• 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.

• Journal of KIISE:Software and Applications
• /
• v.31 no.6
• /
• pp.716-727
• /
• 2004

Component-based software development (CBD) technology has been widely accepted as a new effective paradigm for building software systems with reusable components, consequently reducing efforts and shortening time-to-market. Hence, components should provide standard or common functionalities in a domain, yielding a higher level of reusability. Especially, micro-level variability within the commonality should also be modeled so that a product member-specific business logic or requirement can be supported through component tailoring or customization The importance of commonality and variability (C&V) analysis has been emphasized in several CBD methods, but they lack of well-defined systematic process, detailed instructions, and standard artifact templates. As the result, the development of components has been carried out in ad-hoc fashion, depending on developer's experience. In this paper, we propose a systematic process and work instructions to design components. The process consists of phases and their activities and each activity is specified with detailed instructions and artifact templates in order to facilitate effective development of components. To verify a feasibility of the propose method, a case study in a banking domain and comparison and assessment between the proposed method and other methods are additionally provided. With proposed processes and instructions, reusability and efficiency of developing components can be better supported.

• Information and Communications Magazine
• /
• v.34 no.1
• /
• pp.41-50
• /
• 2016

사물인터넷 비즈니스의 수요가 증가하면서, 다양한 사물들에 대한 식별 및 데이터 공유 체계와 서비스 디스커버리 표준을 제공하는 GS1 (Global Standard 1) 국제 표준이 글로벌 사물인터넷 표준으로써 자리잡고 있다. 유통/물류분야의 지배적 표준에서 시작한 GS1은 1999년 세계 최초로 사물인터넷(Internet of Things)이란 용어와 개념을 소개한 이후, 스마트팩토리, 헬스케어 서비스 표준에서부터 금융 서비스에 이르기까지, 다양한 산업 도메인 응용의 수평적 통합을 가능하게 하는 데이터 기반의 사물인터넷 표준으로서의 입지를 지속적으로 확장해 나가고 있다. 본 논문에서는 GS1 국제 표준에 대한 전반적인 개념 및 특징을 설명하고 현재 활발히 진행되고 있는 다양한 서비스 표준안들과 GS1 표준의 레퍼런스 구현인 Oliot(Open Language for Internet of Things) 오픈소스 프로젝트를 소개하고, 실제 글로벌 비즈니스에서의 적용 사례들을 살펴봄으로써 사물인터넷 비즈니스 플랫폼으로써의 GS1 표준의 전망을 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.857-860
• /
• 2013

스마트폰의 다양하고 편리한 기능은 휴대전화기 시장의 급속한 성장을 이루어 최근에는 3000만 사용자 수를 넘어서고 있지만, 악성코드와 같은 공격으로 인한 보안 사고 또한 증가하고 있다. 개방성을 지향하는 안드로이드 플랫폼에서는 스미싱과 같은 신종 공격으로 인해 보안 사고가 최근 크게 이슈가 되고 있는 상황이다. 이러한 취약성을 보완하기 위해 기존 스마트폰 운영체제와 별도의 도메인을 분리하여 금융거래나 사용자의 중요 정보는 별도의 보안 운영체제에서 처리하는 모바일 가상화 기술이 대두되고 있다. 향후 이러한 모바일 가상화 기술이 대중화될 경우, 일반적인 포렌식 조사 절차로는 현장에서 확보한 스마트폰의 보안 영역에서는 사건 조사에 필요한 증거 수집이 불가능할 수 있다. 따라서 본 논문에서는 최근의 모바일 가상화 기술을 살펴보고, 이를 바탕으로 가상화 플랫폼 기반 모바일 장비의 포렌식 조사 방안에 대해 살펴보고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1097-1100
• /
• 2020

챗봇(Chatbot)은 자연어처리기술 등 인공지능 기술을 기반으로 한 사용자 친화적인 대화 방식 인터페이스를 제공하는 장점이 있어, 금융, 상담, 주문 등 다양한 산업 분야에서 적용되고 있다. 그러나, 챗봇의 응답이 사용자의 정신 모형과 불일치하는 경우, 다음 대화를 이어가는데 어려움을 야기하게 된다. 그러므로, 챗봇의 사용성을 확보하기 위해서는 응답 오류의 제거 또는 완화가 필수적이다. 기존의 챗봇의 사용성 개선과 관련된 연구들은 설문조사와 인터뷰 등 사용성 평가를 통해 상위 수준의 개선 방향만을 제안하고 있다. 따라서, 챗봇 개발 시, 실무자들이 응답 오류의 문제점을 분석하고, 이를 해결하기 위한 구체적인 개선 방안을 제시하는 데 한계가 있었다. 본 논문에서는 FMEA(Failure Modes and Effects Analysis) 기법을 활용해, 응답 오류의 치명도를 파악하고, 치명적인 오류들에 대해서는 FTA(Fault Tree Analysis) 기법을 기반으로 원인 분석을 실시하여 구체적으로 문제를 해결하기 위한 프로세스를 제안한다. 본 프로세스의 효용성을 검증하기 위해 주문 도메인의 챗봇에 적용해 보았다.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.1-28
• /
• 2021

FinTech has been discussed as an important business area towards technology-driven financial innovation. The term fintech is a combination of finance and technology, which means ICT technology currently associated with all finance areas. The popularity of the fintech industry has significantly increased over time, with full investment and support for numerous startups. Therefore, both academia and practice tried to analyze the trend of the fintech area. Despite the fact, however, previous research has limitations in terms of collecting relevant databases for fintech and identifying proper application areas. In response, this study proposed a new method for analyzing the trend of Fintech fields by expanding Fintech's terminology and using network analysis and topic modeling. A new Fintech terminology list was created and a total of 18,341 patents were collected from USPTO for 10 years. The co-classification analysis and network analysis was conducted to identify the technological trends of patent classification. In addition, topic modeling was conducted to identify the trends of fintech in order to analyze the contents of fintech. This study is expected to help both managers and investors who want to be involved in technology-driven financial services seize new FinTech technology opportunities.

