• Information Systems Review
• /
• v.23 no.1
• /
• pp.69-91
• /
• 2021

Credit Bureaus in Korea commonly use financial transaction information of the past and present time for calculating an individual's credit scores. Compared to other rating factors, the repayment history information accounts for a larger weights on credit scores. Accordingly, despite full redemption of overdue payments, late payment history is reflected negatively for the assessment of credit scores for certain period of the time. An individual with debt delinquency can be classified into two groups; (1) the individuals who have faithfully paid off theirs overdue debts(Normal Repayment), and (2) those who have not and as differences of creditworthiness between these two groups do exist, it needs to grant relatively higher credit scores to the former individuals with normal repayment. This study is designed to analyze the factors of normal repayment of Korean financial debt delinquents based on credit information of personal loan, overdue payments, redemption from Korea Credit Information Services. As a result of the analysis, the number of overdue and the type of personal loan and delinquency were identified as significant variables affecting normal repayment and among applied methodologies, neural network models suggested the highest classification accuracy. The findings of this study are expected to improve the performance of individual credit scoring model by identifying the factors affecting normal repayment of a financial debt delinquent.

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.457-466
• /
• 2004

Recommendation is to offer information which fits user's interests and tastes to provide better services and to reduce information overload. It recently draws attention upon Internet users and information providers. The collaborative filtering is one of the widely used methods for recommendation. It recommends an item to a user based on the reference users' preferences for the target item or the target user's preferences for the reference items. In this paper, we propose a neural network based collaborative filtering method. Our method builds a model by learning correlation between users or items using a multi-layer perceptron. We also investigate integration of diverse information to solve the sparsity problem and selecting the reference users or items based on similarity to improve performance. We finally demonstrate that our method outperforms the existing methods through experiments using the EachMovie data.

• Journal of Digital Convergence
• /
• v.10 no.3
• /
• pp.23-37
• /
• 2012

Illegal game players' hacking and propagation of malignant code in online game exposes privacy of online game customers. So, online game companies have to support the standardized systems and operations of customers' privacies. Since online game companies implement authentication of information protection, which focuses on assets or physical, systemic security, they need a more professional system that is related to protection of individual privacy. We analyzed the individual information protection system, which includes ISO27001, ISMS of KISA, GMITS, ePrivacy, online game privacy protection guide, and BS10012. Using the suggested systems, we proposed the systemic tools that measure the level of individual information protection, which includes process and check items of each phase.

• Journal of the Korean Data and Information Science Society
• /
• v.5 no.2
• /
• pp.107-116
• /
• 1994

이 논문은 통계상담사례연구의 일종으로 설문지를 이용한 통계자료분석에 도움이 되도록 소개하고자 한다. 여러항목을 종합하여 한 척도를 구성하고 각 항목마다 중요도나 선호도 등에 따라 다품등 리커트형 척도를 묻는 자료는 개인의 성향이나 지리적 문화적 여건에 따라 그 응답경향이 달라 가질지도 모르는 반응편향성(Response Set Bias)을 감소시켜 보다 좋은 통계자료분석을 할 수 있는 통계적 방법을 소개하며, 이 방법을 적용시킨 통계상담을 예시하고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.578-579
• /
• 2021

According to a survey on the infringement of SMEs, the level of technology protection capability is improving every year, but technology leaks and damage continue to occur. This shows that there is a need for a security management and supervision system that can strengthen the security awareness of SME executives and employees and maintain the security level continuously. The Personal Information & Information Security Management System(ISMS-P) authentication systems is the latest related standard, which has the problem of applying the same certification criteria without considering the types of certification target organizations such as ISPs, IDC, hospitals and schools, and SMEs.. In this paper, 73 evaluation items that can be specialized and applied to SMEs were derived by referring to ISMS-P certification and Personal Information Protection Management System (PIMS) certification. The results of the study show that the number of evaluation items decreased by 28.4% compared to the existing ISMS-P certification.

