• 산업경영시스템학회지
• /
• 제28권3호
• /
• pp.58-64
• /
• 2005

Customer sensibility based recommendation agent system was developed to tailor to the customer the suggestion of goods and the description of store catalog in on-line shopping mall. The recommendation agent system composed of five modules and seven services including specialized algorithm. This study was to investigate the effectiveness of the customer sensibility based recommendation agent system in on-line shopping mall. This study asked 30 male and female students to perform the task in on-line shopping mall and facilitated them questionnaires. The questionnaires were administered to subjects to measure quality precision, ease of use, support of buying, purchasing power, future intention of the system. The study revealed that good part of the subjects positively evaluated the customer sensibility based recommendation system except for ease of use. The study on usability of the recommendation agent system has need to be performed in next. This paper shows that the satisfaction and the buying power of customers may be improved by presenting customer sensibility based recommendation in on-line shopping mall.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.426-439
• /
• 2021

To alleviate the cold-start problem and data sparsity in web service recommendation and meet the personalized needs of users, this paper proposes a personalized web service recommendation method based on a hybrid social network and multi-objective immune optimization. The network adds the element of the service provider, which can provide more real information and help alleviate the cold-start problem. Then, according to the proposed service recommendation framework, multi-objective immune optimization is used to fuse multiple attributes and provide personalized web services for users without adjusting any weight coefficients. Experiments were conducted on real data sets, and the results show that the proposed method has high accuracy and a low recall rate, which is helpful to improving personalized 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2809-2821
• /
• 2023

Effective recommendation of similar business groups is a critical factor in obtaining market information for companies. In this study, we propose a novel method for enhancing similar business group recommendation by incorporating derivative criteria and web crawling. We use employment announcements, employment incentives, and corporate vocational training information to derive additional criteria for similar business group selection. Web crawling is employed to collect data related to the derived criteria from 'credit jobs' and 'worknet' sites. We compare the efficiency of different datasets and machine learning methods, including XGBoost, LGBM, Adaboost, Linear Regression, K-NN, and SVM. The proposed model extracts derivatives that reflect the financial and scale characteristics of the company, which are then incorporated into a new set of recommendation criteria. Similar business groups are selected using a Euclidean distance-based model. Our experimental results show that the proposed method improves the accuracy of similar business group recommendation. Overall, this study demonstrates the potential of incorporating derivative criteria and web crawling to enhance similar business group recommendation and obtain market information more efficiently.

• 산업공학
• /
• 제19권1호
• /
• pp.70-77
• /
• 2006

One of the problems in developing a collaborative recommendation system is the scalability. To alleviate the scalability problem efficiently, enhancing the performance of the recommendation system, we propose a new recommendation system using feature selection. In our experiments, the proposed system using about a third of all features shows the comparable performances when compared with using all features in light of precision, recall and number of computations, as the number of users and products increases.

• 정보처리학회논문지D
• /
• 제16D권2호
• /
• pp.273-280
• /
• 2009

오늘날 컴퓨팅 환경의 진보와 웹의 이용이 활발해짐에 따라 오프라인에서 이루어졌던 있었던 많은 서비스들과 상품의 제공이 웹에서 이루어지고 있다. 이러한 웹 기반 서비스 및 상품은 개인에 적합하게 취사선택되어 제공되는 추세이다. 이렇듯 개인에 적합한 서비스 및 상품의 선택과 제공을 위한 패러다임을 개인화(personalization)라 한다. 개인화된 서비스 및 상품의 제공을 위한 분야로서 연구된 것이 추천(recommendation)이다. 그러나 이러한 추천 기법들은 신규 사용자에게 적합한 추천을 제공하지 못하는 문제와 사용자의 상품에 대한 평점에만 의존하여 추천을 생성한다는 계산 공간에서의 제약 사항을 가지고 있다. 두 문제 모두 추천 분야에서 지속적인 관심을 보이는 분야로서 신규사용자 추천 문제의 경우는 신규 사용자의 평점이 없기 때문에 유사 사용자들을 분류할 수 없음에 기인한다. 그리고 추천 공간 제약에 따른 문제는 추천 차원의 추가에 따른 처리 비용이 급격히 증가한다는 문제를 가지고 있기 때문에 쉽게 접근하기 어렵다. 따라서 본 논문에서는 신규사용자 추천 향상을 위한 기법과 평점 예측 시 예측에 대한 가중치를 적용하는 기법을 제안한다.