• Information Systems Review
• /
• v.21 no.2
• /
• pp.117-137
• /
• 2019

In the Big Data era, data science has become popular with the production of numerous data in various domains, and the power of data has become a competitive power. There is a growing interest in unstructured data, which accounts for more than 80% of the world's data. Along with the everyday use of social media, most of the unstructured data is in the form of text data and plays an important role in various areas such as marketing, finance, and distribution. However, text mining using social media is difficult to access and difficult to use compared to data mining using numerical data. Thus, this study aims to develop Korean Natural Language Application (KoALA) as an integrated application for easy and handy social media text mining without relying on programming language or high-level hardware or solution. KoALA is a specialized application for social media text mining. It is an integrated application that can analyze both Korean and English. KoALA handles the entire process from data collection to preprocessing, analysis and visualization. This paper describes the process of designing, implementing, and applying KoALA applications using the design science methodology. Lastly, we will discuss practical use of KoALA through a block-chain business case. Through this paper, we hope to popularize social media text mining and utilize it for practical and academic use in various domains.

• The KIPS Transactions:PartC
• /
• v.12C no.2 s.98
• /
• pp.301-308
• /
• 2005

According to banking online transaction grows very rapidly, guarantee validity about business transaction has more meaning. To offer guarantee validity about banking online transaction efficiently, certificate status verification system is required that can an ieai-time offer identity certification, data integrity, guarantee confidentiality, non-repudiation. Existing real-time certificate status verification system is structural concentration problem generated that one node handling all transactions. And every time status verification is requested, network overload and communication bottleneck are occurred because ail useless informations are transmitted. it does not fit to banking transaction which make much account of real response time because of these problem. To improve problem by unnecessary information and structural concentration when existing real-time certificate status protocol requested , this paper handle status verification that break up inspection server by domain. This paper propose the method of real~time certificate status verification that solves network overload and communication bottleneck by requesting certification using really necessary Reduction information to certification status verification. And we confirm speed of certificate status verification $15\%$ faster than existing OCSP(Online Certificate Status Protocol) method by test.

• Journal of Korea Technology Innovation Society
• /
• v.17 no.4
• /
• pp.786-819
• /
• 2014

Emphasizing the importance of R&D as a source of open innovation, Korean government is developing various programs focused on technology commercialization and is expanding investment on it. In spite of those efforts, technology commercialization is not vitalized yet due to the lack of demand for technology transfer, R&D planning scheme without considering market, immaturity of technology market, and so on. This study aims to suggest the business ecosystem model so that technology commercialization could be facilitated based on business ecosystem perspective. We set the framework for modeling a business ecosystem through reviewing the previous works, and draw several problems to be solved regarding public R&D commercialization in Korea from the perspective of ecosystem. Considering those, this research proposes the business ecosystem model for public R&D commercialization as a reference model for describing, discussing, and developing the technology commercialization strategy. The proposed model consists of 4 domains as follows: R&D, technology market, information distribution channels, and customers. The business ecosystem model shows that technology commercialization could be facilitated to create the market value through close relationship and organic cooperation among its members that form the ecosystem. Public research institutes as a keystone player could control the fate of the ecosystem. In this regard, this paper suggests roles of public research institutes for evolving the business ecosystem.

• Journal of Service Research and Studies
• /
• v.10 no.4
• /
• pp.57-70
• /
• 2020

Globally, cloud service is a core infrastructure that improves industrial productivity and accelerates innovation through convergence and integration with various industries, and it is expected to continuously expand the market size and spread to all industries. In particular, due to the global pandemic caused by COVID-19, the introduction of cloud services was an opportunity to be recognized as a core infrastructure to cope with the untact era. However, it is still at the preliminary stage for market expansion of cloud service in Korea. This paper aims to empirically analyze how cloud services can be accepted by users by each industry through extended Technology Acceptance Model(TAM), and what factors influence the acceptance and avoidance of cloud services to users. For this purpose, the impact and factors on the acceptance intention of cloud services were analyzed through the hypothesis test through the proposed extended technology acceptance model. The industrial sector selected four industrial sectors of education, finance, manufacturing and health care and derived factors by examining the parameters of TAM, key characteristics of the cloud and other factors. As a result of the empirical analysis, differences were found in the factors that influence the intention to accept cloud services for each of the four industry sectors, which means that there is a difference in perception of the introduction or use of cloud services by industry sector. Eventually it is expected that this study will not only help to understand the intention of using cloud services by industry, but also help cloud service providers expand and provide cloud services to each industry.