• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.2
• /
• pp.119-131
• /
• 2024

In recent years, there has been a significant growth in loan comparson services offered by fintech platforms in South Korea. However, it has been reported that loan comparison platform users tend to have a higher risk of default compared to non-users. This paper investigates the difference in platform-specific credit risk factors using survival analysis models - Kaplan-Meier curves and Accelerated Failure Time (AFT) model. Our findings show that, relative to non-users, users of loan comparison platforms are characterized by elevated default rates, a greater propensity for home ownership, lower credit scores, and shorter loan durations. Furthermore, our AFT models elucidate the variance in default risk among the various loan comparison service platforms, highlighting the imperative for customized strategies that address the unique risk profiles of customers on each platform.

• 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.

• 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 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.

• Journal of Families and Better Life
• /
• v.26 no.3
• /
• pp.169-189
• /
• 2008

There are few studies on the characteristics of defaulters, though research in this field is needed. The purpose of this study was to find out social, economic and psychological characteristics of defaulters who are married and in their thirties. For this study, an in-depth interview was used. The major findings were as follows. The focus of this study is defaulters who are married, in their thirties, have managed small businesses by themselves or with their spouses and have experienced job fluctuation. There were a lot of reasons for their becoming defaulters. Most of all, a slump in business with the occurrence of individual events caused them to be enrolled as defaulters. The monthly mean income of defaulters was $1,800,000{\sim}5,000,000$ won, yet it was irregular. Moreover, they were dependent upon labor income or business income. The monthly mean expenditure of defaulters was $1,000,000{\sim}2,300,000$ won, which constituted about $26%{\sim}57.5%$ of their monthly mean income. The defaulters needed to budget a number of expenditures such as food and private education. Defaulters had $25,000,000{\sim}128,000,000$ won in debts and $300,000{\sim}3,000,000$ won per month in debt payments. Most of them didn't have any emergency funds, monetary assets or fixed assets. Interestingly, they showed high tendency to use debt and low skill for their money management. Defaulters had short time horizons and were likely to buy something on the spur of the moment.

• Journal of Families and Better Life
• /
• v.29 no.6
• /
• pp.9-25
• /
• 2011

This study was performed to explore the factors that affect debt-use intention of young defaulters. In addition, this study compares three models that predict the intention to use debt by young defaulters: the theory of reasoned action and two variations of it. Specifically, this study proposes an extended theory of reasoned action by introducing Ao in place of the cognitive structure in the theory of reasoned action. In addition, this study proposes Ao as an independent variable that acts on BI rather than a dependent variable. Self-administered questionnaires were completed by 196 young defaulters attending a credit management education session held by the Credit Counseling & Recovery Service in Kwang-ju, Korea. Based on the study, the conclusions are as follows: the extended theory of reasoned action as proposed in this article most suitably explained the intention to use debt by young defaulters. It was also found that young defaulters were affected by attitudes toward debt, attitudes toward using debt, and subjective norms. It is therefore suggested that an attitudinal message would change the behavior effectively for young defaulters. The findings appeared to support the usefulness of the extended theory of reasoned action and the role of Ao as an independent variable as proposed in this article to explain the intention to use debt by young defaulters. These findings have an important theoretical meaning in that they modify two existing attitude theories in the context of consumer behavior.

• Journal of Families and Better Life
• /
• v.26 no.6
• /
• pp.35-50
• /
• 2008

The purpose of this study was to analyze the characteristics and financial status of credit delinquents utilizing the debt management program of the Credit Counseling and Recovery Service between January-June in 2007. Total sample of 41,355 cases was analyzed using the statistical program SPSS(Version 12.0). For analysis, descriptive statistics, F-test, Scheffe test, t-test, logit analysis and regression analysis were employed. People in the age range of 30-40s, males, high-school graduates, married couples, part-time employees, costfree residents and residents in other regions were relatively high users of the debt management program. Reasons of credit delinquency were diverse and was combined to credit default. However, increases in expenses and income reductions were found to be the most frequent reasons. Financial conditions of delinquents were worse than those of average persons shown on the national statistics. It was also found that age, sex, educational level, occupation, region of residence, home-ownership, reason of delinquency, income and total outstandings of debt were significant determinants of short-term debt burden which was measured by the ratio of monthly payment to income and long-term debt burden which was measured by repayment period.

• The Korean Journal of Financial Studies
• /
• v.5 no.1
• /
• pp.75-103
• /
• 1999

미국의 지방자치제 발전의 재정적인 견인차 역할을 하고 있는 지방채 시장의 활성화로부터 우리가 얻을 수 있는 시사점은 다음과 같이 요약될 수 있다. 첫째, 주 헌법에 명시된 법률상의 통제 외에는 지방채의 기채제한이 없으므로, 지방자치단체의 자율적인 의사결정에 따라 지방채 발행이 활성화되어 있다. 둘째, 대부분의 지방채가 이자소득에 대하여 연방소득세가 면제되는 면세채권의 형태로 발행되고 있는데, 이는 지방자치단체의 재정부담을 경감시켜 줄 뿐 아니라, 투자자들에게 세금우위라는 투자유인을 제공하고 있다. 셋째, 지방채 발행이 활성화됨에 따라 필연적으로 나타나게 되는 채무불이행 상태에 대비하기 위한 제도적 장치로서 신용평가제도와 지방채 보험 및 보증제도가 확립되어 있다. 넷째, 발행된 지방채의 인수단에 의한 인수제도가 확립되어 있으며, 인수자들간의 역할 분담이 잘 이루어지고 있다.

• 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.