• 산업경영시스템학회지
• /
• 제40권4호
• /
• pp.154-163
• /
• 2017

Collaborative filtering, one of the most widely used techniques to build recommender systems, is based on the idea that users with similar preferences can help one another find useful items. Credit card user behavior analytics show that most customers hold three or less credit cards without duplicates. This behavior is one of the most influential factors to data sparsity. The 'cold-start' problem caused by data sparsity prevents recommender system from providing recommendation properly in the personalized credit card recommendation scenario. We propose a personalized credit card recommender system to address the cold-start problem, using multiple user profiles. The proposed system consists of a training process and an application process using five user profiles. In the training process, the five user profiles are transformed to five user networks based on the cosine similarity, and an integrated user network is derived by weighted sum of each user network. The application process selects k-nearest neighbors (users) from the integrated user network derived in the training process, and recommends three of the most frequently used credit card by the k-nearest neighbors. In order to demonstrate the performance of the proposed system, we conducted experiments with real credit card user data and calculated the F1 Values. The F1 value of the proposed system was compared with that of the existing recommendation techniques. The results show that the proposed system provides better recommendation than the existing techniques. This paper not only contributes to solving the cold start problem that may occur in the personalized credit card recommendation scenario, but also is expected for financial companies to improve customer satisfactions and increase corporate profits by providing recommendation properly.

• 지능정보연구
• /
• 제9권2호
• /
• pp.135-154
• /
• 2003

Credit scoring system (CSS) starts from an analysis of delinquency trend of each individual or industry. This paper conducts a research on credit card delinquency of bank customers as a preliminary step for building effective credit scoring system to prevent excess loan or bad credit status. To serve this purpose, we use association rules as a rule generating data mining technique. Specifically, we generate sets of rules of customers who are in bad credit status because of delinquency by association rule mining. We expect that the sets of rules generated by association rule mining could act as an estimator of good or bad credit status classifier and basic component of early warning system.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권3호
• /
• pp.451-458
• /
• 2021

The objective of this research is to analyze the effect of bad credit and liquidity on bank performance with the mediation of capital adequacy. Data were provided by banking institutions listed on the Indonesia Stock Exchange from the period of 2011-2019. The analysis technique was PLS-SEM supported by an application named WarpPLS 6.0. The results of the research show that the effect of bad credit and liquidity on bank performance is not significant. A high level of bad credit is associated with a low level of bank performance. Bank earnings decline along with low profitability. This relationship is not significant because banks can still cover some proportions of bad credit through capital availability. Capital adequacy as an intervening variable has mediated partially the effect of bad credit and liquidity on bank performance. Besides, capital adequacy has a strong effect on credit distribution. Agency theory says that the owner of the fund (the savers of saving account, current account, deposit account) is called principal while the bank as the trusted institution to manage the fund is called an agent. If customers fulfill their duty, then bad credit never happens.

• 스마트미디어저널
• /
• 제13권2호
• /
• pp.9-15
• /
• 2024

본 논문에서는 신용 예측에서 발생하는 불균형 문제를 해결하기 위해 Diffusion Multi-step Classifier(DMC)를 제안한다. DMC는 Diffusion Model을 통해 신용 예측 데이터의 연속적인 수치형 데이터들을 생성하고 생성된 데이터들을 Multi-step Classifier로 구분하는 것으로 범주형 데이터를 생성한다. DMC를 통해 기존의 데이터를 생성하는 다른 알고리즘보다 실제 데이터와 유사한 분포를 가지는 데이터를 생성할 수 있었다. 이렇게 생성된 데이터를 사용하여 실험을 진행하였을 때 연체를 예측할 확률이 20%이상 상승하였으며, 전체적으로 예측 정확성은 약 4%정도 상승하였다. 이러한 연구 결과는 실제 금융기관에 적용 시 연체율 감소와 수익 증가에 큰 기여를 할 수 있을것으로 예상된다.

• 가정과삶의질연구
• /
• 제25권3호
• /
• pp.169-185
• /
• 2007

The purpose of this research is to analyze Korean and Japanese junior high school and high schools students to inquire into the attitudes these students have towards credit, the importance of credit related education, and the necessity of education on online credit. This will provide an insight into the problems associated with teenage credit related consumer education, and allow a solution to be brought up. The results of the research and the proposal are as follows. First, younger Korean teenagers are more passive in consumption than the same age group in Japan. Second, for Korean teenagers, the amount of allowance and savings were an important factor in the attitude towards credit. In Japan there was a discrepancy between gender groups in the attitude towards credit. Third, personal education sessions for teenagers and follow up is necessary. Fourth, since the current teenage population have been familiar with the internet all their lives, credit education should utilize this medium as a tool. Fifth, when looking into the requests Korean and Japanese young teenagers made on credit web sites, the contents and quality of information is more important than the outlook of the site itself. Sixth, there is a need to provide teenagers, who are accustomed to visual data, information, an experience opportunity, and access to related web sites.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권5호
• /
• pp.119-130
• /
• 2020

