Borrower Risk Research Articles

When shareholders cross-hold lenders’ equity: The effects on the costs of bank loans

We show that syndicated loan spreads are lower as borrowers’ shareholders cross-hold more lenders’ equity. Apart from controlling for borrower and lender fixed effects and various other ownership measures, we address endogeneity concerns by conducting a difference-in-differences analysis exploiting the mergers of institutional investors. Additional tests on cross-holding shareholders’ holding period, the impact of active cross-holders, subsamples of borrowers subject to different degrees of shareholder–creditor conflicts, changes in borrower risk around loan initiation, and the number of financial covenants provide support for the hypothesis that borrower shareholders’ equity holdings of lenders reduce agency costs of debt.

ESG scores and debt costs: Exploring indebtedness, agency costs, and financial system impact

This paper provides evidence that conventional risk measures (Merton Distance to Default, Altman Z-Score, Z-Score and Volatility) fail to capture all the relevant information to assess borrower risk. Moreover, the paper shows that the additional information contained in ESG scores has a negative relationship with the cost of debt, and this relationship is economically significant. In addition, companies whose sustainability generates major concerns (i.e., the most indebted companies and those with the highest agency costs) benefit the most from ESG performance. Finally, the paper provides evidence that the return on companies' ESG efforts in terms of the cost of debt is higher in countries with bank-based financial systems, where long-term relationships between lenders and borrowers prevail, than in countries with market-based financial systems.

ANALYSIS OF LOAN DISBURSEMENT AT PT LAMPUNG BERKAH FINANSIAL TEKNOLOGI

This study investigates the advancements in digital technology and the role of fintech, particularly in the realm of peer-to-peer lending. It specifically focuses on the challenges faced by start-up companies like Lahan Sikam in areas with diverse social structures. The potential risk of default poses a significant threat to consumer confidence. The background section provides an overview of the fintech industry's current state, highlights the challenges faced by Lahan Sikam as a start-up, and establishes objectives to comprehend the company's profile and its funding products. A qualitative research approach with a descriptive methodology was employed at PT Lampung Berkah Finansial Teknologi, where internal control and the application of the 5C principles in credit risk management were observed. Through interviews and observations, the implementation of these principles was revealed. The findings demonstrate that Lahan Sikam has effectively incorporated the 5C principles in assessing borrower risk, focusing on character, capacity, capital, collateral, and conditions.

Data analysis with different variables and credit risk assessment

Nowadays, credit payment is a very common way to pay, such as credit cards, loans, many people can use their credit as a guarantee to borrow money from the bank, however some people will default. So we have to predict whether the borrower will pay on time, it is known as credit risk assessment. In this paper, we analyze a data set on credit risk to predict whether individuals will be late on their payments, helping financial firms improve their earnings and reduce their losses. We not only made predictions on the data, but also analyzed the relationship between the variables that affect the overdue probability to find some specific associations. Specifically, we performed ANOVA analysis and found that married people borrowed significantly more than other groups, and the delinquency rate of people with higher education was lower, and the delinquency rate of married people was higher than that of unmarried people. In addition, we conducted a binary logistic regression and found that gender had no significant impact on the prediction results, but an individuals amount of bill statement, amount of previous payment, past repayment situation and Amount of the given credit had an impact on the prediction results. Other variables, such as marital status and education, can also impact the predicted results. Our research puts forward more factors affecting credit risk and also different angles that can be used to analyzes individual credit risk. This has a guiding role for financial firms like banks and other companies in the financial industry, providing more ways to help them analyze the credit risk of borrowers.

On the factors driving bank lending standards: Global evidence from bank lending surveys

Using a newly available dataset of bank lending surveys for 33 countries, this paper examines the factors driving bank lending standards for credit to enterprises. We find that the balance sheet, competition, and risk perception factors all significantly influence bank lending standards. In addition, we demonstrate that competition is more relevant for easing of lending standards, while collateral and borrower risk are more relevant for tightening of lending standards.

