• 한국벤처창업학회:학술대회논문집
• /
• 2020.06a
• /
• pp.173-190
• /
• 2020

본 연구는 2014년부터 2019년 9월 현재 신용보증기금의 자료를 이용하여 5,521 샘플의 중소상공인의 금융실태를 최초로 광범위하게 분석하였다. 중소상공인의 비중은 남성 장년층이 압도적인데 여성의 경우 청년의 비중이 높은 편이다. 기업 대부분에서 창업자와 대표자가 동일인이다. 상시 및 비상시 직원수는 5명이하가 83%에 달한다. 역시 80% 이상의 중소상공인이 2억 미만의 금액에 대하여 대출보증 서비스를 이용하고 있다. 신보의 재무등급점수는 100점 만점 중 10점 이하의 기업이 47%에 달한다. 2018년 연매출액 평균은 17억원 정도다. 같은 기간 중 부채비율의 평균은 361%다. 본 연구는 향후 중소상공인에 대한 연구와 정책개발에 중요하게 활용될 것으로 기대한다.

• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.71-78
• /
• 2019

This study aims to identify good borrowers within the context of P2P lending. P2P lending is a growing platform that allows individuals to lend and borrow money from each other. Inherent in any loans is credit risk of borrowers and needs to be considered before any lending. Specifically in the context of P2P lending, traditional models fall short and thus this study aimed to rectify this as well as explore the problem of class imbalances seen within credit risk data sets. This study implemented an over-sampling technique known as Synthetic Minority Over-sampling Technique (SMOTE). To test our approach, we implemented five benchmarking classifiers such as support vector machines, logistic regression, k-nearest neighbor, random forest, and deep neural network. The data sample used was retrieved from the publicly available LendingClub dataset. The proposed SMOTE revealed significantly improved results in comparison with the benchmarking classifiers. These results should help actors engaged within P2P lending to make better informed decisions when selecting potential borrowers eliminating the higher risks present in P2P lending.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.153-158
• /
• 2024

Recently, concerns about the spread of credit risk in China's real estate market are gradually increasing. Therefore, it is very meaningful to diagnose the management stability of Chinese commercial banks. This study analyzes the impact of housing prices on the loan proportion and management stability of Chinese commercial banks. In addition, we classify Chinese commercial banks according to size and verify whether there are differences in loan proportion and management stability. If there is a difference by scale, the effect of interaction with housing price changes is also verified. The analysis results are summarized as follows. First, it was found that as the housing price growth rate increases, the proportion of loans from Chinese commercial banks increases. Second, as the rate of increase in housing prices and the proportion of total loans increases, management stability appears to decrease. Third, larger banks were found to have a higher proportion of loans, and smaller banks were found to have greater management stability. The results of this analysis show that Chinese commercial banks' aggressive expansion of their loan proportion is lowering their management stability. Therefore, it is necessary to adjust the loan ratio to the appropriate size level and secure stability with differentiated strategies according to the loan ratio

• 한국벤처창업학회:학술대회논문집
• /
• 2018.04a
• /
• pp.67-74
• /
• 2018

소상공인 창업자들이 자금조달의 대부분을 은행 대출에 의존하고 있는 가운데 소규모 자금 조달을 필요로 하는 이들을 위해 핀테크 기반의 새로운 금융서비스를 통해 소상공인 창업자의 금융 공급을 확산할 필요가 있다. 이러한 환경 변화 패러다임에서 본 연구는 빅데이터와 핀테크 솔루션의 활용이 소상공인의 매출과 금융지원에 미치는 영향을 살펴보기 위해 실제로 공공과 민간의 상권빅데이터자료를 수집하여 분석을 수행하였다. 이를 통해 소상공인에 대한 금융혜택 증대를 위한 사업장의 매출증대 등 소상공인 창업자의 사업성 평가에 필요한 주요변수들을 상권빅데이터를 실증적으로 분석하여 효과성을 검증하는 것이 본 연구의 목적이다. 특히 자금의 대부분을 정책자금을 통해 조달하는 소상공인들이 일반 은행에서도 중소기업 대출의 하나로 비중 있게 이루어질 수 있도록 기존에 활용되지 못한 빅데이터 변수들을 탐색하여 소상공인의 경쟁력 향상을 위한 효율적인 금융지원이 가능함을 확인하고자 하였다. 본 연구에서는 소상공인 창업자의 대출 등 금융지원 확대를 위한 사업성 평가에 상권빅데이터의 활용 가능성이 있는지를 중심으로 문헌적 연구방법 연구와 실증적 분석을 병행하였다. 본 연구는 핀테크와 빅데이터의 활용이 향후 소상공인 자금 조달의 발전 방향이 어떻게 되어야하는지를 모색해야하며, 소상공인을 포함하는 중소기업 신용평가방식의 발전 방향을 구체적으로 모색되어야 할 시점임을 의미하고 있다.

