• Journal of Intelligence and Information Systems
• /
• v.12 no.4
• /
• pp.61-72
• /
• 2006

Ubiquitous computing technologies become mature enough to be applied in acceptable ubiquitous services. In particular, in u-shopping area, personalized recommender systems which automatically collect the nomadic user-related context data and then provide them with products or shops in a flexible manner. However, legacy cooperative queries and context-aware queries so far do not come up with dynamically changing situations and ambiguous query commands, respectively. Hence, The purpose of this paper is to propose a personalized context-aware cooperative query that supports a multi-level data abstraction hierarchy and conceptual distance metric among node instances, while considering the user's context data. To show the feasibility of the methodology proposed in this paper, we have implemented a prototype system, CACO, in the area of site search in a large-scale shopping mall.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.4
• /
• pp.73-79
• /
• 2013

Recently, smart TVs have widely spread in our daily lives. However, it is difficult for users to find proper TV contents among a lot of TV and application contents because of inconvenience of input devices compared with those of smart phones or smart pads, so there are some problems with very low utilization of the smart functionalities of smart TVs. We suggest a personalized contents recommender system on smart TVs to resolve these problems and help for users to search appropriate contents easily and quickly in this research. We design and implement an intelligent system for personalized contents recommendation on the smart TVs based on multi-dimensional analysis considering user profiles and preferences, watching patterns of TV programs, and TV contents use statistics of TV users.

• The KIPS Transactions:PartD
• /
• v.9D no.6
• /
• pp.1009-1016
• /
• 2002

We design and implement a new case-based recommender system using implicit rating information for a digital content site. Our system consists of the User Profile Generation module, the Similarity Evaluation and Recommendation module, and the Personalized Mailing module. In the User Profile Generation Module, we define intra-attribute and inter-attribute weight deriver from own's past interests of a user stored in the access logs to extract individual preferences for a content. A new similarity function is presented in the Similarity Evaluation and Recommendation Module to estimate similarities between new items set and the user profile. The Personalized Mailing Module sends individual recommended mails that are transformed into platform-independent XML document format to users. To verify the efficiency of our system, we have performed experimental comparisons between the proposed model and the collaborative filtering technique by mean absolute error (MAE) and receiver operating characteristic (ROC) values. The results show that the proposed model is more efficient than the traditional collaborative filtering technique.

• Journal of KIISE:Software and Applications
• /
• v.29 no.9
• /
• pp.669-675
• /
• 2002

In recent years most of personalized recommender systems in electronic commerce utilize collaborative filtering algorithm in order to recommend more appropriate items. User-based collaborative filtering is based on the ratings of other users who have similar preferences to a user in order to predict the rating of an item that the user hasn't seen yet. This nay decrease the accuracy of prediction because the similarity between two users is computed with respect to the two users and only when an item has been rated by the users. In item-based collaborative filtering, the preference of an item is predicted based on the similarity between the item and each of other items that have rated by users. This method, however, uses the ratings of users who are not the neighbors of a user for computing the similarity between a pair of items. Hence item-based collaborative filtering may degrade the accuracy of a recommender system. In this paper, we present a new approach that a user's neighborhood is used when we compute the similarity between the items in traditional item-based collaborative filtering in order to compensate the weak points of the current item-based collaborative filtering and to improve the prediction accuracy. We empirically evaluate the accuracy of our approach to compare with several different collaborative filtering approaches using the EachMovie collaborative filtering data set. The experimental results show that our approach provides better quality in prediction and recommendation list than other collaborative filtering approaches.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.111-128
• /
• 2023

With the development of artificial intelligence technology, interest in data-based product preference estimation and personalized recommender systems is increasing. However, if the recommendation is not suitable, there is a risk that it may reduce the purchase intention of the customer and even extend to a huge financial loss due to the characteristics of the financial product. Therefore, developing a recommender system that comprehensively reflects customer characteristics and product preferences is very important for business performance creation and response to compliance issues. In the case of financial products, product preference is clearly divided according to individual investment propensity and risk aversion, so it is necessary to provide customized recommendation service by utilizing accumulated customer data. In addition to using these customer behavioral characteristics and transaction history data, we intend to solve the cold-start problem of the recommender system, including customer demographic information, asset information, and stock holding information. Therefore, this study found that the model proposed deep learning-based collaborative filtering by deriving customer latent preferences through characteristic information such as customer investment propensity, transaction history, and financial product information based on customer transaction log records was the best. Based on the customer's financial investment mechanism, this study is meaningful in developing a service that recommends a high-priority group by establishing a recommendation model that derives expected preferences for untraded financial products through financial product transaction data.

