• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.14 no.1
• /
• pp.139-149
• /
• 2019

The purpose of this study is to contribute to the minimization of the social cost due to the insolvency by improving the success rate of the startups by providing useful information to the founders and the start-up support institutions through analysis of non-financial information affecting the failure of the startups. This study is aimed at entrepreneurs. The entrepreneurs that are defined by the credit guarantee institutions generally refer to entrepreneurs within 5 years of establishment. The data used in the study are sampled from the companies that were supported by the start-up guarantee from January 2014 to December 2013 as the end of December 2017. The total number of sampled firms is 2,826, 2,267 companies (80.2%), and 559 non-performing companies (19.8%). The non-financial information of the entrepreneur was divided into the entrepreneur characteristics information, the entrepreneur characteristics information, the entrepreneur asset information and the entrepreneur 's credit information, and cross-tabulations and logistic regression analysis were conducted. As a result of cross-tabulations, univariate analysis showed that personal credit rating, presence in the industry, presence of residential housing, presence of employees, and presence of financial statements were selected as significant variables. As a result of the logistic regression analysis, three variables such as personal credit rating, occupation in the industry, and presence of residential house were found to be important factors affecting the failure of founding companies. This result shows the importance of entrepreneur 's personal credibility and experience and entrepreneur' s assets in business management. The start-up support institutions should reflect these results in the entrepreneur 's credit evaluation system, and the entrepreneurs need training on the importance of the personal credit and the management plan in the entrepreneurial education. The results of this analysis will contribute to the minimization of the incapacity of startups by providing useful non-financial information to founders and start-up support organizations.

• Journal of Distribution Science
• /
• v.13 no.9
• /
• pp.47-57
• /
• 2015

Purpose - The aim of this paper is to investigate the explanatory power of the Pecking-order theory (the cost of financing increases with asymmetric information) among Korean retail firms from the perspective of debt capacity. According to the Pecking-order theory, a firm's first preference is to use internal funds for its capital needs, its next preference is the issuance of debt, and its last preference is the issuance of equity; this is due to the information asymmetry problem between existing shareholders and investors. However, prior empirical studies, such as Lemmon and Zender (2010), argue that the entire sample test for the Pecking-order theory could be misleading due to the different levels of debt issuance capability of each of the individual firms; in fact, they confirm that the explanatory power of the Pecking-order theory improves after taking into account the differences in debt capacity of the U.S. firms they examined. This paper implements a case study approach among Korean retail firms to examine the relationship between debt capacity and the explanatory power of the Pecking-order theory in Korea. Research design, data, and methodology - This study uses the sample of public retail firms on the Korea Composite Stock Price Index (KOSPI) from the time period of 1990 to 2013. We gather related financial and accounting statements from the financial information firm WISEfn. Credit rating information is provided by the Korea Investor Service. We employ the models of Lemmon and Zender (2010) and Son and Kim (2013) to measure a firm's debt capacity. Their logit models use the rating dummy variable as a dependent variable and incorporate other firm characteristics as independent variables to estimate debt capacity. To test the Pecking-order theory, we adopt variants of the financing deficit model of Shyam-Sunder and Myers (1999). In the test of the Pecking-order theory, we consider all of the changes in total debt obligations, current debt obligations, and long-term debt obligations. Results - Our main contribution to the literature is our confirmation of the predicted relationship between debt capacity and the explanatory power of the Pecking-order theory among Korean retail firms. The coefficients on financing deficits become greater as a firm's debt capacity improves. This is consistent with the results of Lemmon and Zender (2010). The coefficients on the square of the financing deficits are also negative for the firms in the largest debt capacity group, which is also consistent with the predictions in prior literature. Conclusions - This study takes a case study approach by examining Korean retail firms. We confirm that the Pecking-order theory explains the capital structure of retail firms more appropriately, after taking into account the debt capacity of each firm. This result suggests the importance of debt capacity consideration in the testing of the Pecking-order theory. Our result also implies that there has been a potential underestimation of the explanatory power of the Pecking-order theory in existing studies.

