Bad Credit Risks Research Articles

Legal protection for Provider in Peer to Peer Lending: an Example from Indonesian Regulation

The Financial Technology peer to peer (P2P) lending concept still finds many weaknesses, especially in terms of legal protection for parties and risk management from Fintech itself. P2P Lending Regulation in Indonesia currently uses POJK No. 77 / POJK / 2016 concerning technology-based money lending and borrowing services. The position of Fintech P2P lending is similar to a bank, but the concept is a different agreement. Fintech P2P lending funds can come from investors or funders or cooperate with legal entities or banks. Considering that the risk posed by Fintech P2P lending is very large, Fintech must also implement consumer protection, risk management and prudential principles like a bank credit agreement so as to cover the risk of bad credit, the Fintech platform uses other means to protect funds from investors or investors. the other is with the protection fund as done by the Coin works platform. The protection fund does not cover the entire fund invested by the funder, depending on the availability of protection funds and the amount of credit that is experiencing congestion. The POJK regulation in article 19 describes the agreement clause which must contain the dispute resolution mechanism and the settlement mechanism if the implementation of lending and borrowing services is not able to continue operations, so that with the rules related to the clause it is expected that the funder will still get legal certainty and protection for funds.

ANALISIS PENERAPAN SISTEM PENGENDALIAN INTERNAL PEMBERIAN KREDIT USAHA KECIL MENENGAH PADA PT. BANK TABUNGAN NEGARA CABANG TERNATE

In granting loans bank has a risk of bad credit. Internal control is the methods used to coordinate a company to achieve the corporate goals which include organizational structure division of authority, established procedures, and healthy practices. this is done to minimize the risk of bad credit. Banks must be able to detect bad loans first so as not to cause bank losses. The direction of this research is to find out the application of internal control based on credit at PT. Bank Tabungan Negara Ternate. The research method used in this research is a qualitative method. The results of research related to the internal receivable control system has been carried out well in accordance with the elements of internal control of COSO including the control environment, risk assessment, control activities, information and communication, monitoring.Keywords: Internal Control, Granting Credit

IPTEKS PENENTUAN KELAYAKAN KREDIT BANK PADA PT. BANK RAKYAT INDONESIA (PERSERO) TBK, KCP (KANTOR CABANG PEMBANTU) BAHU

The function of banking is to raise funds from the community and channel it to the public. In collecting funds in charge of the bank is a relationship fund and in channeling funds to the public the bank provides credit to help improve the economy and the welfare of the community. In the bank there is a credit relationship that is in charge of analyzing credit at this analytical bank that can see the feasibility and risk of bad credit.Keywords: Credit Analysis, Risk of bad credit

Analisa Suku Bunga Dan Nilai Jaminan Terhadap Resiko Kredit KPR

Credit risk is the inability of the customer to pay installments on time or due. This study aims to determine the effect of interest rates and the total value of collateral, on the risk of bad credit.
 Data obtained from published financial statements published by IDX with the period of 2013 to 2017. The sampling technique used in this study was purposive sampling. The number of samples is 4 banking companies listed on the Indonesia Stock Exchange. The analytical method used in this study is multiple linear regression, correlation, and coefficient of determination to obtain a comprehensive picture of the relationship between variables one with other variables.
 Based on testing the hypothesis by using the statistical t-test and the F test results showed that the interest rate has no effect and is not significant to bad credit, while the guarantee value has a positive and significant effect on bad credit and simultaneously there is a significant influence of interest rates and collateral value on bad credit

ANALISIS PENETAPAN MARGIN AKAD MURABAHAH PADA BANK SYARIAH DI INDONESIA

The purpose of this research is to know the way or model by syariah banking in determining margin level of murabahah financing contract. The sample of this research consist of 1 Sharia Business Unit (UUS), and 2 Sharia Commercial Bank (BUS), namely Bank Riaukepri Syariah, Bank Muamalat, Bank Syariah Mandiri. The results of this study indicate the determination of margin on financing with murabahah scheme at Sharia Bank based on ALCO team decision of each bank refers to BI-Rate, amount of cost of fund component, overhead cost, bad credit risk, which are desired.

