• 대한설비관리학회지
• /
• 제23권4호
• /
• pp.57-64
• /
• 2018

User-based collaborative filtering is a method of recommending an item to a user based on the preference of the neighbor users who have similar purchasing history to the target user. User-based collaborative filtering is based on the fact that users are strongly influenced by the opinions of other users with similar interests. Item-based collaborative filtering is a method of recommending an item by comparing the similarity of the user's previously preferred items. In this study, we create a recommendation model using user-based collaborative filtering and item-based collaborative filtering with consumer's consumption data. Collaborative filtering is performed by using RFM (recency, frequency, and monetary) technique with purchasing data to recommend items with high purchase potential. We compared the performance of the recommendation system with the purchase amount and the performance when applying the RFM method. The performance of recommendation system using RFM technique is better.

• Journal of Information Technology Applications and Management
• /
• 제26권6호
• /
• pp.89-101
• /
• 2019

Many researchers have been focused on designing beauty product recommendation system for a long time because of increased need of customers for personalized and customized recommendation in beauty product domain. In addition, as the application of the deep neural network technique becomes active recently, various collaborative filtering techniques based on the deep neural network have been introduced. In this context, this study proposes a deep neural network model suitable for beauty product recommendation by applying Neural Collaborative Filtering and Generalized Matrix Factorization (NCF + GMF) to beauty product recommendation. This study also provides an implementation of web API system to commercialize the proposed recommendation model. The overall performance of the NCF + GMF model was the best when the beauty product recommendation problem was defined as the estimation rating score problem and the binary classification problem. The NCF + GMF model showed also high performance in the top N recommendation.

• 한국멀티미디어학회논문지
• /
• 제25권6호
• /
• pp.819-832
• /
• 2022

Cross-domain recommender system transfers knowledge across different domains to improve the recommendation performance in a target domain that has a relatively sparse model. However, they suffer from the "negative transfer" in which transferred knowledge operates as noise. This paper proposes a novel Multiple Fusion-based Deep Cross-Domain Recommendation named MFDCR. We exploit Doc2Vec, one of the famous word embedding techniques, to fuse data user-wise and transfer knowledge across multi-domains. It alleviates the "negative transfer" problem. Additionally, we introduce a simple multi-layer perception to learn the user-item interactions and predict the possibility of preferring items by users. Extensive experiments with three domain datasets from one of the most famous services Amazon demonstrate that MFDCR outperforms recent single and cross-domain recommendation algorithms. Furthermore, experimental results show that MFDCR can address the problem of "negative transfer" and improve recommendation performance for multiple domains simultaneously. In addition, we show that our approach is efficient in extending toward more domains.

• International Journal of Computer Science & Network Security
• /
• 제21권2호
• /
• pp.148-157
• /
• 2021

The effectiveness of recommendation systems depends on the performance of the algorithms with which these systems are designed. The quality of the algorithms themselves depends on the quality of the strategies with which they were designed. These strategies differ from author to author. Thus, designing a good recommendation system means implementing the good strategies. It's in this context that several research works have been proposed on various strategies applied to algorithms to meet the needs of recommendations. Researchers are trying indefinitely to address this objective of seeking the qualities of recommendation algorithms. In this paper, we propose a new algorithm for recommending learning items. Learner performance predictions and collaborative recommendation methods are used as strategies for this algorithm. The proposed performance prediction model is based on convolutional neural networks (CNN). The results of the performance predictions are used by the proposed recommendation algorithm. The results of the predictions obtained show the efficiency of Deep Learning compared to the k-nearest neighbor (k-NN) algorithm. The proposed recommendation algorithm improves the recommendations of the learners' learning items. This algorithm also has the particularity of dissuading learning items in the learner's profile that are deemed inadequate for his or her training.

• 한국의류산업학회지
• /
• 제17권2호
• /
• pp.216-226
• /
• 2015

This study identifies factors of perceived risk of up-cycling fashion products and investigates perceived risk factors that influence consumers' trust, purchase intention, and recommendation intention towards upcycling fashion products. We also examine the relationship of trust, purchase intention, and recommendation intention for upcycling fashion products. A qualitative research method using a free narrative form and depth interview were used. The perceived risk from up-cycling fashion products generated 5 factor solutions: aesthetic risk, sanitary risk, social risk, performance risk, and economic risk. Next, 201 effective data were collected from a questionnaire survey and analyzed with SPSS 22.0. The results are summarized as follows. First, aesthetic risk and performance risk had a negative effect on products. Second, aesthetic risk and performance risk had negative influence on purchase intention for upcycling fashion products. Third, performance risk had a negative impact on recommendation intention for upcycling fashion products. Fourth, trust had positive effect on purchase intention and recommendation intention for upcycling fashion products. The results of the current study provides various theoretical and practical implications for marketers and retailers interested in up-cycling fashion products.

• 한국인터넷방송통신학회논문지
• /
• 제14권4호
• /
• pp.187-195
• /
• 2014

본 논문은 선행 연구에서 개발한 MissLess 키보드의 성능을 평가한다. MissLess 키보드는 모바일 단말기 내의 사전에 저장되는 모든 어휘에 해시 코드 값을 할당한다. 그리고, 사용자가 입력한 어휘와 일정 범위의 해시 코드를 가진 어휘를 골라내는 해시필터링, 골라낸 어휘와 입력된 어휘의 철자 유사성을 실시간으로 비교하여 유사 단어를 추려내는 철자 유사성 기반 정렬, 그리고 마지막으로 사용자의 사용 빈도가 놓은 어휘를 우선적으로 골라내는 사용자 패턴 기반 추천의 3 단계를 거쳐 어휘를 추천한다. 본 논문은 추천 알고리즘의 각 단계별로 성능 요소를 분석하고, 이들 요소가 미치는 추천 성능의 영향을 평가하고 평가된 결과를 보인다.