• Korean Journal of Construction Engineering and Management
• /
• v.21 no.5
• /
• pp.64-73
• /
• 2020

The government announced a plan for fund support to the enterprises with high possibility of recovery and early restructuring for the enterprises with low recovery by objectifying credit assessment system. Such announcement of government could be extended to restructuring risk of middle standing enterprises with low financial soundness by establishing the basis to prepare prompt restructuring by reinforcing the basis for restructuring through capital market. This research analyzed financial soundness based on the financial evaluation of bank by selecting 10 middle standing construction companies which focused on housing business in 2019, based on such analysis result, it was confirmed that there was a high possibility of restructuring risk. This research determined that there would be a decrease in growth rate of construction industry on the whole in 2020 due to fall of economic growth rate and reinforced real estate regulation, accordingly, there's a big possibility for middle standing construction companies with paid-in capital ratio due to its low possibility of maintenance of stable credit rating. This research established KCSI assessment model by utilizing the material of a reliable research institute in order for middle standing construction companies to evade restructuring risk, and indicated risk ratio differentiated per each item through a working-level expert survey. Such research result could suggest credit risk reduction method to middle standing construction company management staffs, and prepare a basis to evade restructuring risk.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.25-41
• /
• 2011

Recently, support vector machines (SVMs) are being recognized as competitive tools as compared with other data mining techniques for solving pattern recognition or classification decision problems. Furthermore, many researches, in particular, have proved them more powerful than traditional artificial neural networks (ANNs) (Amendolia et al., 2003; Huang et al., 2004, Huang et al., 2005; Tay and Cao, 2001; Min and Lee, 2005; Shin et al., 2005; Kim, 2003).The classification decision, such as a binary or multi-class decision problem, used by any classifier, i.e. data mining techniques is so cost-sensitive particularly in financial classification problems such as the credit ratings that if the credit ratings are misclassified, a terrible economic loss for investors or financial decision makers may happen. Therefore, it is necessary to convert the outputs of the classifier into wellcalibrated posterior probabilities-based multiclass credit ratings according to the bankruptcy probabilities. However, SVMs basically do not provide such probabilities. So it required to use any method to create the probabilities (Platt, 1999; Drish, 2001). This paper applied AdaBoost algorithm-based support vector machines (SVMs) into a bankruptcy prediction as a binary classification problem for the IT companies in Korea and then performed the multi-class credit ratings of the companies by making a normal distribution shape of posterior bankruptcy probabilities from the loss functions extracted from the SVMs. Our proposed approach also showed that their methods can minimize the misclassification problems by adjusting the credit grade interval ranges on condition that each credit grade for credit loan borrowers has its own credit risk, i.e. bankruptcy probability.

• The Journal of Information Systems
• /
• v.15 no.3
• /
• pp.175-186
• /
• 2006

최근 정보기술(IT; Information Technology) 및 네트워크 기술의 발달은 기업사회의 의사결정 패턴에 큰 변화를 주고 있다. 특히 글로벌 정치경제 환경이 급변함에 따라 기업들의 의사결정은 보다 빠른 피드백(feedback loop)을 요구하고 있어 과거의 정확성을 중심의 패턴에 변화된 정보의 시기적 절성(timely information)이 크게 강조되고 있다. 본 논문에서는 이러한 첨단기술사회에서 빠르게 의견수렴을 할 수 있는 기술적인 프레임워크를 구축하였다. 본 시스템은 현대사회의 주요한 경제 및 재무의사결정 구조(infrastructure)인 신용평가(credit rating)제도를 웹 기반 시스템으로 구현함으로서 정보의 시기적절성과 현재성을 높이는 의사결정지원시스템을 시현하였다.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.49-64
• /
• 1999