Improve credit scoring using transfer of learned knowledge from self-organizing map

Credit scoring is important for credit risk evaluation and monitoring in the accounting and finance domain. For financial institutions, the ability to predict the business failure is crucial, as incorrect decisions have direct financial consequences. A variety of pattern recognition techniques including neural networks, decision trees, and support vector machines have been applied to predict whether the borrowers should be considered a good or bad credit risk. This paper presents a hybrid approach to building the credit scoring model and illustrates how the unsupervised learning based on self-organizing map (SOM) can improve the discriminant capability of feedforward neural network (FNN). Within the hybridization scheme, the knowledge (i.e., prototypes of clusters) found by SOM is transferred as input to the subsequent FNN model. Four real-world data sets are used in the experiments for credit approval problems. By varying the parameters, the experimental results demonstrate the predictive model built by the hybrid approach can achieve better performance than the stand-alone FNN particularly when a limited amount of labeled data is available. This gives some insights on how to construct more accurate predictive models when the data collection is difficult in some financial applications. A complete and unique graphical visualization technique is shown which better outlines the trade-off between distinct metrics and attained performance.

Research Opportunities for Neural Networks: The Case for Credit

SummaryThis article identifies research opportunities in the use of artificial neural networks in credit scoring and related business intelligence situations, particularly as they have been emerging in the global economy. In the literature review, particular attention is paid to commercial lending credit risk assessment and consumer credit scoring. Investors and auditors need models that can predict whether a customer will stay viable. Lenders must manage their credit risk to maximize profits and cash flow, while minimizing losses. As the global economic recession continues, investors are tightening their investment belts and need models that help them make better investment decisions, while lenders must strengthen lending practices and better identify both good and bad credit risks. Artificial neural networks may help firms improve their credit model development, and thereby their credit decisions and profitability. Such technology may also help improve development in emerging economies. Copyright © 2016 John Wiley & Sons, Ltd.

Women and Subprime Lending: An Essay Advocating Self-Regulation of the Mortgage Lending Industry

This project will build upon my most recent article, Racism’s Property Victims: Prime Subprime Mortgage Targets, by considering gender and gender trait stereotypes as predictors of whether or not a borrower receives a subprime loan or refinance. I hope to use 2006 HUD and HMDA data, along with other studies and research, to explore the subprime lending disparity experienced by women, in particular women at the highest income levels.According to several prominent studies, single women are one of the fastest growing segments of the home buying population. In 1995, single women were 14% of all home buyers and in 2006, single women were 22% of all homebuyers. Moreover, woman-owned companies are the fastest growing segment among small businesses. The bad news is that statistics also indicate that women are the fastest growing segment of the population filing bankruptcy. My article has the potential to make a very important contribution to this underwritten area of the law. Given the increasingly active and prominent presence of single women in the real estate market, why has this group not been targeted by banks as a promising “emerging” population of candidates for prime loans? Are single women borrowers and business owners perceived by lenders as full participants in the economy? Could it be that the bankruptcy statistics provide all the answers — single women are just bad credit risks — or do the bankruptcy statistics merely reflect the unavoidable consequences of the harm done to women borrowers by lenders earlier in the lending process? My article will address these and other important questions.

Machine Learning in Financial Crisis Prediction: A Survey

For financial institutions, the ability to predict or forecast business failures is crucial, as incorrect decisions can have direct financial consequences. Bankruptcy prediction and credit scoring are the two major research problems in the accounting and finance domain. In the literature, a number of models have been developed to predict whether borrowers are in danger of bankruptcy and whether they should be considered a good or bad credit risk. Since the 1990s, machine-learning techniques, such as neural networks and decision trees, have been studied extensively as tools for bankruptcy prediction and credit score modeling. This paper reviews 130 related journal papers from the period between 1995 and 2010, focusing on the development of state-of-the-art machine-learning techniques, including hybrid and ensemble classifiers. Related studies are compared in terms of classifier design, datasets, baselines, and other experimental factors. This paper presents the current achievements and limitations associated with the development of bankruptcy-prediction and credit-scoring models employing machine learning. We also provide suggestions for future research.

