• Asia pacific journal of information systems
• /
• 제25권3호
• /
• pp.579-596
• /
• 2015

Many studies have focused on the prediction of corporate credit rating using various data mining techniques. One of the most frequently used algorithms is support vector machines (SVM), and recently, novel techniques such as SVM+ and SVM+MTL have emerged. This paper intends to show the applicability of such new techniques to multi-classification and corporate credit rating and compare them with conventional SVM regarding prediction performance. We solve multi-class SVM+ and SVM+MTL problems by constructing several binary classifiers. Furthermore, to demonstrate the robustness and outstanding performance of SVM+MTL algorithm over other techniques, we utilized four typical multi-class processing methods in our experiments. The results show that SVM+MTL outperforms both conventional SVM and novel SVM+ in predicting corporate credit rating. This study contributes to the literature by showing the applicability of new techniques such as SVM+ and SVM+MTL and the outperformance of SVM+MTL over conventional techniques. Thus, this study enriches solving techniques for addressing multi-class problems such as corporate credit rating prediction.

• 경영정보학연구
• /
• 제22권3호
• /
• pp.81-97
• /
• 2020

최근의 감성분류 연구는 출력변수가 하나인 단일레이블 분류방법을 사용한 연구가 많다. 특히, 이러한 연구는 하나의 극성 값(긍정, 부정)만을 찾는 연구가 많다. 그러나 한 문장 안에는 다중적인 의미가 내포되어 있다. 그 중에서도 감정과 오피니언이 이러한 특징을 갖는다. 본 논문은 두 가지 연구목적을 제시한다. 첫째, 한 문장 안에 다양한 토픽(주제 또는 애스팩트)이 있다는 사실을 기반으로, 해당 문장을 각 애스팩트 별로 감성을 분류하는 애스팩트 마이닝을 수행한다. 둘째, 두개 이상의 종속변수(출력 값)를 한 번에 분석하는 다중레이블 분류방법을 적용한다. 이에 본 연구는 감성분류의 연구가 단일분류기에 의해서만 이루어진 연구를 개선하고자 다중레이블 분류방법에 의한 애스팩트 마이닝을 수행하고자 한다. 이와 같은 연구목적을 달성하기 위해 국내 뮤지컬 데이터를 수집하였다. 분석결과 문장 안에 있는 다양한 애스팩트별 감성을 추출하였고, 유의한 결과를 얻었다.

• 산업경영시스템학회지
• /
• 제22권50호
• /
• pp.363-372
• /
• 1999

This paper is to propose models for systematic classification and estimation of quality costs. Especially in this research, quality costs are categorized into three aspects, ie., conventional quality cost system, ZD(Zero Defect) quality cost system and Taguchi quality system. In conclusion, I hope that this study will have contribution to application of quality loss system for all the business in Korea.

• 산업공학
• /
• 제20권3호
• /
• pp.387-394
• /
• 2007

Numerous countries promote business programs to revitalize local economy, increase employment, and nurture high-tech industries. Recently, a number of business incubators have been established and operated with aims to adapt to changing environment and increase economic competitiveness in Korea. To give satisfactory results of governmental policy, the requirement to develop the evaluation model to support effective operations of business incubators using the objective and rational criteria is growing. The purpose of this study is to develop evaluation model in Business Incubator using Data Mining Process. We suggested the evaluation model of business incubator, 'Score-5 RS' consists of making evaluation factor process using weighted sum and 5-grade classification and analyzing process by Decision Tree algorithm.

• 한국정보시스템학회:학술대회논문집
• /
• 한국정보시스템학회 2001년도 추계학술대회 발표논문집:차세대 전상거래 시대의 비즈니스전략
• /
• pp.438-450
• /
• 2001

This study is to classify the typology of e-business model based on the practical strategic model for successful e-business implementation. For that purpose, we review the conceptual framework of e-business and collected the data from 127 companies implementing e-business. The study is conducted in three phases as follows. First, six factors consisted of 22 items are derived through factor analysis. Second, Cluster analysis is employed to group the firms into different strategic patterns. A five-cluster solution is found to maximize the distances between cluster means across the six factor patterns. The models are named as 'ascendancy and convergence', 'expansion and moderate price', 'expansion and improvement of quality', 'ascendancy and process', and 'improvement of quality' respectively. Third, ANOVA is used to examine the impact on the performance differences attributable to the models. The results of the study are; (1) the 'ascendancy and process', 'expansion and improvement of quality' and 'expansion and moderate price' models were associated with significantly higher performance levels than the 'improvement of quality' model, and (2) the hybrid strategies are needed to implement e-business successfully based on the 'ascendancy and process' model.