본 연구는 백화점 고객이 신용 카드 신청 요구 시에 작성되는 가입 정보 및 사용되고 있는 고객의 거래 정보는 카드 사용 패턴으로 신용도를 예측하는 여러 방법론을 제시하고 성능을 비교하였다. 가입 정보를 분석하기 위해 역전파 신경망(Back-Propagation Neural Network, BPNN), 사례기반추론(Case-Based reasoning)을, 거래 정보를 분석하기 위해 역전파 신경망과 더불어 시간지연 신경망(Time-Delayed Neural Network, TDNN)을 각각 사용하여 그 결과를 비교하였다. 또한 전체시스템의 적중률을 높이기 위햐여, ID3와 신경망을 이용한 Meta-Leaning 방법을 제시하였으며, Meta-Learning 방법과 다른 방법들을 비교, 분석을 하였다. 본 연구에서는 모형 수립과 검증을 위하여 T백화점의 실제 신용 카드 가입 고객 데이터를 이용하여 실험하였다. 데이터의 성격에 따라 각 모델의 예측력에는 차이가 나타났으나, 신경망 모형의 예측력이 우수하였으며, 시간적 특성을 고려하는 시간지연 신경회로망 모형의 예측력은 더욱 우수하게 나타났다. 또한 Meta-Learning 모형을 사용하면 예측력이 더 높아진다는 것을 확인할 수 있었다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2003.05a
• /
• pp.835-842
• /
• 2003

현행 기업신용평가모형에 관한 연구는 크게 부실예측모형 및 채권등급 평가모형으로 구분된다. 이러한 신응평가모형에 관한 연구는 단순히 부실여부 또는 이미 전문가 집단에 의해 사전에 정의된 등급체계만을 예측하는 데 초점을 맞추고 있었다. 그러나. 대부분의 금융기관에서 사용하는 신응평가모형은 기업의 부실여부만을 예측하거나 기존의 채권등급을 예측하기 위만 목적보다는 기업의 고유 신응위험을 평가하여 이에 적합한 신용등급을 부여함으로써, 효율적인 대출업무를 수행하기 위해 활용되고 있다. 본 연구에서는 기존의 부실예측모형들을 대상으로 다중 부실확률모형 (Business Failure Probability Map; BFPM) 접근방법을 이용한 신응등급화 방법을 제안하고자 한다. 본 연구에서 제시된 다중 부실확률모형은 신경망모형과 로짓모형을 통합하여 부도율, 점유율을 고려한 다단계 신용등급을 예측할 수 있게 해준다. 다중 부도확률지도 접근방법을 이용하여 각 금융기관에서 정의하는 수준의 신용리스크를 효과적으로 추정하고, 이를 기준으로 보다 객관적인 다단계 신용등급을 산출하는 새로운 신응등급화 방법을 제시 하고자 한다.

• Journal of Intelligence and Information Systems
• /
• v.4 no.2
• /
• pp.1-21
• /
• 1998

귀납적 학습방법들의 분류성능을 비교 평가하기 위하여 대표적 분류문제의 하나인 신용평가 문제를 사용하였다. 분류기로서 사용된 귀납적 학습방법론들은 통계학의 다변량 판별분석(MDA), 기계학습 분야의 C4.5, 신경망의 다계층 퍼셉트론(MLP) 및 Cascade Correlation Network(CCN)의 4 가지이며, 학습자료로는 국내 3개 신용평가기관이 발표한 신용등급 및 공포된 재무제표를 사용하였다. 신용등급 예측의 정확도에 의한 분류성능을 평가하였는데 연도별 평가와 시계열 평가의 두 가지를 실시하였다. Cascade Correlation Network이 가장 좋은 분류성능을 보였지만 4가지 분류기들 사이에 통계적으로 유의한 차이는 발견되지 않았다. 이는 사용된 학습자료가 갖는 한계로 인한 것으로 추정되지만, 성능평가 과정에 있어 학습자료의 전처리 과정이 분류성과의 제고에 매우 유효함이 입증되었다.

• Journal of Information Technology Services
• /
• v.1 no.1
• /
• pp.7-15
• /
• 2002

The role of SI in this IT era is recognized high as a value-creating activity in the overall industries. But the valuation factors are not so attractive compared to other industries. Among the negative factors are the relatively high cost of sales and operating cost, the lack of technical differentiation among the firms, the low level of entry barrier, and the resulting competition in the SI industry. But some positive factors such as the expectation for the overall introduction of IT into eoconomy, development of SM (System Management) projects, and the sales of developed soultions and components increase the value of SI firms.