• Journal of the Korean Data and Information Science Society
• /
• v.26 no.6
• /
• pp.1207-1216
• /
• 2015

This study aims to compare the model power in developing corporate credit rating models and to suggest a good way to build models based on the characteristic of data. Among many measurement methods, AR is used to measure the model power under various conditions. SAS/MACRO is in use for similar repetitions to reduce time to build models under several combination of conditions. A corporate credit rating model is composed of two sub-models; a credit scoring model and a default prediction model. We verify that the latter performs better than the former under various conditions. From the result of size comparisons, models of large size corporate are more powerful and more meaningful in financial viewpoint than those of small size corporate. As a corporate size gets smaller, the gap between sub-models becomes huge and the effect of outliers becomes serious.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.467-474
• /
• 2024

This study analyses customer data from a US online lending platform to empirically document the discriminatory treatment that low- and middle-income borrowers face in financial markets. Researchers are using financial data from nearly 2.93 million loans between 2007~2020 of the Lending Club on the open-source Kaggle platform. We find that thin-filers borrowers, especially those with lower credit scores, receive loans at higher interest rates. This discriminatory treatment undermines financial inclusion and has the potential to increase social inequality. The significance of this research is that it sheds substantial light on the problem of inequality in financial markets and, based on the findings, suggests concrete measures to ensure equitable access to finance for all customers and enhance sustainable financial inclusion. In doing so, we propose a shift towards enhancing the social responsibility of institutions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2000.05a
• /
• pp.268-273
• /
• 2000

기존의 웹 기반 학습 평가 시스템은 학습자의 선택 기회가 없는 상태에서 일방적으로 제시된 문제지로 평가하게 되거나, 문제 은행에서 임의로 추출한 문제도 단순히 무작위로나 난이도만을 고려하여 문제지를 구성하였고, 그 결과에 대한 성취도의 분석도 한 문제지에 대한 정오표 또는 점수로 단순하게 제시하기 때문에 학습자의 지속적인 학습 관리가 이루어지지 못하고 있다. 본 논문에서는 문제유형, 과목 및 단원 난이도, 문항 형태, 문항당 배점, 문항당 배당 시간등의 다양한 정보를 가진 유형별 문제 은행을 구축하였다. 학습자는 마치 문제집을 풀고 싶은 유형의 문제를 선택하듯이 문제 은행에서 문제를 자율적으로 구성하여 평가할 수 있는 유형별 문제지나 대학수학능력시험의 기준에 맞추어 자동 구성되는 종합 문제지로 다양하게 평가할 수 있다. 또한, 한문제지에 대한 결과뿐만 아니라 유형별, 월별 성취도 분석을 통하여 평가한 총점에 대한 획득한 점수의 누적 통계를 그래프로 일목요연하게 보여주어 한 학습자에 대한 지속적인 성취도 분석이 가능하도록 구축하였다.

• International Area Studies Review
• /
• v.22 no.2
• /
• pp.61-91
• /
• 2018

Credit Guarantee scheme is one of the most effective tools for the small business policy. The performance analysis on domestic institution level is relevant in terms of various factors of assisting tools factor. This study measured comparative global efficiency by DEA model and Super-efficiency model among 70 credit guarantee institutions in Japan, Taiwan, and Korea who are operating the schemes. At the result of the analysis, Korean credit guarantee institutions are comparatively efficient than Japanese institutions, and the DMU shows moderate in operation efficiency. The Super-efficiency ranked by Hiroshima, Taiwan SMEG, Pusan, Chiba, Shizuoka, Ulsan, and KOTEC. Most of the Credit Guarantee Institutions showed increasing returns to scale, and it indicates increasing input strategy. The statistical difference of efficiency level in Japan and Korea shows very meaning numbers. This research suggest that (1)Periodical Analysis are needed on Japanese Schemes, (2)The analysis on the impact of credit guarantee scale to the national economy and SME policy, (3) Analysis on the conclusive factors of the efficiency, (4)The policy direction has to be made by inefficient factor analysis, (5) The measurement tools of efficiency of the schemes in various aspects.

• Journal of the Korea society of information convergence
• /
• v.6 no.2
• /
• pp.23-44
• /
• 2013

First, the average scores of personal financial management ability in the college students' financial management attitude were 72.24 for male and 71.65 for female, so that male students showed a little higher score than female. College students who had an experience of opening a bank account and who kept a record of spending revealed higher scores. Those whose parents were elementary or middle school graduates unfolded the highest score, 73.67, and the lowest score, 63.35, from those whose parents had M.A. or Ph.D. The average scores of personal financial management ability in the college students' financial management knowledge indicated almost no difference with 63.26 for male and 63.35 for female. Only whether they had an experience of opening a bank account, keeping a record of spending, or a credit card revealed score differences. Depending on the students' majors, there were also score differences. Students from engineering department came up with the highest score, an average of 66.88, and students from art & physical education department with the lowest score, 53.39, in the financial management knowledge. The personal financial management ability in the college students' financial management function showed that the score of male students was a little higher than that of female, 64.26 versus 63.58. Students who kept a record of spending and whose parents' income was between three million won and four million won marked the highest score, an average of 65.26, and students whose parents' income was below two million won marked the lowest score, an average of 60.43, in the college students' financial management function. There were score differences in the college students' financial management function depending on the students' majors. Students from engineering department came up with the highest score, an average of 69.67, and students from public health department with the lowest score, 63.21.