Multiple classifier architectures and their application to credit risk assessment

Multiple classifier systems combine several individual classifiers to deliver a final classification decision. In this paper the performance of several multiple classifier systems are evaluated in terms of their ability to correctly classify consumers as good or bad credit risks. Empirical results suggest that some multiple classifier systems deliver significantly better performance than the single best classifier, but many do not. Overall, bagging and boosting outperform other multi-classifier systems, and a new boosting algorithm, Error Trimmed Boosting, outperforms bagging and AdaBoost by a significant margin.

Islamic Bank Failure: A Case Study

Recent turmoil in financial markets has once again emphasised the need for regulatory vigilance–especially in relation to banks in distress and those experiencing a run on depositors’ funds. The Islamic Bank Ltd of South Africa collapsed in 1997, and its failure exposed the cost of bad credit risk management, operational dysfunction and regulatory breaches. This study finds early regulatory intervention may have addressed major liquidity shortcomings and perhaps even forestalled the bank’s collapse. Despite effective intervention measures, the evidence shows a run on funds fuelled by noise and loss of confidence is difficult to reverse without direct and significant central bank liquidity infusion and deposit guarantees. Evidence of poor management and dereliction of duty by external auditors to report on material irregularities reinforces the need for a new whole- of-regulatory approach. Further, Shari’ah compliance is found to be ineffectual without substantive legal support.

The use of MSD model in credit scoring

A credit scoring classification problem can be defined as a decision process in which information from application forms for new or extended credit is used to separate the applicants into good and bad credit risks. In the credit industry, it is important to find a method that optimally separates applicants into ‘goods’ and ‘bads’ as good classification models can provide competitive advantage. These classification models can be developed by statistical techniques (e.g. statistical discriminant analysis and logistic regression), neural networks and mathematical programming (MP) discriminant analysis methods, although MP methods are less widely used in practice in spite of their advantages, e.g. MP methods are non-parametric and desired classifier characteristics can be represented by constraints in the MP model. In this paper, a MP model is described and compared with other known methods, using real data. The MP model uses minimization of the sum of the deviations of misclassified observations from the discriminant function as its objective function. The performance of this MP model is evaluated on three datasets for credit card applications and is compared with the performance of ak-NN classifier, discriminant analysis, support vector machines and and logistic regression.

Predicting payment and nonpayment of direct mail obligations: Profiling good and bad credit risks

Profiles of prospect groups are developed in terms of their likelihood of fulfilling financial obligations to direct mail offers. An extensive database of individuals responding to a variety of direct mail offers is analyzed, and the variables that best differentiate the likelihood of defaulting or not defaulting on their financial commitments are identified. Two specific data-analytic models are presented. The first tests hypotheses pertaining to a limited set of demographic and credit-related variables. The second begins with a set of 271 variables and identifies the 11 that best predict default likelihood.

Predicting payment and nonpayment of direct mail obligations: Profiling good and bad credit risks

Predicting payment and nonpayment of direct mail obligations: Profiling good and bad credit risks

Predicting payment and nonpayment of direct mail obligations: Profiling good and bad credit risks

Profiles of prospect groups are developed in terms of their likelihood of fulfilling financial obligations to direct mail offers. An extensive database of individuals responding to a variety of direct mail offers is analyzed, and the variables that best differentiate the likelihood of defaulting or not defaulting on their financial commitments are identified. Two specific data-analytic models are presented. The first tests hypotheses pertaining to a limited set of demographic and credit-related variables. The second begins with a set of 271 variables and identifies the 11 that best predict default likelihood.

The Credit-Constrained Consumer: An Empirical Study of Demand and Supply in the Loan Market

This article presents an empirical analysis of credit-constrained households in which models of both demand and supply sides of the market for loans are simultaneously estimated. We develop a discrete-choice logit model of the consumers' decision on whether or not to apply for credit. Combining this with a reduced-form logistic model for the banks' credit-granting decision, we then estimate the model with cross-sectional data, as a nonlinear, ordered, sequential logit. Our findings shed light on the criteria used by banks in assessing credit applications and reveal the strong dependence of preferences on demographic characteristics. The results also suggest that agents face significant fixed costs in applying for loans. The fact that we jointly estimate models of both supply and demand sides of the credit market enables us to examine whether particular groups in the population are more frequently credit rationed because they tend to demand more loans or because they are viewed as bad credit risks by lenders.

