• 한국정보시스템학회지:정보시스템연구
• /
• 제29권1호
• /
• pp.241-265
• /
• 2020

Purpose Various machine learning techniques are used to implement for predicting corporate credit. However, previous research doesn't utilize time series input features and has a limited prediction timing. Furthermore, in the case of corporate bond credit rating forecast, corporate sample is limited because only large companies are selected for corporate bond credit rating. To address limitations of prior research, this study attempts to implement a predictive model with more sample companies, which can adjust the forecasting point at the present time by using the credit score information and corporate information in time series. Design/methodology/approach To implement this forecasting model, this study uses the sample of 2,191 companies with KIS credit scores for 18 years from 2000 to 2017. For improving the performance of the predictive model, various financial and non-financial features are applied as input variables in a time series through a sliding window technique. In addition, this research also tests various machine learning techniques that were traditionally used to increase the validity of analysis results, and the deep learning technique that is being actively researched of late. Findings RNN-based stateful LSTM model shows good performance in credit rating prediction. By extending the forecasting time point, we find how the performance of the predictive model changes over time and evaluate the feature groups in the short and long terms. In comparison with other studies, the results of 5 classification prediction through label reclassification show good performance relatively. In addition, about 90% accuracy is found in the bad credit forecasts.

• 동아시아경상학회지
• /
• 제9권3호
• /
• pp.15-28
• /
• 2021

Purpose -In the credit transaction, the issuing bank must examine the documents to pay the credit amount. In order to smoothly execute the credit transaction, document review is a key element, so the 5th revised credit unification rule specifically defines the document review procedure. Research design, data, and methodology - The document review procedure specified in the UCP Rules can be largely divided into the document review period and the rejection procedure for inconsistent documents. First of all, confusion was caused by the ambiguous regulation.. Result - With regard to the document review period, in the actual credit transaction, the issuing bank often negotiates with the issuing client about the waiver of the document inconsistency. Next, in the process of notifying the rejection of inconsistent documents, the issuing bank shall send the rejection notice. Conclusion - This study suggests that the requirement to list all inconsistencies makes it impossible for the issuing bank to further notify the refusal, thereby limiting the right to defend against inconsistencies not listed in the first refusal notice and consequently having the effect of matching them. In addition, the issuing bank's rejection notice is closely related to the beneficiary's exercise of the right to replenish documents.

• 산경연구논집
• /
• 제13권10호
• /
• pp.1-8
• /
• 2022

Purpose: Support vector machines (SVMs) ensemble has been proposed to improve classification performance of Credit risk recently. However, currently used fusion strategies do not evaluate the importance degree of the output of individual component SVM classifier when combining the component predictions to the final decision. To deal with this problem, this paper designs a support vector machines (SVMs) ensemble method based on fuzzy integral, which aggregates the outputs of separate component SVMs with importance of each component SVM. Research design, data, and methodology: This paper designs a personal credit risk evaluation index system including 16 indicators and discusses a support vector machines (SVMs) ensemble method based on fuzzy integral for designing a credit risk assessment system to discriminate good creditors from bad ones. This paper randomly selects 1500 sample data of personal loan customers of a commercial bank in China 2015-2020 for simulation experiments. Results: By comparing the experimental result SVMs ensemble with the single SVM, the neural network ensemble, the proposed method outperforms the single SVM, and neural network ensemble in terms of classification accuracy. Conclusions: The results show that the method proposed in this paper has higher classification accuracy than other classification methods, which confirms the feasibility and effectiveness of this method.

• 교육녹색환경연구
• /
• 제19권4호
• /
• pp.70-77
• /
• 2020

본 연구에서는 고교학점제를 포함하여 학교 공간에 관한 많은 선행연구를 검토하여 고교학점제 교육환경 구성 시 가장 적합한 요소를 도출한 후 중요도 분석을 제시하고자 한다. 이에 분석요인으로 도출된 중요도 분석을 통하여 각 단위학교의 고교학점제 교육환경 조성에 기초적인 자료로 제공하고 고교학점제에 따른 교육환경의 공간적 중요도를 통한 교육정책적 방향 선정시 신축학교와 기존 학교의 차별화된 접근 방향에 도움이 되고자 한다. 연구의 방법으로서 관련 전문가를 통한 계층화 의사결정방법을 통하여 교육환경의 중요도 분석을 시행하였다. 분석결과 교육환경 구축을 위해 전략적 중요도를 중심으로 선택적이고 집중적으로 교육환경의 기능을 수행하고 그 활성화를 극대화하는 교육과정과 교육환경의 상호관계 등에 대한 분석적 고찰이 필요한 것으로 나타났다.

• 수산해양교육연구
• /
• 제27권6호
• /
• pp.1546-1555
• /
• 2015

This study was performed to analyze the item characteristics of competency inventory for designer (CID), which Gil (2011) developed for measurement of design competency. To accomplish the purpose of this study, general partial credit (GPC) model based on polytomous item response theory was applied. The findings were as follows: First, CID is a reliable instrument for measuring design competency. Second, most items of CID have low item discrimination and average item difficulty according to the GPC model. Especially, there are some problems to have low item discrimination in view of validation. To improve the goodness of CID, we will need to examine why CID has low item discrimination.

