• Asia pacific journal of information systems
• /
• 제15권3호
• /
• pp.223-241
• /
• 2005

In spite of the rapid growth of mobile multimedia contents market, most of the customers experience inconvenience, lengthy search processes and frustration in searching for the specific multimedia contents they want. These difficulties are attributable to the current mobile Internet service method based on inefficient sequential search. To overcome these difficulties, this paper proposes a MOBIIe COntents Recommender System for Movie(MOBICORS-Movie), which is designed to reduce customers' search efforts in finding desired movies on the mobile Internet. MOBICORS-Movie consists of three agents: CF(Collaborative Filtering), CBIR(Content-Based Information Retrieval) and RF(Relevance Feedback). These agents collaborate each other to support a customer in finding a desired movie by generating personalized recommendations of movies. To verify the performance of MOBICORS-Movie, the simulation-based experiments were conducted. The results from this experiments show that MOBICORS-Movie significantly reduces the customer's search effort and can be a realistic solution for movie recommendation in the mobile Internet environment.

• 산업경영시스템학회지
• /
• 제40권4호
• /
• pp.154-163
• /
• 2017

Collaborative filtering, one of the most widely used techniques to build recommender systems, is based on the idea that users with similar preferences can help one another find useful items. Credit card user behavior analytics show that most customers hold three or less credit cards without duplicates. This behavior is one of the most influential factors to data sparsity. The 'cold-start' problem caused by data sparsity prevents recommender system from providing recommendation properly in the personalized credit card recommendation scenario. We propose a personalized credit card recommender system to address the cold-start problem, using multiple user profiles. The proposed system consists of a training process and an application process using five user profiles. In the training process, the five user profiles are transformed to five user networks based on the cosine similarity, and an integrated user network is derived by weighted sum of each user network. The application process selects k-nearest neighbors (users) from the integrated user network derived in the training process, and recommends three of the most frequently used credit card by the k-nearest neighbors. In order to demonstrate the performance of the proposed system, we conducted experiments with real credit card user data and calculated the F1 Values. The F1 value of the proposed system was compared with that of the existing recommendation techniques. The results show that the proposed system provides better recommendation than the existing techniques. This paper not only contributes to solving the cold start problem that may occur in the personalized credit card recommendation scenario, but also is expected for financial companies to improve customer satisfactions and increase corporate profits by providing recommendation properly.

• 지능정보연구
• /
• 제11권1호
• /
• pp.191-205
• /
• 2005

전자상거래의 확산에 따라 인터넷 쇼핑몰에서의 구매활동은 일반적인 현상이 되었다 그 결과, 유사한 업종이나 업태의 인터넷 쇼핑몰이 범람하게 되었고 업체들 간의 경쟁도 심화되어 차별화 된 서비스를 제공하지 않는 업체는 도태되기 쉬운 상황이다. 본 연구에서는 치열한 경쟁환경 하에서 인터넷 쇼핑몰들의 차별화 된 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 개인화 된 상품추천시스템 모형이다. 유전자 알고리즘은 추출하기가 어려운 소비자의 성향을 데이터를 통해 추출하고 이에 맞는 상품군을 선택할 수 있도록 해 주는 최적화 기법으로 상품추천시스템의 추천엔진으로써 유용할 것으로 기대된다 본 연구에서는 제안하는 유전자 알고리즘에 기반한 추천규칙들이 장착된 웹 기반의 개인화 된 상품추천시스템의 프로토타입을 개발하고 이에 대한 실제 사용자들의 이용 만족도를 확인함으로써 렬 연구에서 제안한 방법론의 유용성을 확인하고자 한다.

• 한국IT서비스학회지
• /
• 제21권2호
• /
• pp.109-126
• /
• 2022

The number and variety of products and services offered by companies have increased dramatically, providing customers with more choices to meet their needs. As a solution to this information overload problem, the provision of tailored services to individuals has become increasingly important, and the personalized recommender systems have been widely studied and used in both academia and industry. Existing recommender systems face important problems in practical applications. The most important problem is that it cannot clearly explain why it recommends these products. In recent years, some researchers have found that the explanation of recommender systems may be very useful. As a result, users are generally increasing conversion rates, satisfaction, and trust in the recommender system if it is explained why those particular items are recommended. Therefore, this study presents a methodology of providing an explanatory function of a recommender system using a review text left by a user. The basic idea is not to use all of the user's reviews, but to provide them in a summarized form using only reviews left by similar users or neighbors involved in recommending the item as an explanation when providing the recommended item to the user. To achieve this research goal, this study aims to provide a product recommendation list using user-based collaborative filtering techniques, combine reviews left by neighboring users with each product to build a model that combines text summary methods among deep learning-based natural language processing methods. Using the IMDb movie database, text reviews of all target user neighbors' movies are collected and summarized to present descriptions of recommended movies. There are several text summary methods, but this study aims to evaluate whether the review summary is well performed by training the Sequence-to-sequence+attention model, which is a representative generation summary method, and the BertSum model, which is an extraction summary model.