Effect of Loan Assets Classification on Financial Performance of Nigerian Listed Deposit Money Banks

This ex post facto research study examines the effect of loan asset classifications and the impacts of substandard, doubtful, and loss loans on the financial performance of listed deposit money banks in Nigeria. The studied Population included all 14 deposit money banks listed on the Nigerian Stock Exchange (NSE) within the period of 2008 to 2019. The study purposively sampled 10 out of the 14 banks for the purpose of data collection and employed multiple regression analysis of data collated from the annual financial reports of the sampled banks within the studied period. In view of the absence of cross-section effect in the dataset, the pooled independent OLS regression was chosen for analysis and interpretation, revealing that the combined outcome of substandard (SSL) and loss loans (LL) variables are significantly related with the financial performance of listed deposit money banks in Nigeria, while doubtful loans show an insignificant effect on financial performance. The study concludes that bank loans are strong predictor of financial performance in Nigeria, thus it is recommended that banks should eradicate weaknesses such as underwriters’ initial failure to adequately assess borrower risk level prior to issuing loans and to subsequently successfully enforce repayment of the loans.

Mortgage Loan Costs: Magnitude and Drivers of Variation

This article uses national data disclosed as part of the Home Mortgage Disclosure Act (HMDA) to examine variations in loan costs based on type of loan, borrower, purpose (purchase, improvement, or refinance), and neighborhood characteristics. Loan costs are generally higher for nonconventional conforming loans with higher levels of credit risks (loans with higher combined loan-to-value, higher debt-to-income ratios, and for investment properties). This implies that product and borrower risk impact loan costs. However, borrower characteristics such as income and race/ethnicity are also associated with differences in loan costs even after controlling for loan characteristics, location, and lender fixed effects. Total loan costs are higher both in dollar terms and as a share of the loan amount for Black borrowers and Hispanic borrowers, and total loan costs represent a higher share of the loan amount for lower income borrowers. These disparities are larger in neighborhoods with higher levels of lender concentration and implicit racial bias. These findings suggest that in addition to access to mortgages and interest rates, loan costs can represent a barrier for access to homeownership with a disparate impact for Black and Hispanic borrowers, which contributes to perpetuate the homeownership gap.

Entrepreneurial borrowing overdue prediction based on stacking model transfer learning

PurposeBy introducing Stacking algorithm to solve the underfitting problem caused by insufficient data in traditional machine learning, this paper provides a new solution to the cold start problem of entrepreneurial borrowing risk control.Design/methodology/approachThe authors introduce semi-supervised learning and integrated learning into the field of migration learning, and innovatively propose the Stacking model migration learning, which can independently train models on entrepreneurial borrowing credit data, and then use the migration strategy itself as the learning object, and use the Stacking algorithm to combine the prediction results of the source domain model and the target domain model.FindingsThe effectiveness of the two migration learning models is evaluated with real data from an entrepreneurial borrowing. The algorithmic performance of the Stacking-based model migration learning is further improved compared to the benchmark model without migration learning techniques, with the model area under curve value rising to 0.8. Comparing the two migration learning models reveals that the model-based migration learning approach performs better. The reason for this is that the sample-based migration learning approach only eliminates the noisy samples that are relatively less similar to the entrepreneurial borrowing data. However, the calculation of similarity and the weighing of similarity are subjective, and there is no unified judgment standard and operation method, so there is no guarantee that the retained traditional credit samples have the same sample distribution and feature structure as the entrepreneurial borrowing data.Practical implicationsFrom a practical standpoint, on the one hand, it provides a new solution to the cold start problem of entrepreneurial borrowing risk control. The small number of labeled high-quality samples cannot support the learning and deployment of big data risk control models, which is the cold start problem of the entrepreneurial borrowing risk control system. By extending the training sample set with auxiliary domain data through suitable migration learning methods, the prediction performance of the model can be improved to a certain extent and more generalized laws can be learned.Originality/valueThis paper introduces the thought method of migration learning to the entrepreneurial borrowing scenario, provides a new solution to the cold start problem of the entrepreneurial borrowing risk control system and verifies the feasibility and effectiveness of the migration learning method applied in the risk control field through empirical data.