• 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.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.7 no.3
• /
• pp.65-73
• /
• 2012

Microfinance has been an important tool for the economic growth and poverty alleviation. But the success factors and risk factors have not been synthesized in academic literature. This article has paid attention to success factors and potential risk of the Grameen Bank. Grameen Bank methodology is almost the reverse of the conventional banking methodology. Conventional banking is based on the principle that the more you have, the more you can get. Founder of Grameen Bank, Professor Yunus pointed out that, "The least you have the highest you have the priority to receive a loan". On the basis of theoretical literature, there have been different kinds of success factors of microfinance observed in this paper. Key success factors of Grameen Bank are like these: innovation, strict administrative structure, adaptation and learning practice, incentive system. Complementary services such as business consulting and brokerage will contribute to borrowers' economic performance development.

• Journal of Industrial Convergence
• /
• v.16 no.4
• /
• pp.33-46
• /
• 2018

Personal credit scoring is an effective tool for banks to properly guide decision profitably on granting loans. Recently, many classification algorithms and models are used in personal credit scoring. Personal credit scoring technology is usually divided into statistical method and non-statistical method. Statistical method includes linear regression, discriminate analysis, logistic regression, and decision tree, etc. Non-statistical method includes linear programming, neural network, genetic algorithm and support vector machine, etc. But for the development of the credit scoring model, there is no consistent conclusion to be drawn regarding which method is the best. In this paper, we will compare the performance of the most common scoring techniques such as logistic regression, neural network, and support vector machines using personal credit data of the financial institution in China. Specifically, we build three models respectively, classify the customers and compare analysis results. According to the results, support vector machine has better performance than logistic regression and neural networks.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.13 no.3
• /
• pp.125-140
• /
• 2018

According to statistics, it is shown that domestic SMEs rely on bank loans for the majority of fund procurement. From financial information shortage (Thin file) that does not provide information necessary for credit evaluation from banks such as financial statements. In order to overcome these problems, recently, in alternative finance such as P2P, using differentiated information such as demographics, trading information and the like utilizing Fintech instead of existing financial information, small funds A new credit evaluation method has been expanding to provide SMEs with small amounts of money. In this paradigm of environmental change, in this research, credit evaluation which can expand fund supply to SMEs by utilizing big data based on trade area information such as sales fluctuation, location conditions etc. In this research, we try to find such a solution. By analyzing empirically the big data generated in the trade area, we verify the effectiveness as a credit evaluation factor and try to derive the main parameters necessary for the business performance evaluation of the founder of SMEs. In this research, for 17,116 material businesses in Seoul City that operate the service industry from 2009 to February 2018, we collect trade area information generated for each business location from Big Data specialized company NICE Zini Data Co., Ltd.. We collected and analyzed the data on the locations and commercial areas of the facilities that were difficult to obtain from SMEs and analyzed the data that affected the Corporate financial Distress. It is possible to refer to the variable of the existing unused big data and to confirm the possibility of utilizing it for efficient financial support for SMEs, This is to ensure that commercial lenders, even in general commercial banks, are made to be more prominent in one sector of the financing of SMEs. In this research, it is not the traditional financial information about raising fund of SMEs who have basically the problem of information asymmetry, but a trade area analysis variable is derived, and this variable is evaluated by credit evaluation There is differentiation of research in that it verified through analysis of big data from Trading-area whether or not there is an effect on.

• The Journal of the Korea Contents Association
• /
• v.17 no.9
• /
• pp.145-158
• /
• 2017

Lately, rapid increase of household debt and economic change has affected cash flow of household, insolvent risk has increased by high repayment burden of the principal and interest. Previous researches was progressing various discussion, composed objective repayment burden index about household debt. But it was relatively insufficient about perception of consumer. This research compare and analysis determinants of subjective repayment burden in household debt by income quintile, using 2016 Household Financial Welfare Survey. The research result is follows. The income 1 and 2 quartile groups have the higher monthly rent and credit card loan and the housing preparation loan ratio, the higher burden on repayment of the principal and interest. The Income 3 and 4 quartile groups have the higher 60s or older and member of household and real estate mortgage loan, the higher burden on repayment of the principal and interest. The Income 5 quartile group has the higher loan ratio for debt repayment preparation, the higher burden on repayment of the principal and interest.

• Journal of Intelligence and Information Systems
• /
• v.13 no.2
• /
• pp.15-26
• /
• 2007

In this study, a SOHO (Small Office Home Office) bankruptcy prediction model is proposed using Modified Bagging Predictors which is modification of traditional Bagging Predictors. There have been several studies on bankruptcy prediction for large and middle size companies. However, little studies have been done for SOHOs. In commercial banks, loan approval processes for SOHOs are usually less structured than those for large and middle size companies, and largely depend on partial information such as credit scores. In this study, we use a real SOHO loan approval data set of a Korean bank. First, decision tree induction techniques and artificial neural networks are applied to the data set, and the results are not satisfactory. Bagging Predictors which has been not previously applied for bankruptcy prediction and Modified Bagging Predictors which is proposed in this paper are applied to the data set. The experimental results show that Modified Bagging Predictors provides better performance than decision tree inductions techniques, artificial neural networks, and Bagging Predictors.