• Information Systems Review
• /
• v.23 no.1
• /
• pp.155-172
• /
• 2021

With the recent increase in online product purchases, a recommender system that recommends products considering users' preferences has still been studied. The recommender system provides personalized product recommendation services to users. Collaborative Filtering (CF) using user ratings on products is one of the most widely used recommendation algorithms. During CF, the item-based method identifies the user's product by using ratings left on the product purchased by the user and obtains the similarity between the purchased product and the unpurchased product. CF takes a lot of time to calculate the similarity between products. In particular, it takes more time when using text-based big data such as review data of Amazon store. This paper suggests a hybrid recommendation system using a 2-phase methodology and text data mining to calculate the similarity between products easily and quickly. To this end, we collected about 980,000 online consumer ratings and review data from the online commerce store, Amazon Kinder Store. As a result of several experiments, it was confirmed that the suggested hybrid recommendation system reflecting the user's rating and review data has resulted in similar recommendation time, but higher accuracy compared to the CF-based benchmark recommender systems. Therefore, the suggested system is expected to increase the user's satisfaction and increase its sales.

• 한국경영정보학회:학술대회논문집
• /
• 2008.06a
• /
• pp.153-170
• /
• 2008

Customers' needs change every moment. Profitability of stores can't be increased anymore with an existing standardized chain store management. Accordingly, a personalized store management tool needs through prediction of customers' preference. In this study, we propose a recommending procedure using dynamic customers' preference by analyzing the transaction database. We utilize self-organizing map algorithm and association rule mining which are applied to cluster the chain stores and explore purchase sequence of customers. We demonstrate that the proposed methodology makes an effect on recommendation of products in the market which is characterized by a fast fashion and a short product life cycle.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.01a
• /
• pp.47-50
• /
• 2015

TV는 타 도메인과 달리, 사전에 정해진 시간에 콘텐츠가 방영된다. 그러므로 TV 프로그램 추천 시스템은 시청자의 현재 시각(time-context)을 고려해야 한다. 시간 기반의 TV 프로그램 추천 방법이 다수 연구되었지만, 대부분의 기존 연구는 특정 시간대(timeslot)에서의 시청자의 선호도를 계산하는 데에만 집중되어 있고, 시청 내역 전체기간에서의 선호도를 고려하지 않은 문제점이 있다. 이러한 문제를 해결하기 위해, 시청자의 지역 선호도와 전역 선호도를 모두 고려한 시간 기반의 TV 프로그램 추천기법을 제안한다. 이를 위해 제안 방법에서는 시간대의 길이에 따라 여러 가지 선호도 모델을 사용한다. 여러 개의 선호도 모델로부터 산출된 선호도를 병합하여 가장 선호도가 높은 TV 프로그램을 추천한다. 실 데이터를 이용한 실험을 통해 기준방식과 비교함으로써, 제안 방법의 효용성을 검증하였다.

• Journal of information and communication convergence engineering
• /
• v.18 no.1
• /
• pp.55-60
• /
• 2020

As personalized customer services create a society that emphasizes the personality of an individual, the number of product reviews and quantity of user data generated by users on the internet in mobile shopping apps and sites are increasing. Such product review data are classified as unstructured data. Unstructured data have the potential to be transformed into information that companies and users can employ, using appropriate processing and analyses. However, existing systems do not reflect the detailed information they collect, such as user characteristics, purchase preference, or purchase priority while analyzing review data. Thus, it is challenging to provide customized recommendations for various users. Therefore, in this study, we have developed a product recommendation system that takes into account the user's priority, which they select, when searching for and purchasing a product. The recommendation system then displays the results to the user by processing and analyzing their preferences. Since the user's preference is considered, the user can obtain results that are more relevant.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.95-99
• /
• 2008

유비쿼터스 환경에서 사용자는 개인용 디바이스를 이용하여 보이지 않는 수많은 자원들과 서로 연결하여 원하는 서비스를 제공 받기를 원한다. 이러한 요구사항을 만족시키기 위하여 유비쿼터스 지능 공간에 존재하는 자원들 사이의 공유가 필요하며 이를 효율적으로 수행하기 위한 연구는 새로운 연구 주제이다. 그러나 동일한 환경이라 할 지라도 각 사용자들의 상황은 서로 다르며 개인적인 성향 역시 다양하다. 그러므로 동일한 공간에서 동일한 서비스를 원하는 사용자들이라 할 지라도 현재의 상황과 사용자 개개인의 개성에 따라 필요로 하는 자원이 다른 것이 현실이다. 그러므로 본 논문에서는 사용자의 상황을 인지하여 맞춤형 자원을 추천하는 시스템을 개발한다. 추천 시스템은 사용자의 상황을 인지하기 위한 방법으로 온톨로지 기반 추론을 수행하고, 개인화 추천 서비스를 제공하기 위하여 규칙들 이용한 규칙 기반 추론 방법을 수행한다.