Factors Determining the Loan Default Risk of Individual Borrowers of Banks: An Empirical Study (2021)

Factors Determining the Loan Default Risk of Individual Borrowers of Banks: An Empirical Study (2021)

Loan Risk Prediction Model based on Random Forest

As people's consumption habits change, loan plays a crucial role in our modern society. It provides individuals who do not have sufficient money with funds to purchase residential property or start a business. However, for avoiding unpleasant loan defaults, all financial institutions will first assess the borrower's risk index. By predicting the default risk of the borrower to decide whether to lend money. Machine learning algorithms, including random forest, linear regression and so on, have been benefited most of the real-world applications. With the development of machine learning methods, this paper, based on the personal history loan data of an institution studies the loan default risk, and uses the random forest classification model to predict the possibility of loan default. The result showed that the accuracy of this method was 85.62%, which show its application ability of real-world loan prediction and benefits the manager to decide the degree of risk for loan grant.

Peer-to-Peer (P2P) Lending in Europe: Evaluating the Default Risk of Borrowers in the Context of Gender and Education

In recent years, the importance of social lending activities and their effects on consumers have been highlighted by the widespread use of peer-to-peer lending platforms and the global race in fintech. Our study focuses on factors that affect the likelihood that European borrowers on peer-to-peer lending platforms, which are currently based in Estonia, Finland, and Spain, will default on their loans. Starting with the publicly accessible Bondora database, we examine the different economic and social characteristics of the borrowers to analyze the factors that contributed to loan default between 2013 and 2021. We use a Logit model to calculate the ex-post probability of default for factors derived from Principal Component Analysis as well as the original variables supplied by the database. The results show how crucially important education is for borrowers in lowering the risk of default, along with loan characteristics like high debt levels, long loan terms, and high interest rates. In addition, gender plays an important role in determining loan default, with a particular focus on women's conditions within the family. Regarding financial inclusion and its social implications, our findings suggest different ways to improve financial literacy and promote peer-to-peer lending. Future research could develop on the findings by applying them to other lending platforms and countries.

Bank safety-oriented culture and lending decisions

This study investigates the effects of bank safety-oriented cultures on loan contracts. We regress stock returns during the 1998 Long-Term Capital Management (LTCM) crisis on these risk-taking characteristics and obtain a residual component to proxy the safety-oriented culture of banks. Our empirical results show that banks with a safety-oriented culture increase the probability of signing a contract with low risk borrowers and that they charge lower loan spreads. We also find that these banks ask for more loan covenants to protect their creditor’s rights. Finally, banks with a safety-oriented culture suffer less from borrowers’ defaults and have higher market responses around the dates of loan announcements. Also, our findings reject the alternative hypothesis that banks with a safety-oriented culture only accept less risky lending due to their conservative risk attitude, thus destroying market value for banks.

Prediction of Credit Card Loan Risk Based on Multilayer Perceptron Neural Network Model

Under the background of Internet finance and the popularization of intelligent terminal equipment, the scale of data and the diversity of information have developed exponentially rapidly, while the bad debt rate of personal credit is vague and much higher than that of commercial banks in the traditional technology period. Most of the traditional credit evaluation is driven by models, and the robustness of the risk control system is poor, which cannot meet the increasingly complex demand for default risk prediction. Since commercial banks have accumulated large-scale data assets, it has great significance to combine machine learning technology to help banks extract effective information from massive data and achieve risk assessment of borrowers, thereby reducing the risk of default in borrowing. This paper selects a credit card related data set, uses principal component analysis to extract feature vectors, and obtains a risk assessment index system for borrowers. Then, based on MLP neural network, a credit card loan risk prediction model is constructed. The study reads: The MLP model based on principal component analysis has high accuracy, fast running speed and strong stability. It is an ideal model for commercial banks to evaluate the credit risk of borrowers. This study can provide a new reference for commercial banks to solve the problem of credit risk prediction.