• 지능정보연구
• /
• 제18권4호
• /
• pp.79-95
• /
• 2012

금융기관들에서 개발한 신용 대출 상품이 증가함에 따라 사기 거래의 수 또한 급속히 증가하고 있다. 따라서, 재정적 위험을 성공적으로 관리하기 위해 금융기관들은 대출 승인 심사를 강화하고 신용 대출 사기를 사전에 탐지할 수 있는 능력을 증대시켜 나가야 한다. 신용 대출 사기를 탐지하기 위한 분류 모델을 구축하는 과정에서 분류 결과에 따른 유틸리티(즉, 정분류에 따른 이익과 오분류에 따른 비용)는 분류의 정확도보다 더 중요하다. 본 연구는 개인별 유틸리티에 기반하여 신용 대출 사기를 탐지하기 위한 분류 모델을 구축하는 것을 목적으로 하였다. 다양한 실험을 통해, 본 연구에서 제시한 모델이 기회 유틸리티와 현금 흐름의 두 관점 모두에서 개인별 유틸리티에 기반하지 않은 모델보다 더 높은 유틸리티를 제공하며, 평균 유틸리티에 기반한 모델보다 더 정확한 유틸리티를 제공한다는 것을 보였다. 본 연구는 기회 유틸리티와 현금 흐름의 두 관점에서 얻어진 실험 결과를 다양한 측면에서 살펴보았다.

• 한국전산구조공학회논문집
• /
• 제33권2호
• /
• pp.73-79
• /
• 2020

BIM 도구는 설계프로세스에서 기술의 사용이 증가하면서 그에 따른 정보표준체계가 필요하게 되었다. 건설이 완료된 결과(Result) 분류는 25종 단위시설에 327종의 유형, 결과를 구성하는 객체는 174종의 Part와 207종의 Component로 분류하고 있다. 선행연구에서는 도로와 하천 분야 대상으로 속성분류체계를 대분류 4종, 중분류 13종, 소분류 58종, 속성정보 333종으로 분류하였고, 객체분류에 따른 대량의 속성정보를 입력하는 것의 소요 시간을 줄이는 것이 관건이었다. 따라서, Revit 플러그인과 같은 외부 응용 프로그램 개발을 통해 구체적이고 반복적인 작업에 자동화가 필요하다. BIM 속성분류체계를 따르면서 사용자의 생산성과 편의성을 강화할 수 있는 BIM 속성입력 프로그램을 구현하였다.

• Asia pacific journal of information systems
• /
• 제29권1호
• /
• pp.65-82
• /
• 2019

Technological innovations over the years have accentuated the workings in corporate- connected organizations and different application platforms. Hence, a unified management information system (MIS) that can utilize the Web and propel programming developments is required. Software agents, the latest developments in computer software technology, can be utilized to rapidly and effortlessly build integrated information systems. Consequently, 59 research papers on the use of software agents in MIS were identified from top 40 MIS journals published between 2007 and 2017. Then, we reviewed and classified all the research papers according to two categories: application fields and application categories. The application fields consisted of eight sub-groups: manufacturing, telecommunication systems, traffic and transportation management, information filtering and gathering, electronic commerce, business process management, entertainment, and medical care; whereas the application categories consisted of three sub-groups: multi-agent systems, personal assistants, and multi-agent simulation. The research papers were further divided into journal and year of publication, and journal and application field. The objective of our research was to understand the trend of the use software agent technology in MIS by examining the published research paper beside to add knowledge and content to the information system academic discipline.

• 시스템엔지니어링학술지
• /
• 제18권1호
• /
• pp.99-104
• /
• 2022

In this paper, to increase the maintenance efficiency of the urban railway train control system and to build a standard data system, we collect as much as possible structured, unstructured, and semi-structured data, and collect data by sensing and monitoring the system status and system status and monitoring. pre-process function data(Identification, purification, integration, transformation) through effective data classification and maintenance activities business classification system was studied. The purpose of this is to define the data matrix model by considering the relationship with the data generated and managed in the O&M stage of the train control system operated by the urban railway together with the WBS model, and to reflect and utilize it in practice.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2011년도 춘계학술대회
• /
• pp.243-250
• /
• 2011

In this study, we examine the changes of the freight transport business penetration system and its classification through the theoretical study. By searching case studies of related systems in developed countries, this thesis derives problem and suggests improvement.