• Journal of Intelligence and Information Systems
• /
• v.8 no.2
• /
• pp.91-103
• /
• 2002

A collaborative filtering which supports personalized services of users has been common use in existing web sites for increasing the satisfaction of users. A collaborative filtering is demanded that items are estimated more than specified number. Besides, it tends to ignore information of other users as recommending them on the basis of information of partial users who have similar inclination. However, there are valuable hidden information into other users' one. In this paper, we use Association Rule, which is common wide use in Data Mining, with collaborative filtering for the purpose of discovering those information. In addition, this paper proved that Association Rule applied to Recommender System has a effects to recommend users by the relation between groups. In other words, Association Rule based on the history of all users is derived from. and the efficiency of Recommender System is improved by using Association Rule with collaborative filtering.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.389-390
• /
• 2023

본 논문에서는 패션 매칭의 어려움을 해결해주기 위하여 '무신사' 쇼핑몰을 이용하여 크롤링하고 이를 정제한 dataset을 이용하여 패션 스타일의 핵심 요소 중 하나인 신발에 초점을 맞추어, 이미지 기반의 패션 매칭 시스템인 빅데이터 기반 패션 도우미, Shoes Navigator 를 제안한다. 이를 위해 컴퓨터 비전 및 딥 러닝 기술을 활용하여 이미지에서 의류 항목을 자동으로 감지하고, 스타일, 색상과 같은 패션 특성을 추출한다. 또한, 사용자의 개인적인 스타일을 고려하여 최적의 매칭을 제안하기 때문에 패션 코디 문제를 용이하게 해결할 수 있다.

• 한국IT서비스학회:학술대회논문집
• /
• 2008.11a
• /
• pp.419-422
• /
• 2008

유비쿼터스 시대의 핵심 기반기술인 RFID와 관련하여 공공기관을 중심으로 시범 사업 및 본 사업이 활발하게 추진되고 있다. 또한 RFID 기반 정보시스템에 대한 감리 수요도 계속 증가하고 있으며, 특히 개인정보보호에 대한 관심이 확산되면서 보안감리의 비중도 높아지고 있다. 이와 관련하여 RFID 기반 정보시스템의 사업특성을 적절히 반영한 보안감리 점검항목이 요구되고 있다. 따라서 본 논문에서는 현행 RFID 기반 정보시스템에 대한 감리를 보다 체계적이고 효율적으로 수행하는데 활용될 수 있는 RFID 사업특성기반의 보안감리 점검항목을 제안한다.

• 한국IT서비스학회:학술대회논문집
• /
• 2008.11a
• /
• pp.135-138
• /
• 2008

본 연구에서는 한국과 중국의 인터넷 광고 내용에 대한 내용분석 연구로서 문헌연구를 통해 주요변수항목에 관한 선행연구를 통해 측정항목을 도출하였으며 한-중간 인터넷 광고의 내용 차이를 분석하였다. 구체적으로 인터넷 광고 상품유형, 개인주의/집단주의, 광고소구, 소비가치, 광고컬러, 광고모델, 광고 글자 수 및 광고 컷(cut)의 길이 총 8개의 주요변수항목을 통한 분석으로 두 나라 간 인터넷 광고에 나타난 내용적 차이를 분석하였다. 그 결과 양국 간 인터넷 배너광고의 특성에는 많은 차이가 발견되었으며, 그 이유는 문화적 차이, IT인프라의 차이, 산업발전단계의 차이, 그리고 소비확산단계의 차이로 해석될 수 있었다. 마지막으로 중국으로 진출하는 한국기업들이 인터넷 광고 전략을 위한 시사점을 제시하였다.

• Journal of Internet Computing and Services
• /
• v.4 no.5
• /
• pp.31-41
• /
• 2003

At present, the market size of electronic commerce has increased and also the construction of internet shopping mall has expended. But it raises question about issue that the manpower who develope user interface lack of the comprehensive and systematic approach. For that reason this study identified the main factor of the user interface contents in internet shopping mall and suggested the contents item based on the reliability, safety and ease of uses for the customer. Eventually, the developed basic contents items are company information, the protection policy of private information, user agreement. product information, settlement information, order process, delivery process and customer support.