• 지능정보연구
• /
• 제14권2호
• /
• pp.63-82
• /
• 2008

추천시스템은 정보 과부하의 문제를 해결하기 위해 폭넓게 사용되어지고 있다. 지난 수십년 동안 다양한 추천시스템이 정보량이 그것을 처리할 수 있는 능력보다 더 빠르게 증가하게 됨에 따라 개발되어져 왔다. 이 같은 상황에서 본 연구의 목적은 기 개발된 추천시스템을 분석하여 시스템적 관점을 제공하고 이를 구현하는데 따르는 기본적인 이슈들을 밝히는 것이다. 이를 통하여 추천시스템의 개선을 위한 유용한 정보를 제안하며, 시스템 개발자들에게는 그러한 시스템을 개선하기 위한 아이디어를 제공하고자 한다. 특히 본 연구는 추천시스템의 이론적 관점에 집중하는데, 이를 위해 과거 추천시스템의 도메인과 목표, 주요 방법 및 평가 방법에 대해서 다루고자 하며, 이 결과는 통계치나 도표 등의 형태로 보이려고 한다.

• 정보처리학회논문지D
• /
• 제15D권3호
• /
• pp.421-428
• /
• 2008

협업여과 기법은 추천 시스템에서 널리 사용되는 기술이지만, 소비자의 참조그룹을 선정하는 방법에 따라 추천의 정확도가 달라지는 특성을 가지고 있다. 이에 본 논문에서는 콘텐츠 추천의 정확도를 높이기 위하여 소비자의 감성과 소비유형을 참조그룹으로 하여 협업여과기반으로 콘텐츠를 추천하는 기법을 제안한다. 소비자의 감성을 기쁨, 슬픔, 혐오, 행복, 이완 다섯 가지로 구분하고, 소비유형을 저실용/저쾌락, 저실용/고쾌락, 고실용/저쾌락, 고실용/고쾌락 네 가지로 구분하여 콘텐츠 추천 기법의 성능을 분석한 결과, 본 논문에서 제안하는 기법으로 콘텐츠를 추천한 경우가 소비자 감성과 소비유형을 고려하지 않은 전체 참조그룹으로 추천한 경우보다 정확도가 향상됨을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제23권1호
• /
• pp.31-42
• /
• 2020

During the 4th Industrial Revolution, service platforms utilizing diverse contents are emerging, and research on recommended systems that can be customized to users to provide quality service is being conducted. hybrid recommendation systems that provide high accuracy recommendations are being researched in various domains, and various filtering techniques, machine learning, and deep learning are being applied to recommended systems. However, in a recommended service environment where data must be analyzed and processed real time, the accuracy of the recommendation is important, but the computational speed is also very important. Due to high level of model complexity, a hybrid recommendation system or a Deep Learning-based recommendation system takes a long time to calculate. In this paper, a Cascade-hybrid recommended algorithm is proposed that can reduce the computational time while maintaining the accuracy of the recommendation. The proposed algorithm was designed to reduce the complexity of the model and minimize the computational speed while processing sequentially, rather than using existing weights or using a hybrid recommendation technique handled in parallel. Therefore, through the algorithms in this paper, contents can be analyzed and recommended effectively and real time through services such as SNS environments or shared economy platforms.

• 농업과학연구
• /
• 제44권2호
• /
• pp.283-295
• /
• 2017

This study analyzed the effect of the intrinsic and extrinsic attributes of gochujang, Korean red chili paste, on purchasing intention and recommendation intention for consumption. Survey participants were female, married, aged 30 - 39 years, and highly educated with graduation from a university. Most participants purchased gochujang 1 - 2 times per year, most commonly at a shopping mall, and acquired information on the gochujang product from an advertisement or sponsored TV shows. For the factor analysis, five variables for intrinsic quality were considered: namely, healthiness, economics, convenience, diversity, and sense, whereas three variables were considered for extrinsic quality: trust, external appearance, and image. The factor analysis also confirmed the correlation between the validity and the reliability of the purchasing and recommendation intentions. The effect of intrinsic quality of gochujang on purchasing and recommendation intentions was tested through a multiple regression analysis. The purchase intention was most significantly affected by healthiness, cost, and convenience. On the other hand, the recommendation intention was most significantly affected by the diversity and, to a lesser degree, by the healthiness of the product. Among the extrinsic qualities, trust of consumers and the product appearance had a significant effect on purchasing intention. Recommendation intention was significantly affected by the appearance. And trust significantly influenced the recommendation. Therefore, a concrete and systematic marketing approach considering these factors.