НЕПРАЦЮЮЧІ БАНКІВСЬКІ КРЕДИТИ СУБ’ЄКТІВ ГОСПОДАРЮВАННЯ: ДІАГНОСТИКА ПРОБЛЕМИ ТА ШЛЯХИ ЇЇ ВИРІШЕННЯ

The article establishes that one of the most important problems of the banking system of Ukraine is the growth of the volume and share of non-performing loans. Quantitative estimates of NPLs vary significantly between banks of different groups - the worst is the situation in Privatbank and other state-owned banks, the best is in banks with private domestic and foreign capital. The reasons for the existence of the problem of non-performing loans are determined: objective (external shocks, the long war with the Russian Federation) and subjective (low quality of risk management, lack of credit policy, abuse during the granting of loans, inadequate assessment of collateral, insufficient diversification of loan portfolios, significant concentration of loans in types of economic activity with unfavorable conjuncture). In order to solve the problem of non-performing loans, banks are suggested to improve their internal risk management systems, timely assess and forecast the credit risk of borrowers on a consolidated basis, taking into account related parties, implement mechanisms for early response to the deterioration of the borrower's affairs, apply financial restructuring procedures in a timely and balanced manner, conduct an annual stress testing of the largest bank borrowers. Banks with a high level of NPLs are proposed to create a non-performing assets unit as part of the risk management unit, the functions of which are: preparing conclusions on risks for credit decisions; credit monitoring; valuation of pledged property; checking its availability and condition; assessment of credit risk; supporting the calculation of the bank's reserves for expected credit losses. It is shown that the NBU's regulatory actions are aimed at preventing the creation of new imbalances in the monetary market and reducing existing ones, supporting the smooth functioning of the banking system in the conditions of martial law. It was established that mandatory requirements for banks are the use of audited financial statements to assess the credit risk of large debtors and groups, and its continuous monitoring. After the end of martial law, second-tier banking institutions were asked to update their NPL reduction strategies.

Peer to peer lending risk analysis based on embedded technique and stacking ensemble learning

Peer to peer lending is famous for easy and fast loans from complicated traditional lending institutions. Therefore, big data and machine learning are needed for credit risk analysis, especially for potential defaulters. However, data imbalance and high computation have a terrible effect on machine learning prediction performance. This paper proposes a stacking ensemble learning with features selection based on embedded techniques (gradient boosted trees (GBDT), random forest (RF), adaptive boosting (AdaBoost), extra gradient boosting (XGBoost), light gradient boosting machine (LGBM), and decision tree (DT)) to predict the credit risk of individual borrowers on peer to peer (P2P) lending. The stacking ensemble model is created from a stack of meta-learners used in feature selection. The feature selection+ stacking model produces an average of 94.54% accuracy and 69.10 s execution time. RF meta-learner+Stacking ensemble is the best classification model, and the LGBM meta-learner+stacking ensemble is the fastest execution time. Based on experimental results, this paper showed that the credit risk prediction for P2P lending could be improved using the stacking ensemble model in addition to proper feature selection.

Mathematical Modeling of the Consumer Loan Market in Russia under Sanctions

The article develops and investigates a new model for the formation of interest rates on consumer loans based on an analysis of commercial interests and the logic of behavior of commercial banks. The model assumes that the borrowers’ incomes are described by a geometric Brownian motion. Commercial banks assess the default risk of borrowers. According to the Feynman–Kac formula, the assessment is reduced to solving a boundary value problem for partial differential equations. An analytical solution to this problem is constructed. The model is used to analyze the problem of maintaining consumer credit under the current conditions as a mechanism for social adaptation of households.