• 대한산업공학회지
• /
• 제41권2호
• /
• pp.185-208
• /
• 2015

The explosive growth of the world-wide-web and the emergence of e-commerce has led to the development of recommender systems. Recommender systems are personalized information filtering used to identify a set of items that will be of interest to a certain user. This paper reviews recommender systems and presents their pros and cons.

• 한국컴퓨터정보학회논문지
• /
• 제27권9호
• /
• pp.59-68
• /
• 2022

추천시스템은 소비자를 대신하여 소비자가 선호할 만한 아이템이나 서비스를 검색하여 구매할 수 있도록 한다. 추천시스템의 추천은 사용자들이 경험하지 않은 아이템들에 대한 선호 예측이기 때문에 완전하게 맞는 답이 도출되는 것은 불가능하다. 따라서 예측에 대한 평가가 수행되어야만 비로소 추천시스템이 정확한지 아닌지를 판단할 수 있다. 그러나 사용자 선호에 대한 예측 정확성만을 높이는 추천은 오히려 사용자의 만족도를 하락시킬 수 있는데 이는 사용자의 취향만을 반영한 편중된 결과로 사용자는 다양한 아이템들로 구성된 추천 결과를 받을 수 없는 필터버블 현상이 야기되기 때문이다. 품질 측정 지표의 다각화가 필요한 이유이고 대표적으로 다양성 지표가 사용된다. 본 논문에서는 추천 결과의 다양성 증대를 위한 3가지 기본 접근방법인 bin packing, weighted random choice, greedy re-ranking을 실제 e-커머스 데이터인 패션 쇼핑몰 데이터에 적용하여 도출된 결과와 F1 score에 기반을 둔 차이를 분석한다.

• Journal of Information Technology Applications and Management
• /
• 제21권1호
• /
• pp.85-105
• /
• 2014

Exhibition industry is important business domains to many countries. Not only lots of countries designated the exhibition industry as tools to stimulate national economics, but also many companies offer millions of service or products to customers. Recommender systems can help visitors navigate through large information spaces of various booths. However, no study before has proposed a methodology for identifying and acquiring prospective visitors although it is important to acquire them. Accordingly, we propose a methodology for identifying, acquiring prospective visitors, and recommending the adequate booth information to their preferences in the exhibition industry. We assume that a visitor will be interested in an exhibition within same class of exhibition taxonomy as exhibition which the visitor already saw. Moreover, we use user-based collaborative filtering in order to recommend personalized booths before exhibition. A prototype recommender system is implemented to evaluate the proposed methodology. Our experiments show that the proposed methodology is better than the item-based CF and have an effect on the choice of exhibition or exhibit booth through automation of word-of-mouth communication.

• 한국IT서비스학회지
• /
• 제22권1호
• /
• pp.43-56
• /
• 2023

With the development of the e-commerce market, various types of products continue to be released. However, customers face an information overload problem in purchasing decision-making. Therefore, personalized recommendations have become an essential service in providing personalized products to customers. Recently, many studies on GCN-based recommender systems have been actively conducted. Such a methodology can address the limitation in disabling to effectively reflect the interaction between customer and product in the embedding process. However, previous studies mainly use implicit feedback data to conduct experiments. Although implicit feedback data improves the data scarcity problem, it cannot represent customers' preferences for specific products. Therefore, this study proposed a novel model combining explicit and implicit feedback to address such a limitation. This study treats the average ratings of customers and products as the features of customers and products and converts them into a high-dimensional feature vector. Then, this study combines ID embedding vectors and feature vectors in the embedding layer to learn the customer-product interaction effectively. To evaluate recommendation performance, this study used the MovieLens dataset to conduct various experiments. Experimental results showed the proposed model outperforms the state-of-the-art. Therefore, the proposed model in this study can provide an enhanced recommendation service for customers to address the information overload problem.

• 한국컴퓨터정보학회논문지
• /
• 제23권12호
• /
• pp.219-226
• /
• 2018

Collaborative filtering has been most popular approach to recommend items in online recommender systems. However, collaborative filtering is known to suffer from data sparsity problem. As a simple way to overcome this problem in literature, Jaccard index has been adopted to combine with the existing similarity measures. We analyze performance of such combination in various data environments. We also find optimal weights of factors in the combination using a genetic algorithm to formulate a similarity measure. Furthermore, optimal weights are searched for each user independently, in order to reflect each user's different rating behavior. Performance of the resulting personalized similarity measure is examined using two datasets with different data characteristics. It presents overall superiority to previous measures in terms of recommendation and prediction qualities regardless of the characteristics of the data environment.

• Asia pacific journal of information systems
• /
• 제34권1호
• /
• pp.226-247
• /
• 2024

Most studies on recommender systems to evaluate recommendation performances focus on offline evaluation methods utilizing past customer transaction records. However, evaluating recommendation performance through real-world stimulation becomes challenging. Moreover, such methods cannot evaluate the duration of the recommendation effect. This study measures the personalized recommendation (stimulus) effect when the product recommendation to customers leads to actual purchases and evaluates the duration of the stimulus personalized recommendation effect leading to purchases. The results revealed a 4.58% improvement in recommendation performance in the online environment compared with that in the offline environment. Furthermore, there is little difference in recommendation performance in offline experiments by period, whereas the recommendation performance declines with time in online experiments.