• Information Systems Review
• /
• v.24 no.1
• /
• pp.105-123
• /
• 2022

Thanks to the remarkable success of Artificial Intelligence (A.I.) techniques, a new possibility for its application on the real-world problem has begun. One of the prominent applications is the bankruptcy prediction model as it is often used as a basic knowledge base for credit scoring models in the financial industry. As a result, there has been extensive research on how to improve the prediction accuracy of the model. However, despite its impressive performance, it is difficult to implement machine learning (ML)-based models due to its intrinsic trait of obscurity, especially when the field requires or values an explanation about the result obtained by the model. The financial domain is one of the areas where explanation matters to stakeholders such as domain experts and customers. In this paper, we propose a novel approach to incorporate financial domain knowledge into local rule generation to provide explanations for the bankruptcy prediction model at instance level. The result shows the proposed method successfully selects and classifies the extracted rules based on the feasibility and information they convey to the users.

• The KIPS Transactions:PartD
• /
• v.18D no.4
• /
• pp.287-298
• /
• 2011

With the rage for Netbooks recently, Tablet PC and Smart phone users are rapidly increasing. Despite of the forecast that anticipates frequently practical use in various organizations and society, the comparison studies among the mobile devices rarely exist. The study examines the acceptable intention of the mobile devices, with which can replace traditional workstations and notebooks. UTAUT(Unified Theory of Acceptance and Use of Technology) was applied to the investigation of influencing factors for the acceptable intention, instead of the typical TAM(Technology Acceptance Model). The results illustrate that the significant differences of acceptable intention among the mobile devices occur based on two-side network effect even though some Smart phones share OSs and Apps with Tablet PCs and Netbooks.

• Journal of KIISE:Software and Applications
• /
• v.26 no.9
• /
• pp.1105-1113
• /
• 1999

객체 지향 소프트웨어의 확장과 더불어 소프트웨어의 재사용성의 중요도가 부각되면서 소프트웨어를 콤포넌트 단위로 구현하는 추세이다. 따라서 콤포넌트 기반의 소프트웨어 개발에서의 통합 테스트가 중요한 이슈로 떠오르고 있다. 그러나 콤포넌트들의 통합 테스트에 대한 연구는 미흡한 상태이다. 본 논문에서는 UML을 기반으로 체계적인 통합 테스트 모형을 제안하고. 나아가 본 논문에서는 "멀티미디어 정보처리 시스템"의 사례를 본 논문의 콤포넌트 통합 테스트 모형에 적용한 결과를 분석하여 기술한다. 콤포넌트 통합 테스트 모형은 UML(Unified Modeling Language)의 순서도(sequence diagram)와 협력도(collaboration diagram)를 이용하여 전체 시스템에서 UML의 사건흐름을 구성하는 콤포넌트들 사이의 인터페이스 영역에 존재하는 오류들을 추출한다. 그리고 UML을 기반으로 통합 테스트를 수행함으로써, 테스트 준비 작업을 줄이고, 기존의 UML 지원 도구들과 연계하여 테스트 자동화 도구의 구현을 앞당길 수 있다. 또한 시스템의 순차적 흐름 뿐 아니라, 동시에 수행되는 흐름에 대한 정보까지 모두 수용하여 테스트함으로써, 콤포넌트 기반의 분산 환경의 특성에 적합하다. Abstract As the object-oriented approach to software development becomes more mature, software development from pre-existing, independently developed components becomes an important aim of software engineering. Therefore, integration testing becomes an important aspect of component-based software development. However, there has been little work done in the area of the component-based integration testing. In this paper, we propose the "component integration test model" which is based on UML. Furthermore, we describe a case study on "Multimedia Information Processing System" conducted to analyse the result from which our model is applied. Our model extracts the faults, which exist in interfaces of components, using sequence diagram and collaboration diagram of UML(Unified Modeling Language). As our model is based on UML, the preparation effort for testing is reduced and its test-tools can be implemented more easily through linking existing UML tool. And our model accepts the information of concurrent flow represented by collaboration diagram as well as sequential flow, so it is more suitable to component-based distributed environment.based distributed environment.

• The Journal of Society for e-Business Studies
• /
• v.13 no.2
• /
• pp.117-147
• /
• 2008

Developing various ubiquitous computing services (U-services) is being propelled throughout the industry. As U-services are being penetrated into our daily life, research on the factors influencing the acceptance of U-services is highly needed. In this line of study, we examined previous literatures about information technology acceptance and UTAUT model, and applied UTAUT model to U-service acceptance. To characterize the U-services into our research model, we newly introduced 'context based personalization' factor. Since the respondents could not directly experience the U-services yet, we adopted scenario-based questionnaire. For this, we deliberately developed U-service scenario. And then this U-service scenario is verified using capability-based assessment method. Using data collected from 251 respondents, this study found that 'context based personalization' factor was positively and significantly related to the acceptance of U-service as well as UTAUT model's 4 factors such as performance expectancy, effort expectancy, social influence and facilitating conditions.

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.101-114
• /
• 2021

This study aimed to analyze the degree of consumers' expectations for their performance and efforts in using overseas direct purchase, impact of overseas direct purchase on the society, and effect of price value to their intention to use overseas direct purchase in the future. In addition, the significance of overseas direct purchase on the user-perceived availability is empirically analyzed. As a result of the study, it was confirmed that performance expectancy, effort expectancy, social influence, and price value showed significantly positive effect on the intention to use overseas direct purchase in the future. With respect to the perceived availability in using overseas direct purchase, it was found out that effort expectancy and price value had significantly positive effect; however, it appeared that performance expectancy and social influence had no significant effect on the perceived availability of the users.

