을 정하기 위해 클러스터링 기술을 사용한 Scalable Hybrid Recommender System을 제안한다. 제안된 모델은 recommender 시스템의 확장성과 정확성을 향상시키기 위해서 아이템에 대한 사용자의 평가 정보, demographic 정보와 구체적인 시간 정보를 사용한다. Reduction 기술 사용을 통해 Item-feature 매트릭스의 사이즈를 축소하고, 사용자 demographic 정보를 사용하여 temporal aware hybrid user model을 만든 후, 비슷한 정보를 가진 사용자간 클러스터링을 통해, 가장 유사한 정보를 가진 사용자들을 추출하여, 사용자간 정보를 비교함으로써 사용자가 원하는 아이템의 특성을 예상하고 사용자에게 N개의 아이템을 추천함으로써, 기존의 recommender 시스템보다 더욱 향상된 결과를 도출해 낼 수 있는 알고리즘을 제시하였다.

• Journal of Information Technology Applications and Management
• /
• 제16권1호
• /
• pp.97-113
• /
• 2009

Collaborative filtering(CF) has been a very successful approach for building recommender system, but its widespread use has exposed to some well-known problems including sparsity and scalability problems. In order to mitigate these problems, we propose two novel models for improving the typical CF algorithm, whose names are ISCF(Item-Selected CF) and USCF(User-Selected CF). The modified models of the conventional CF method that condense the original dataset by reducing a dimension of items or users in the user-item matrix may improve the prediction accuracy as well as the efficiency of the conventional CF algorithm. As a tool to optimize the reduction of a user-item matrix, our study proposes genetic algorithms. We believe that our approach may relieve the sparsity and scalability problems. To validate the applicability of ISCF and USCF, we applied them to the MovieLens dataset. Experimental results showed that both the efficiency and the accuracy were enhanced in our proposed models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권7호
• /
• pp.3192-3212
• /
• 2016

With the advent and popularity of e-commerce, an increasing number of consumers prefer to order tourism products online. A recommender system can help these users contend with information overload; however, such a system is affected by the cold start problem. Online tourism destination searching is a more difficult task than others on account of its more restrictive factors. In this paper, we therefore propose a tourism destination recommender system that employs opinion-mining technology to refine user preferences and item opinion reputations. These elements are then fused into a hybrid collaborative filtering method by combining user- and item-based collaborative filtering approaches. Meanwhile, we embed an artificial interactive module in our recommender system to alleviate the cold start problem. Compared with several well-known cold start recommendation approaches, our method provides improved recommendation accuracy and quality. A series of experimental evaluations using a publicly available dataset demonstrate that the proposed recommender system outperforms existing recommender systems in addressing the cold start problem.

• Journal of Information Technology Applications and Management
• /
• 제21권4호
• /
• pp.203-223
• /
• 2014

This study proposes a novel context-aware recommender system, which is designed to recommend the items according to the customer's responses to the previously recommended item. In specific, our proposed system predicts the user's emotional state from his or her responses (such as facial expressions and movements) to the previous recommended item, and then it recommends the items that are similar to the previous one when his or her emotional state is estimated as positive. If the customer's emotional state on the previously recommended item is regarded as negative, the system recommends the items that have characteristics opposite to the previous item. Our proposed system consists of two sub modules-(1) emotion prediction module, and (2) responsive recommendation module. Emotion prediction module contains the emotion prediction model that predicts a customer's arousal level-a physiological and psychological state of being awake or reactive to stimuli-using the customer's reaction data including facial expressions and body movements, which can be measured using Microsoft's Kinect Sensor. Responsive recommendation module generates a recommendation list by using the results from the first module-emotion prediction module. If a customer shows a high level of arousal on the previously recommended item, the module recommends the items that are most similar to the previous item. Otherwise, it recommends the items that are most dissimilar to the previous one. In order to validate the performance and usefulness of the proposed recommender system, we conducted empirical validation. In total, 30 undergraduate students participated in the experiment. We used 100 trailers of Korean movies that had been released from 2009 to 2012 as the items for recommendation. For the experiment, we manually constructed Korean movie trailer DB which contains the fields such as release date, genre, director, writer, and actors. In order to check if the recommendation using customers' responses outperforms the recommendation using their demographic information, we compared them. The performance of the recommendation was measured using two metrics-satisfaction and arousal levels. Experimental results showed that the recommendation using customers' responses (i.e. our proposed system) outperformed the recommendation using their demographic information with statistical significance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.538-561
• /
• 2020

Recommender Systems (RecSys) have a major role in e-commerce for recommending products, which they may like for every user and thus improve their business aspects. Although many types of RecSyss are there in the research field, the state of the art RecSys has focused on finding the user similarity based on sequence (e.g. purchase history, movie-watching history) analyzing and prediction techniques like Recurrent Neural Network in Deep learning. That is RecSys has considered as a sequence prediction problem. However, evaluation of similarities among the customers is challenging while considering temporal aspects, context and multi-component ratings of the item-records in the customer sequences. For addressing this issue, we are proposing a Deep Learning based model which learns customer similarity directly from the sequence to sequence similarity as well as item to item similarity by considering all features of the item, contexts, and rating components using Dynamic Temporal Warping(DTW) distance measure for dynamic temporal matching and 2D-GRU (Two Dimensional-Gated Recurrent Unit) architecture. This will overcome the limitation of non-linearity in the time dimension while measuring the similarity, and the find patterns more accurately and speedily from temporal and spatial contexts. Experiment on the real world movie data set LDOS-CoMoDa demonstrates the efficacy and promising utility of the proposed personalized RecSys architecture.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제36권4호
• /
• pp.298-305
• /
• 2009