• The Journal of Society for e-Business Studies
• /
• v.22 no.4
• /
• pp.159-173
• /
• 2017

In order to provide technical financial support to small and medium-sized venture companies based on technology, the government implemented the TCB evaluation, which is a kind of technology rating evaluation, from the Kibo and a qualified private TCB. In this paper, we briefly review the current state of TCB evaluation and available indicators related to technology evaluation accumulated in the Korea Credit Information Services (TDB), and then use indicators that have a significant effect on the technology rating score. Multiple regression techniques will be explored. And the relative importance and classification accuracy of the indicators were calculated by applying the key indicators as independent features applied to the generalized boosting model, which is a representative machine learning classifier, as the class influence and the fitness of each model. As a result of the analysis, it was analyzed that the relative importance between the two models was not significantly different. However, GBM model had more weight on the InnoBiz certification, R&D department, patent registration and venture confirmation indicators than regression model.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.26-28
• /
• 2017

스마트폰 보유율과 모바일 이용 행태가 급변함에 따라 방송사에서는 양방향 서비스를 포함한 다양한 방송 서비스를 제공하려고 노력하고 있다. 양방향 서비스 방송에서 시청자가 보낸 문구를 실제 화면에 보여주기까지 PD 와 담당자들의 수작업이 필요하다. 하지만 하루 평균 약 7,200 건 (MBC 오늘아침 소통중계)의 양방향 서비스 관련 로그가 남게 되어, PD 가 일일이 판별하기에는 많은 노력이 따른다. 이러한 불필요한 노력을 줄이기 위해 본 논문에서는 감정 분석을 이용한 딥러닝 인공지능 기반 양방향 서비스 방송 소프트웨어 시스템을 제안한다. 첫째, 시청자들이 전송한 의견, 건의사항, 내용 등을 전처리 과정을 진행한다. 둘째, 감정 사전을 이용해 전처리 된 단어와 비교하여 시청자가 보낸 문구의 감정 점수를 계산한다. 셋째, 과거 실제 방송에 송출된 시청자 문구를 감정 점수와 함께 딥러닝을 이용하여 훈련시킨다. 본 논문의 성능을 평가하기 위해, 2017 년 생방송 오늘아침 소통중계에 사례연구를 진행하였고 효율성을 보였다. 앞으로 이러한 양방향 서비스 방송 소프트웨어 시스템 도입으로, PD 가 방송 제작에 더욱 집중 할 수 있도록 차별화된 방송을 준비하는데 크게 기여할 것이라 기대한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1336-1339
• /
• 2013

SCTR(StockCharts Technical Ranks)는 주식시장의 주가 상승 강도를 기술적 분석(Technical Analysis)의 6가지 지표에 따라 점수화하여 순위로 나타낸 것이다. 본고에서는 SCTR을 이용하여 국내 주가지수에서 거래되는 증권의 매수 및 매도를 추천하는 시스템을 제시한다. 매수 및 매도의 추천은 유전 알고리즘에 의하여 매매의 신호를 잘 반영하는 SCTR Oscillator 값을 적용한다. 이를 위하여 SCTR을 산출하고, 유전 알고리즘으로 모의투자 하여 구한 상한선과 하한선을 기준으로 주가의 추세를 분석하여 종목을 추천하는 시스템을 구현한다.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.3
• /
• pp.257-267
• /
• 2022

The employment effect of innovation-certified SMEs (venture certification, inno-biz certification and main-biz certification) and general SMEs was compared and analyzed. Through propensity score matching, general SMEs with similar tendencies to SMEs for each innovation certification were selected. The employment effect was approached from two perspectives: the absolute employment effect, the employment growth rate, and the relative employment effect, the sales-employment coefficient. As a result of the analysis, it was confirmed that venture certified SMEs and inno-biz certified SMEs, which are technology innovation-type certifications, have an advantage in absolute employment effect. In addition, it was concluded that innovation-certified SMEs have more room for employment than general SMEs by achieving sales growth that exceeds employment growth. Therefore, there is a possibility to enhance the employment effect of innovation-certified SMEs by strengthening employment-related incentives for innovation-certified SMEs.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2006.06a
• /
• pp.176-182
• /
• 2006

본 연구에서는 기존 Bagging Predictors에 수정을 가한 Modified Bagging Predictors를 이용하여 SOHO 에 대한 부도예측 모델을 제시한다. 대기업 및 중소기업에 대한 기압부도예측 모델에 대한 많은 선행 연구가 있어왔지만 SOHO 만의 기업부도예측 모델에 관한 연구는 미비한 상태이다. 금융기관들의 대출심사시 대기업 및 중소기업과는 달리 SOHO에 대한 대출심사는 이직은 체계화되지 못한 채 신용정보점수 등의 단편적인 요소를 사용하고 있는 것에 현실이고 이에 따라 잘못된 대출로 안한 금융기관의 부실화를 초래할 위험성이 크다. 본 연구에서는 실제 국내은행의 SOHO 데이터 집합이 사용되었다. 먼저 기업부도 예측 모델에서 우수하다고 연구되어진 인공신경망과 의사결정나무 추론 기법을 적용하여 보았지만 만족할 만한 성과를 이쓸어내지 못하여, 기존 기업부도예측 모델연구에서 적용이 미비하였던 Bagging Predictors와 이를 개선한 Modified Bagging Predictors를 제시하고 이를 적용하여 보았다. 연구결과,; SOHO 부도예측에 있어서 본 연구에서 제시한 Modified Bagging Predictors 가 인공신경망과 Bagging Predictors등의 기존 기법에 비해서 성과가 향상됨을 알 수 있었다. 제시된 Modified Bagging Predictors의 유용성을 확인하기 위해서 추가적으로 대수의 공개 데이터 집합을 활용하여 성능을 비교한 결과 Modified Bagging Predictors 가 기존의 Bagging Predictors 에 비해 일관적으로 성과가 향상됨을 알 수 있었다.