• Journal of the Korean Society for information Management
• /
• v.34 no.2
• /
• pp.47-80
• /
• 2017

The purpose of this study is to develop an adoptive model of institutional repositories (IRs) by identifying the key factors affecting adoptive intention of IRs and explaining the relations among these factors. Through a survey of 270 researchers and 12 in-depth interviews in the field of physics, mathematics, and life science in Korea, performance expectancy, perceived risks, socio-organizational influence, and individual characteristics were found to have substantial influences on the adoptive intention of IRs. Among the key factors, individual characteristics showed the greatest effect on the adoptive intention of IRs, followed by performance expectancy and other socio-organizational influences except for the perceived risks. Strategies to enhance the adoptive intention of IRs based on analyses of the results were suggested, in terms of the reformation of research assessment system at the national level, strengthening of role of the operational institution, and the need for voluntary scientists-participating service.

• Informatization Policy
• /
• v.24 no.1
• /
• pp.79-99
• /
• 2017

Despite the early success story, the pan-industry diffusion of big data has been slow mostly due to lack of confidence of the value creation and privacy-related concerns. The problem leads us to the need to a stakeholder analysis on the adoption process of big data. The present study combines technology acceptance model, task-technology fit theory, and privacy calculus theory to integrate the positive and negative factors on the big data adoption. The empirical analysis was performed based on the survey from the current and potential big data users. Results revealed perceived usefulness, task-technology fit, and privacy concern are significant antecedents to the intention to use big data. Furthermore, there are significant differences in the perceptions of each constructs among groups divided by the types of big data use, with several exceptions. And the control effect was found in the magnitude of the relation between independent variables and dependent variable. The theoretical and politic implications of the analysis are discussed as to the promotion of big data industry.

• International Commerce and Information Review
• /
• v.16 no.3
• /
• pp.25-50
• /
• 2014

This study is to identify the factors and explore the moderating effects of gender in influencing customer behavioral intention to adopt mobile commerce in Shanghai and Guangzhou in China. An extended study based on TRA, TPB and TAM, UTAUT, technology adoption model is applied for designing on this study model of behavioral intention to adopt mobile commerce focused on emotional variables and cross-gender differences. The results of analysis reveal that the effects of perceived risk, personal innovativeness, individual familarity and social influence on behavioral intentions to adopt mobile commerce as well as to differ across gender. Differences cross gender is specially the perceived risk and social influence. Findings imply that mobile commerce operators need to be communicated to female consumers, the risk-free quality including security, payment and certification system along with the social influence of using mobile commerce. When targeting female consumers in China, the word of mouth marketing strategic approach and improvement of communications of mobile commerce should be focused.

• 한국IT서비스학회:학술대회논문집
• /
• 2007.11a
• /
• pp.473-478
• /
• 2007

본 연구는 데이터 품질개선을 위해 사용자들에게 베타데이터 관리 시스템 사용의도에 영향을 줄 수 있는 주요 요인들이 무엇이 있는지 식별해보고 요인간의 관련성을 분석 하였다. 최근 이슈화고 있는 Data Architecture, Data Integration, Data Quality 프로젝트를 계획 또는 경험이 있는 조직 IT담당자들을 대상으로 메타데이터 관리 시스템 사용의도 설문을 하였고, SPSS를 이용하여 통계적 희귀분석을 수행하였다. 분석에서 이를 설명하는 연구모형으로 정보기술수용모델(Technology Acceptance Model:TAM)을 적용하였으며, 사용 용이성(Perceived easy of use), 유용성(perceived usefulness)에 영향을 주는 외생변수로는 개인의 데이터 품질개선의도, 동기부여, 조직의 지원 등으로 나타났다. 분석결과 데이터품질 개선의도가 시스템 사용의도에 영향이 있음을 실증하였고, 사회적 요인(동기부여, 조직의 기원) 모두 유용성에는 영향을 미쳤으나 사용 용이성에는 유의하지 많은 결과를 보였다. 이 연주에서는 조직이 데이터 품질 개선을 위해 메타데이터 관리시스템을 사용하고자 할 경우 고려사항과 향후 사용자 관점의 기술수용들을 확장된 연구를 수행하여 데이터품질 개선에 방안들을 탐색할 것을 제안하였다.

• Journal of Digital Convergence
• /
• v.18 no.7
• /
• pp.123-133
• /
• 2020

The aim of this study is to scrutinize acceptance intentions of Korean users and influences of information security related factors on mobile payment services based on biometric authentication methods, like finger print authentication or face recognition authentication, by focusing on ApplePay. Unlike previous studies on user acceptance of mobile payment which lack considerations on information security related factors, this study employs the UTAUT with detailed information security factors to create a research model and PLS(Partial Least Squares) method to analyze the model. Based on the analysis, gaining trust on service through company's efforts on information protection, personal characteristics and trust on applied security technologies are important factors to Korean users along with social awareness and service infrastructures. The result of this study would be helpful to companies or organizations, which provide biometric-based mobile payment services, to understand needs of Korean consumers. Based on this study, further analysis is expected to find impacts of user experiences on same company's or competitors' products to acceptance intentions.