Research on SMEs’ Reputation Mechanism and Default Risk Based on Investors’ Financial Participation

Small and micro enterprises (SMEs) play a significant role in the market economy. While online lending has brought financial inclusion for SMEs’ borrowers, it has also increased the default risk, which restricts the normative development of online lending. To explore the impact of the reputation mechanism on borrowers’ default behavior, this paper provides a theoretical model of asymmetric information dynamic games under the online lending mechanism and an empirical study, which takes the number of bidders that reflects the investors’ participation as a proxy variable for the reputation effect factor. The theoretical model showed the borrowers’ default behavior is effectively restrained by the increase in the reputation effect factor in the reputation mechanism, and the empirical study found that an increase in the number of bidders can significantly reduce the risk of borrowers’ default, which verifies the conclusion of the theoretical model.

Dynamic Evaluation Model of the Default Risk of Online Loan Borrowers Based on K-means and SVM

Objective: With the development of Internet finance, the scale of peer-to-peer (P2P) online lending platforms have rapidly expanded. Additionally, the phenomenon of losses among online lending platforms and the problem of default by borrowers have emerged, greatly restricting the healthy development of online lending platforms. Therefore, it is necessary to dynamically set the credit rating of the borrowers according to the performance of the borrowers, and establish a default risk evaluation model for the borrowers of the online lending platform to promote the healthy development of the online lending platform. Method: This paper uses web crawler technology to obtain borrower information as the sample data, selects 17 core variables as explanatory variables, and utilizes project status as the target variable. First, according to the performance of the borrower, we use K-means to cluster, obtain a dynamic credit rating by calculation and reset the rating to obtain new borrower information. Second, we determine the optimal parameters of the support vector machine algorithm through cross-validation and establish the best evaluation model for online loan borrowers' default risk. Finally, we conduct experimental verification. Results: The classification accuracy of the proposed algorithm is better than that of decision trees and random forest, and the classification effect is the strongest. Conclusion: The experimental results show that the model has good stability and generalizability, and the research results provide dynamic decision support for early warnings of online lending platform risk and risk prevention and control; they can thus help promote the healthy development of online lending platforms.

Credit Risk Prediction for Peer-To-Peer Lending Platforms: An Explainable Machine Learning Approach

Small and medium enterprises face the challenge of obtaining start-up fund due to the strict rules and conditions set by banks and financial institutions. The plight yields to the growth in popularity of online peer-to-peer lending platforms which are an easier way to obtain loan as they have fewer rigid rules. However, high flexibility of loan funding in peer-to-peer lending comes with high default probability of loan funded to high-risk start-ups. An efficient model for evaluating credit risk of borrowers in peer-to-peer lending platforms is important to encourage investors to fund loans and justify the rejection of unsuccessful applications to satisfy financial regulators and increase transparency. This paper presents a supervised machine learning model with logistic regression to address this issue and predicts the probability of default of a loan funded to borrowers through peer-to-peer lending platforms. In addition, factors that affect the credit levels of borrowers are identified and discussed. The research shows that the most important features that affect probability of default are debt-to-income ratio, number of mortgage account, and Fair, Isaac and Company Score.

Buffer Model Determination of Systemic Strategic Risks for Borrowers in Force Majeure Circumstances

This study substantiates the concept of systemic strategic risks for borrowers and buffers systemic strategic risk in force majeure to the analyze the credit risk of banks. The authors studied the existing approaches used to assess the creditworthiness of borrowers and the credit risk of banks. The factors that influence the level of credit risk of borrowers are also identified. Quantitative and qualitative parameters of a borrower's creditworthiness, used in banking risk management, are also determined. An economic and mathematical model is proposed to determine the systemic strategic risk buffer for borrowers in force majeure circumstances. It is proposed that technology should be used to create a systemic strategic risk buffer for borrowers for hedging in force majeure circumstances as a monetary policy tool and include Basel III in the requirements of the banking agreement.