• 인터넷정보학회논문지
• /
• 제7권1호
• /
• pp.121-130
• /
• 2006

차세대 무선 네트워크에서는 응용들이 실시간 선불 서비스를 제공해야 하며, 최종 사용자에게 서비스를 제공하기 이전에 요청된 서비스에 대해 신용을 사전 체크하여야 한다. 또한 선불서비스를 효과적으로 제공하기 위해서는 신용제어 기능이 최소한의 지연만을 가져야 한다. 본 논문에서는 모바일 IPv6 환경에서 실시간 신용제어가 가능한 권한검증 구현 모델을 제안하였다. 제안한 모델은 일반적인 신용제어 권한검증 절차와 모바일 IPv6 인증 절차를 통합한 구조를 갖는다. 지연을 최소화하기 위해 제안한 모델을 싱글 서버 내에 구현하였으며, 이 시스템은 권한검증과 인증을 동시에 수행한다. 구현한 시스템의 구현구조를 소프트웨어 기능 블록과 유니트 형태로 제시하였다. 구현한 모델의 feasibility를 검증하기 위해서 구현한 시스템의 지연을 측정하였으며 측정 시, 몇 가지 인증 확장 프로토콜 (EAP)을 적용하였다. 측정된 결과에 따르면 신용제어 권한검증과 인증이 분리된 기존 모델과 비해서 제안한 통합 모델이 상대적으로 지연시간이 적었다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제30권4호
• /
• pp.203-226
• /
• 2021

Purpose The purpose of this study is to enhance the accuracy score of personal credit scoring using the convolutional neural networks and secure the transparency of the deep learning model using eXplainalbe Artifical Inteligence(XAI) technique. Design/methodology/approach This study built a classification model by using the convolutional neural networks(CNN) and applied a methodology that is transformation of numerical data to imaged data to apply CNN on personal credit data. Then layer-wise relevance propagation(LRP) was applied to model we constructed to find what variables are more influenced to the output value. Findings According to the empirical analysis result, this study confirmed that accuracy score by model using CNN is highest among other models using logistic regression, neural networks, and support vector machines. In addition, With the LRP that is one of the technique of XAI, variables that have a great influence on calculating the output value for each observation could be found.

• 유통과학연구
• /
• 제22권3호
• /
• pp.49-58
• /
• 2024

Purpose: Research on financial development plays a crucial role in guiding and implementing policies for both financial development and economic growth. This study aims to evaluate the impact of financial development on the economic growth of Southeast Asian countries. Research design, data and methodology: The research utilizes data from 11 Southeast Asian countries from 2015 to 2022. Financial development data is proxied by credit distribution in private sector. Results: Based on the analysis using the FGLS model, it indicates that financial development has a positive impact on the economic growth of Southeast Asian countries. In addition, the study also examines the impact of state investment costs and FDI investment on economic growth. The results also show that foreign direct investment flows still play an important role in Southeast Asian countries (FDI has a positive impact on economic growth). State investment costs also impact economic growth, showing that the development of public investment also brings good development to countries. Conclusions: These results suggest that credit policies for financial development in general, and the development of private credit in particular, play a significant role in these countries. Building a system to promote the activities of private sector economies will help stimulate the economic development of Southeast Asian countries.

• 한국의상디자인학회:학술대회논문집
• /
• 한국의상디자인학회 2005년도 Fasion road:Korea to belarus
• /
• pp.33-34
• /
• 2005

• 아태비즈니스연구
• /
• 제11권3호
• /
• pp.199-215
• /
• 2020

Purpose - This article tries to test if the conditional consumption capital asset pricing model (CCAPM) with bank credit for household as a conditional variable can explain the cross-sectional variation of stock returns in Korea. The performance of conditional CCAPM is compared to that of multifactor asset pricing models based on Arbitrage Pricing Theory. Design/methodology/approach - This paper extends the simple CCAPM to the conditional version of CCAPM by using bank credit for household as conditioning information. By employing KOSPI and KOSDAQ stocks as test assets from the second quarter of 2003 to the first quarter of 2018, this paper estimates risk premiums of conditional CCAPM and a variety of multifactor linear models such as Fama-French three and five-factor models. The significance of risk factors and the adjusted coefficient of determination are the basis for the comparison in models' performances. Findings - First, the paper finds that conditional CCAPM with bank credit performs as well as the multifactor linear models from Arbitrage Pricing theory on 25 test assets sorted by size and book-to-market. When using long-term consumption growth, the conditional CCAPM explains the cross-sectional variation of stock returns far better than multifactor models. Not only that, although the performances of multifactor models decrease on 75 test assets, conditional CCAPM's performance is well maintained. Research implications or Originality - This paper proposes bank credit for household as a conditional variable for CCAPM. This enables CCAPM, one of the most famous economic asset pricing models, to conform with the empirical data. In light of this, we can now explain the cross-sectional variation of stock returns from an economic perspective: Asset's riskiness is determined by its correlation with consumption growth conditional on bank credit for household.