Adverse Selection and Moral Hazard Effects in the Mortgage Market: An Empirical Analysis

With imperfect information, prices may have sorting and incentive effects that confound the received theory of market behavior.' These effects are more likely to be observed in situations where transactions extend over a lengthy period of time, as in credit and labor markets. Hence, one may observe equilibrium credit rationing or equilibrium unemployment in labor markets, even though these markets are competitive and free of government regulation [7; 8]. In credit markets, higher interest rates may adversely sort good credit risks from bad credit risks. Similarly, higher interest rates may induce borrowers to invest in riskier projects and not to exercise due diligence in the minimization of risks (moral hazard). Either the adverse selection or the moral hazard effects can lead to a reduction in expected profits as the interest rate rises. The supply of loanable funds is an increasing function of expected profits. If expected profits decline over some interval of rising interest rates, then the supply of loanable funds will be concave and backward bending with regard to interest rates over that interval. Stiglitz and Weiss identify the interest rate at which the supply function bends backward as the bank-optimal interest rate [8, 394]. The purpose of this paper is to test the empirical implications drawn from the growing adverse selection and moral hazard literature in the home mortgage market. A recent citation search reveals that the Stiglitz and Weiss [8] paper has been cited over one hundred and fifty times in the last nine years. In his survey of the literature, Stiglitz notes that most of this derivative literature is theoretical and ... that the models . . . have not been the subject of extensive empirical testing [7, 42]. The paper is organized as follows. In section II we review the adverse selection and moral hazard literature, consider the characteristics peculiar to the mortgage market and identify the empirical implications. Section III gives our estimates for the empirical model of the mortgage market. Among other results we find that mortgage supply is a concave function of the rate of

Die voorspelling van kredietrisiko met behulp van biografiese veranderlikes: Is dit die antwoord?

The prediction of credit risk by means of biographic variables: Is this the answer? The objective of this study is to identify specific biographical variables, to quantity them and to investigate their relative importance in the prediction of credit risk. A representative sample of 250 bad credit risk clients and 250 good credit risk clients is used in the study. A multiple stepwise regression analysis and multiple stepwise discriminant analysis were carried out. Nine biographical variables were identified which explain approximately 16% of the variance of credit risk.

ANALYSIS OF A COMMERCIAL BANK MINORITY LENDING PROGRAM: COMMENT

ROBERT EDELSTEIN'S RECENT ARTICLE in this Journal examines the role of banks in financing the development of Black-owned businesses.' In Edelstein's article the key issue is does a bank differentiate between potentially good and potentially bad credit risks (p. 37). His empirical analysis suggests some variables that may be useful for screening the credit worthiness of loan applications from Black entrepreneurs. We share his concern about how banks differentiate between good and bad credit risks, but have serious reservations about his approach and findings. We especially disagree with his interpretation of loan size as an indicator of loan soundness. He examines a sample of 290 Black-owned businesses who received loans from Philadelphia banks between April 1968 and January 1970. A loan was classified to be GOOD or BAD on the basis of its repayment status in January 1970; loans whose repayment was on schedule on that date are GOOD loans, and all others are classified as BAD loans.2 In January 1970, 122 (42%) of the 290 sampled loans were GOOD.3 With this definition of GOOD and BAD loans, Edelstein attempts to explain loan repayment performance (LRP) with loan size and borrower characteristics using two-stage least squares. The dependent variable, LRP, is dichotomous taking on a value of unity for GOOD loans and zero for BAD loans. For the jth loan recipient,

Determining Good and Bad Credit Risks Among High- and Low-Income Families

At present the many low-income families who cannot obtain credit from the large retailers must pay the extremely high credit charges of ghetto merchants-charges that typically are buried in the price of the goods purchased.' Several large retailers use credit scoring systems to identify the relatively good risks among their credit applicants. Insofar as these credit scoring systems are based on samples of current customers which underrepresent low-income families, the criteria derived may not be accurate predictors of the risk class of a low-income credit applicant. There is no strong a priori reason that the variables correlated with high-income goodrisk families should be correlated with low-income good-risk families, given possible social or cultural differences. This investigation was an attempt to discover criteria that can identify relatively good credit risks among low-income families.