• The Journal of Society for e-Business Studies
• /
• v.23 no.3
• /
• pp.207-224
• /
• 2018

In this article, an empirical study was conducted by using public dataset from Lending Club Corporation, the largest online peer-to-peer (P2P) lending in the world. We explore significant predictor variables related to P2P lending default that housing situation, length of employment, average current balance, debt-to-income ratio, loan amount, loan purpose, interest rate, public records, number of finance trades, total credit/credit limit, number of delinquent accounts, number of mortgage accounts, and number of bank card accounts are significant factors to loan funded successful on Lending Club platform. We developed online P2P lending default prediction models using discriminant analysis, logistic regression, neural networks, and decision trees (i.e., CART and C5.0) in order to predict P2P loan default. To verify the feasibility and effectiveness of P2P lending default prediction models, borrower loan data and credit data used in this study. Empirical results indicated that neural networks outperforms other classifiers such as discriminant analysis, logistic regression, CART, and C5.0. Neural networks always outperforms other classifiers in P2P loan default prediction.

• Journal of Family Resource Management and Policy Review
• /
• v.26 no.3
• /
• pp.19-34
• /
• 2022

There are growing concerns about debt insolvency among youth and low-income households. The deterioration in household debt quality among young people is due to a combination of sluggish employment, an increase in student loan burden and an increase in high-interest loans from the secondary financial sector. The purpose of this study was to explore the possibility of household debt default among young borrowers in Korea and to predict the factors affecting this possibility. This study utilized the 2021 Household Finance and Welfare Survey and used random forest algorithm to comprehensively analyze factors related to the possibility of default risk among young adults. This study presented the importance index and partial dependence charts of major determinants. This study found that the ratio of debt to assets(DTA), medical costs, household default risk index (HDRI), communication costs, and housing costs the focal independent variables.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.419-437
• /
• 2023

As the number of thin filers in Korea surpasses 12 million, there is a growing interest in enhancing the accuracy of assessing their credit default risk to generate additional revenue. Specifically, researchers are actively pursuing the development of default prediction models using machine learning and deep learning algorithms, in contrast to traditional statistical default prediction methods, which struggle to capture nonlinearity. Among these efforts, Graph Neural Network (GNN) architecture is noteworthy for predicting default in situations with limited data on thin filers. This is due to their ability to incorporate network information between borrowers alongside conventional credit-related data. However, prior research employing graph neural networks has faced limitations in effectively handling diverse categorical variables present in credit information. In this study, we introduce the Transformer embedded Graph Convolutional Network (TeGCN), which aims to address these limitations and enable effective default prediction for thin filers. TeGCN combines the TabTransformer, capable of extracting contextual information from categorical variables, with the Graph Convolutional Network, which captures network information between borrowers. Our TeGCN model surpasses the baseline model's performance across both the general borrower dataset and the thin filer dataset. Specially, our model performs outstanding results in thin filer default prediction. This study achieves high default prediction accuracy by a model structure tailored to characteristics of credit information containing numerous categorical variables, especially in the context of thin filers with limited data. Our study can contribute to resolving the financial exclusion issues faced by thin filers and facilitate additional revenue within the financial industry.

• Korea Real Estate Review
• /
• v.28 no.3
• /
• pp.21-35
• /
• 2018

The recent performance of residential mortgages demonstrated how default risk operated separately from prepayment risk. In this study, we investigated the determinants of the borrowers' decisions pertaining to early termination through default from the mortgage performance data released by Freddie Mac, involving securitized mortgage loans from January 2011 to September 2013. We estimated a Cox-type, proportional hazard model with a single risk on fundamental factors associated with default options for individual mortgages. We proposed a mortgage default model that included two specifications of delinquency: one using a delinquency binary variable, while the other using a delinquency probability. We also compared the results obtained from two specifications with respect to goodness-of-fit proposed in the spirit of Vuong (1989) in both overlapping and nested models' cases. We found that a model with our proposed delinquency probability variable showed a statistically significant advantage compared to a benchmark model with delinquency dummy variables. We performed a default prediction power test based on the method proposed in Shumway (2001), and found a much stronger performance from the proposed model.

• Management & Information Systems Review
• /
• v.3
• /
• pp.179-199
• /
• 1999

Case-Based Reasoning(CBR) offers a new approach for developing knowledge based systems. In case-based approach the problem solving experience of the domain expert is encoded in the form of cases. CBR has successfully been applied to many kinds of problems such as design, planning, diagnosis and forecasting. In this paper, CBR was applied for forecasting default risk. The applied result was successful in spite of the small casebase. Generally, CBR requires large casebase. So, if the number of data was large, the result was better. But in this paper, what financial variable was more forecastable was not tested. Next, this should be tested.