• 한국IT서비스학회지
• /
• 제20권3호
• /
• pp.57-73
• /
• 2021

Recently, online job websites have been activated as unemployment problems have emerged as social problems and demand for job openings has increased. However, while the online job platform market is growing, users have difficulty choosing their jobs. When users apply for a job on online job websites, they check various information such as job contents and recruitment conditions to understand the details of the job. When users choose a job, they focus on various details related to the job rather than simply viewing and supporting the job title. However, existing online job websites usually recommend jobs using only quantitative preference information such as ratings. However, if recommendation services are provided using only quantitative information, the recommendation performance is constantly deteriorating. Therefore, job recommendation services should provide personalized services using various information about the job. This study proposes a recommended methodology that improves recommendation performance by elaborating on qualitative preference information, such as details about the job. To this end, this study performs a topic modeling analysis on the job content of the user profile. Also, we apply LDA techniques to explore topics from job content and extract qualitative preferences. Experiments show that the proposed recommendation methodology has better recommendation performance compared to the traditional recommendation methodology.

• 지능정보연구
• /
• 제16권4호
• /
• pp.195-211
• /
• 2010

전시회는 전시업체가 새로운 상품이나 서비스를 관람객에게 알리기 위해 개최되는 것으로 효과적인 마케팅 수단으로 중요한 역할을 수행한다. 전시회를 방문하는 다양한 관람객의 니즈를 충족시키기 위하여 다양한 유비쿼터스 기술이 전시회에 응용되고 있지만 관람객이 사전에 요청한 정보만을 제공함으로 개별 관람객의 선호가 반영되지 않아 관람객의 니즈를 충족시키기에는 한계가 있다. 이러한 한계를 해결하기 위한 방법으로 개인의 선호에 부합하는 부스를 추천하는 추천 시스템의 이용이 가능하다. 추천시스템은 전시 환경에서 관람객의 선호를 추론하여 선호에 부합하는 방문 부스를 추천하여 관람객의 니즈를 충족시킬 수 있다. 그러나 추천 시스템 중 가장 성공적으로 평가 받는 기존의 협업 필터링은 관람객의 부스 방문 순서에 나타나는 선호를 반영하지 않아 동적으로 변화하는 선호를 가지는 관람객으로 구성된 전시 환경의 추천 시스템으로는 적합하지 않다. 따라서 본 연구에서는 관람객의 방문 순서를 고려하는 기법 중 순차 연관 규칙을 이용하여 관람객의 선호에 부합하는 부스를 추천하는 방법론을 제안하였다. 본 연구에서 제안한 방법론의 성과 측정을 위해 실제 전시회에서 획득한 데이터를 사용하여 기존의 협업 필터링과 비교한 결과 전체적으로 추천의 성과가 향상되어 향후 전시 환경에서의 부스 추천시스템에 적용하여 관람객의 니즈를 충족시킬 것으로 기대된다.

• 한국컴퓨터정보학회논문지
• /
• 제28권9호
• /
• pp.93-104
• /
• 2023

현대 사회의 서비스 방식은 대면 방식보다 비대면 방식을 선호하는 추세이다. 하지만 신발과 같이 상품을 추천하는 서비스는 대면 방식의 서비스가 불가피하다. 본 논문에서는 비대면 서비스를 목적으로 자동으로 발의 사이즈를 측정하고, 측정 결과를 기반으로 신발을 추천하는 시스템을 제안한다. 제안방법의 성능을 분석하기 위해 사이즈 측정 오차율과 추천성능을 분석하였다. 추천성능 실험에 사용한 방법은 총 10가지이고, 이의 방법 중 가장 좋은 성능을 보이는 추천 방법을 시스템에 적용하였다. 오차율에 대한 실험결과, 사이즈 관련 오차가 작음을 알 수 있었고, 추천성능에 대한 실험결과, 추천에 대한 유의한 결과를 도출할 수 있었다. 본 논문에서의 제안방법은 실험실 수준으로 향후 실제 환경으로 확대 적용할 필요가 있다.

• 스마트미디어저널
• /
• 제9권1호
• /
• pp.45-50
• /
• 2020

딥 러닝의 발전에 따라 추천시스템에서 딥 러닝 기반의 인공신경망을 활용한 연구가 활발히 진행되고 있다. 특히, RNN(Recurrent Neural Network)기반의 추천시스템은 데이터의 순차적 특성을 고려하기 때문에 추천시스템에서 좋은 성과를 보여주고 있다. 본 연구는 RNN기반의 알고리즘인 GRU(Gated Recurrent Unit)와 세션 기반 병렬 미니배치(Session Parallel mini-batch)기법을 활용한 여행경로 추천 시스템을 제안한다. 본 연구는 top1과 bpr(Bayesian personalized ranking) 오차함수의 앙상블을 통해 추천 성과를 향상시켰다. 또한, 데이터 내에 순차적인 특성을 고려한 RNN기반 추천 시스템은 여행경로에 내재된 여행지의 의미가 반영된 추천이 이루어진다는 것을 확인되었다.