The study seeks to evaluate the impacts of three types of credit - formal, semi-formal, and informal credits - on the well-being of households in Vietnam's rural areas. Based on data from the Vietnam Household Living Standard Surveys in 2014 and 2016, the research uses the instrumental variable fixed-effect models to estimate the effects of three kinds of credit on household's per capita income and expenditure. There are some significant findings. First, in rural areas, formal credit is the most popular source with stable and cheap borrowing costs. Informal credit is a complement to formal credit to meet urgent needs. Funding agriculture activities is the most commonly cited purpose of borrowing, followed by purchasing assets. The highest misuse rate belongs to the group of loans for agriculture production. Second, the results show that credit helps smoothen consumption rather than generate income for rural households. Three types of credit have insignificant or negative effects on household's per capita income. Formal loans significantly improve total expenditure and spending on healthcare and education. Informal and semi-formal credits show a little influence on consumption. Informal loans have a significantly positive effect on healthcare expenditure. In contrast, having semi-formal loans tends to decrease spending on foods.

• 한국인공지능학회지
• /
• 제9권1호
• /
• pp.21-27
• /
• 2021

In this Paper, Since the 1990s, Korea's credit card industry has steadily developed. As a result, various problems have arisen, such as careless customer information management and loans to low-credit customers. This, in turn, had a high delinquency rate across the card industry and a negative impact on the economy. Therefore, in this paper, based on Azure, we analyze and predict the delinquency and delinquency periods of credit loans according to gender, own car, property, number of children, education level, marital status, and employment status through linear regression analysis and enhanced decision tree algorithm. These predictions can consequently reduce the likelihood of reckless credit lending and issuance of credit cards, reducing the number of bad creditors and reducing the risk of banks. In addition, after classifying and dividing the customer base based on the predicted result, it can be used as a basis for reducing the risk of credit loans by developing a credit product suitable for each customer. The predicted result through Azure showed that when predicting with Linear Regression and Boosted Decision Tree algorithm, the Boosted Decision Tree algorithm made more accurate prediction. In addition, we intend to increase the accuracy of the analysis by assigning a number to each data in the future and predicting again.

• KDI Journal of Economic Policy
• /
• 제44권3호
• /
• pp.1-26
• /
• 2022

This paper analyzes the effects of the cut in the legal maximum interest rate (from 27.4% to 24%) that occurred in February of 2018 on loan interest rates, the default rates, and the loan approval rate of borrowers in the non-banking sector. We use the difference-in-difference identification strategy to estimate the effect of the cut in the legal maximum interest rate using micro-level data from a major credit-rating company. The legal maximum rate cut significantly lowers the loan interest rate and default rate of low-credit borrowers (i.e., high-credit-risk borrowers) in the non-banking sector. However, this effect is limited to borrowers who have not been excluded from the market despite the legal maximum interest rate cut. The loan approval rate of low-credit borrowers decreased significantly after the legal maximum interest rate cut. Meanwhile, the loan approval rate of high-credit and medium-credit (i.e., low credit risk and medium credit risk) borrowers increased. This implies that financial institutions in the non-banking sector should reduce the loan supply to low-credit borrowers who are no longer profitable while increasing the loan supply to high- and medium-credit borrowers.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권7호
• /
• pp.35-47
• /
• 2020

An economic downturn can occurred through unexpected events in various fields, such as the subprime mortgage crisis and the outbreak of Coronavirus Disease-2019 (COVID-19). Trade credit is important for small- and medium-sized enterprises (SMEs), especially during a monetary contraction, as it is the last option for firms that lack bank credit. This study aims to determine whether trade credit is profitable for the buyer and supplier firms during and after a financial crisis. We use panel data consisting of all trade credit transactions and financial statements of 5,751 Korean firms during the period 2008-2012. It shows that trade credit is more profitable for both buyers and suppliers in the post-crisis period than during the crisis. Moreover, trade payable is more effective for unconstrained buyers than for constrained buyers. Finally, a mixed strategy is superior to an aggressive or passive strategy of SMEs. The results suggest less profitability of trade credit during a period of contraction and greater sensitivity of the buyer SMEs, emphasizing the idiosyncratic liquidity strategy of each firm. This study can be helpful to develop a strategy of profitable trade credit for SMEs and to establish a policy of managing liquidity for the authority.

• 실천공학교육논문지
• /
• 제14권3호
• /
• pp.471-477
• /
• 2022

본 연구에서는 고교학점제에서 데이터과학 과목을 신청한 학생들을 위하여 교육 프로그램을 개발하였다. 이에 데이터과학교육에 대하여 기존 연구와 요구사항을 분석하고 학습 계획을 설계하였으며, 단계별 교육 프로그램에 따라 교육 프로그램을 개발하였다. 또한 기존 연구에서 고교학점제를 위한 데이터과학교육에 대한 연구가 활발하지 않았으므로 기존의 학교 현장에서 연구되었던 데이터 과학 교육에 대한 연구를 참고하여 문제 정의, 데이터 수집, 데이터 전처리, 데이터 분석, 데이터 시각화, 모의 분석의 단계로 연구를 진행하였다. 본 연구를 통하여 고교학점제에서 데이터과학교육에 대한 연구가 더욱 활발해질 것으로 기대한다.