• The Journal of the Korea Contents Association
• /
• v.16 no.3
• /
• pp.81-90
• /
• 2016

This study aims to investigate the association between stock performance and credit ratings, and credit rating changes using a sample of 1,691 KRX firm-years that acquire equity in the form of long-term bonds from 2002 to 2013. Previous U.S. literature is mixed with regard to the relation between credit ratings and stock price. On one hand, there is evidence of a positive relation between credit ratings and stock prices, an anomaly established in U.S. studies. On the other hand, the CAPM model suggests a negative relation between stock prices and credit ratings, implying that investors expect financial rewards for bearing additional risk. To our knowledge, we are the first to examine the relationship between stock price and default risk proxied by credit ratings in period t+1. We find a negative (positive) relation between credit ratings (risk) in period t+1 and stock returns in period t, suggesting that credit rating agencies do not consider stock returns as a metric with the potential to influence default risk. Our results suggest that market participants may prefer firms with higher credit risk because of expected higher returns.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.185-192
• /
• 2022

This study investigates the effect of the semi-supervised learning(SSL) method on predicting default risk of peer-to-peer(P2P) loans. Despite its proven performance, the supervised learning(SL) method requires labeled data, which may require a lot of effort and resources to collect. With the rapid growth of P2P platforms, the number of loans issued annually that have no clear final resolution is continuously increasing leading to abundance in unlabeled data. The research data of P2P loans used in this study were collected on the LendingClub platform. This is why an SSL model is needed to predict the default risk by using not only information from labeled loans(fully paid or defaulted) but also information from unlabeled loans. The results showed that in terms of default risk prediction and despite the use of a small number of labeled data, the SSL method achieved a much better default risk prediction performance than the SL method trained using a much larger set of labeled data.

• The Journal of the Korea Contents Association
• /
• v.10 no.3
• /
• pp.187-195
• /
• 2010

So that this study confirms going concern's availability laying focus on entertainment industry possibility of default judge, focus in cash flow that is important accounting indicator pointer to do cause of bankruptcy, payable capability, insolvent estimate etc and analyzed effect that governance gets in cash flow. The sampling period was from 2005 to 2008 and the number of samples was 44. In analysis technique, implement basic statistical, t-test, correlation, regression. Is as following if summarize result. CFO, for debt ratio, negative(-), enterprise size was exerting positive(+), and cash flow by investment activity enterprise size negative(-) influence reach.

• The Journal of the Korea Contents Association
• /
• v.6 no.4
• /
• pp.146-157
• /
• 2006

Causal relationship means what relations the result occurred have with a fact as a reason. In general, a formular that no result exists without reasons is used for the method to confirm existence and inexistence of causal relationship. Problematic causal relationships in Private Law are reparations (Article No. 393 of Private Law) due to debt nonfulfillment and reparation due to tort (Application of Article No. 393 by Article No. 750, and No. 763 of Private Law). The purpose pursued by reparation system in private law is to promote equal burden of damages, and the range of reparation at this time is decided by the range of damage and the range of damage is decided by the principle of causal relationship. That the causal relationship theory fairly causes confusion by treating one problem and the other problem as the same thing, instead of dividing them according to the purpose of protection presented by the law is a reason of the criticism from different views.

• The Korean Journal of Financial Management
• /
• v.27 no.2
• /
• pp.169-204
• /
• 2010

This paper examines the dynamic relationship between fund flow and market risk at the aggregate level and explores whether sudden sharp changes in fund flow (fund run) can cause a systemic risk in the Korean financial markets. We use daily and weekly data and regression and VAR analysis. Main results of the paper are as follows: First, in the stock market, a concurrent and a lagged unexpected fund flows have a positive relationship with market volatility. A positive shock in fund flow predicts an increase in stock market volatility. In the bond market, an unexpected fund flow has a negative relationship with the default risk premium, but a positive relationship with the term premium. And an unexpected fund flow of the money market fund has a negative relationship with the liquidy risk, but the explanatory power is very low. Second, for examining whether changes in fund flow induce a systemic risk, we construct a spillover index based on the forecast error variance decomposition of VAR model. A spillover index represents that how much the shock in fund flow can explain the change of market risk in a market. In general, explanatory powers from spillover indexes are so fluctuant and low. In the stock market, the impact of shocks in fund flow on market risk is relatively high and persistent during the period from the end of 2007 to 2008, which is the subprime-mortgage crisis period. In bond market, since the end of 2008, the impact of shocks in fund flow spreads to default risk continually, while in the money market, such a systematic effect doesn't take place. The persistent patterns of spillover effect appearing around a certain period in the stock market and the bond market suggest that the shock to the unexpected fund flow may increase the market risk and can be a cause of systemic risk in the financial markets. However, summarizing the results of regression and VAR model analysis, and considering the very low explanatory power of spillover index analysis, we can conclude that changes in fund flow have a very limited power in explaining changes in market risk and it is not very likely to induce the systemic risk by a fund run in the Korean financial markets.