협력적 여과 시스템은 내용 기반 여과 시스템과는 대조적으로 아이템에 대한 정보를 반영하지 않으며, 또한 사용자가 자신의 흥미에 대한 정보를 제공하지 않았을 경우 추천을 할 수 없다는 단점을 갖는다. 본 논문에서는 협력적 여과 시스템의 단점을 해결하기 위하여 연관 아이템 트리를 이용한 추천 에이전트를 제안한다. 제안된 방법은 벡터 공간 모델과 K-means 알고리즘을 이용하여 사용자를 군집시킨 후 그룹의 대표 평가값을 추출한다. 다음으로, 군집된 그룹별로 아이템간의 상호정보량을 계산하여 아이템간의 연관도를 파악하며, 이를 기반으로 연관 아이템 트리를 생성한다. 이와 같이 생성한 각 그룹의 연관 아이템 트리와 그룹의 대표 평가값을 이용하여 새로운 사용자에게 아이템을 추천한다. 제안된 추천 에이전트는 사용자 정보와 아이템 정보를 병합하여 새로운 사용자에게 아이템을 추천하며, 아이템간의 유사도를 계산하기 위하여 상호정보량을 사용하고 이를 기반으로 연관 아이템 트리를 생성함으로써 초기에 아이템에 대하여 평가한 정보가 부족한 사용자에게 정확도가 높은 아이템을 추천할 수 있다는 장점을 갖는다. 제안된 방법은 MovieLens 추천 시스템의 데이터 집합을 사용하여 기존의 방법과 비교하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제18권3호
• /
• pp.619-628
• /
• 2007

This study is devoted to suggesting the norm of detection abnormal users who are inferior to the other users in the recommender system compared with estimation accuracy. To select the abnormal users, we propose the pre-filtering method by using the preference ratings to the item rated by users. In this study, the experimental result shows the possibility of detecting the abnormal users before the process of preference estimation through the prediction algorithm. And It will be possible to improve the performance of the recommender system by using this detecting norm.

• Management Science and Financial Engineering
• /
• 제11권3호
• /
• pp.137-153
• /
• 2005

Collaborative filtering-based recommendation systems make personalized recommendations based on users' ratings on products. Recommender systems must collect sufficient rating information from users to provide relevant recommendations because less user rating information results in poorer performance of recommender systems. To learn about new users, recommendation systems must first present users with an initial item list. In this study, we designed and analyzed seven selection strategies including the popularity, favorite, clustering, genre, and entropy methods. We investigated how these strategies performed using MovieLens, a public dataset. While the favorite and popularity methods tended to produce the highest average score and greatest average number of ratings, respectively, a hybrid of both favorite and popularity methods or a hybrid of demographic, favorite, and popularity methods also performed within acceptable ranges for both rating scores and numbers of ratings.

• Journal of Information Technology Applications and Management
• /
• 제24권4호
• /
• pp.1-12
• /
• 2017

Item-based collaborative filtering (IBCF) is an important technology that is widely used in recommender system of online shopping malls. It uses historical information to compute item-item similarity and make predictions. However, in offline shopping each customer's purchasing pattern can be occurred continuously and repeatedly due to time and space constraints contrast to online shopping. Those facts can make IBCF to have limitations from being applied to offline shopping malls directly. In order to improve the quality of recommendations made by IBCF in offline shopping mall, we propose an ensemble approach that considers both item-item similarity of IBCF and each customer's purchasing patterns which are modeled by item networks. Our experimental results show that this approach produces recommendation results superior to those of existing works such as pure IBCF or bestseller approaches.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제16권10호
• /
• pp.1010-1014
• /
• 2010

잡지기사 관련 상품 연계 추천 서비스는 온라인 상에서 잡지 가사의 컨텍스트를 반영하여 상품을 추천하는 서비스이다. 현재 이러한 서비스는 잡지기사와 상품에 부여되어 있는 태그 간의 유사성을 기준으로 한 추천 기술에 의존하고 있으나, 태그 부여 비용과 추천의 정확도가 높지 않은 단점이 있다. 본 논문에서는 잡지 기사 컨텍스트 관련 상품연계 추천 기술의 한 요소로서 상품이미지 정보로부터 상품의 종류를 자동으로 분류하고 이를 상품의 태그로 활용하는 방법을 제안한다. 이미지에서 추출한 시각단어(visual word)와 상품 종류 간의 고차 연관관계를 하이퍼네트워크 기법을 통해 학습하고, 학습된 하이퍼네트워크를 이용하여 상품 이미지에 한 개 이상의 태그를 자동으로 부여한다. 실제 온라인 쇼핑몰에서 사용되는 10 가지 종류의 상품 1,251개의 이미지 데이터를 기반으로, 하이퍼네트워크 이용한 상품이미지 자동 태깅 기법이 다른 기계학습 방법과 비교하여 경쟁력 있는 성능을 보여줌과 동시에, 복수개의 태그 부여를 통해 상품 이미지 태깅의 정확성이 향상됨을 보인다.