Credit Risk Of Borrowers Research Articles

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.

Assessing insurer green finance in response to manufacturing carbon emissions trading in a dragon-king environment: A capped barrier cap option approach

It is essential to examine how carbon trading affects the financial performance of life insurers who offer funding in a challenging dragon-king environment. The primary focus of this study is to evaluate the effects of manufacturing-borrower carbon emissions trading on the insurer's interest margin and insurance stability. To this end, a capped barrier cap option model is developed to capture the manufacturing borrower credit risk from green operations, the quality of the dragon-king environment, and the insurer's equity valuation through liquidity management with life insurance policy loans. The findings of this study indicate that stricter regulatory caps increase insurer interest margins but hurt insurance stability. Additionally, green improvements help increase interest margins but create greater insurance instability. The increase in carbon allowances purchased by the carbon-intensive borrower for production permission increases the insurer's interest margins but reduces insurance instability. These energy policies create insurer profitability and financial instability, causing regulators to reconsider their energy policies from the perspective of fund providers. Our study contributes to the green literature by considering that manufacturing borrower cap-and-trade participation affects insurer performance in a dragon-king environment. The results of this study can inform policymakers and insurers in developing effective carbon trading strategies to balance profitability and stability in challenging environments.

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.

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.

Valuating consumer credit portfolios

This paper proposes a model that associates borrower credit risk with the cash flow method to assess the economic value of a consumer credit portfolio. A Monte Carlo simulation applying the method to an illustrative loan reveals that the lending standards of the institution, captured in the model by the expected and unexpected losses of the contract according to Basel II Internal Rating-Based Approach, is a key driver of the portfolio's intrinsic value, lending support to the evidence that a bank's credit policy and a bank's valuation are associated.

Regulating Frauds in Online Marketplace Lending: A Comparative Study on China and U.S.

Recent platform frauds in the U.S. and other parts of the world raise skepticism about the viability of online marketplace lending (OML), a fast-growing new industry. In China, over one-third of peer-to-peer lending platforms have failed, many involve outright fraud. We find in the U.S., OML platforms profit from loan origination but do not bear borrower credit risk, giving rise to the incentive to overstate borrowers’ quality. In China, most OML platforms are “balance sheet lenders” but not subject to the banking regulations. Failure to control borrower credit risk and moral hazard lead to Ponzi Scheme-type platform-runs. Our comparative case study on Lending Club (NYSE: LC) versus Yirendai (NYSE: YRD), and empirical analysis of 735 OML plat-forms in China confirm these observations. We discuss regulatory responses and market-based solutions including leveraging users’ social networks in lending.

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.

Extreme Learning Machine Enhanced Gradient Boosting for Credit Scoring

Credit scoring is an effective tool for banks and lending companies to manage the potential credit risk of borrowers. Machine learning algorithms have made grand progress in automatic and accurate discrimination of good and bad borrowers. Notably, ensemble approaches are a group of powerful tools to enhance the performance of credit scoring. Random forest (RF) and Gradient Boosting Decision Tree (GBDT) have become the mainstream ensemble methods for precise credit scoring. RF is a Bagging-based ensemble that realizes accurate credit scoring enriches the diversity base learners by modifying the training object. However, the optimization pattern that works on invariant training targets may increase the statistical independence of base learners. GBDT is a boosting-based ensemble approach that reduces the credit scoring error by iteratively changing the training target while keeping the training features unchanged. This may harm the diversity of base learners. In this study, we incorporate the advantages of the Bagging ensemble training strategy and boosting ensemble optimization pattern to enhance the diversity of base learners. An extreme learning machine-based supervised augmented GBDT is proposed to enhance the discriminative ability for credit scoring. Experimental results on 4 public credit datasets show a significant improvement in credit scoring and suggest that the proposed method is a good solution to realize accurate credit scoring.

Analysis of Reporting Consecutive Losses in ABC Finance Plc Since Financial Year 2009/2010: A Case Study

The study mainly focuses on the ABC Finance PLC, a company listed in the Colombo Stock Exchange (CSE) under the diversified financial sector according to the Global Industry Classification Standards (GICS). The company is registered as a licensed finance company and registered finance leasing establishment as well. During the FY 2008/2010 the company has acquired ABC credit card company, a financially weak company that was engaged in local credit card operations, through debt funding, which is a significant event of the company. The main focus of this study is to identify the reasons for reporting consecutive losses in ABC Finance PLC since financial year 2009/2010, and provide recommendations. The study employed ratio analysis and graphical analysis to find out the reasons behind reporting consecutive losses. Accordingly, the study finds that company's interest expense on is higher during the period between FY 2008/2009 to 2017/2018 compared to other financial years because of the acquisition funded by debt. Another observation is loans and advances interest income are decreasing while there is a loan and advances growth in the company, mainly because of more loans being non-Performing as a result of high credit risk of borrowers. The hire purchase interest incomes show a decreasing trend during the period of company making losses mainly because of decrease in the demand for hire purchase service of ABC Finance Plc. Further, the company's fee-based income is decreasing, establishment expenses are increasing, director's emoluments of the company are increased bylarge percentage (395.6%) from FY 2008/2009 to 2009/2010 and it is maintained in the same level after that year which is as a result of a decision made with the intention to motivate the directors to increase the performance. In order to be away from the consecutive loss-making situation, it is recommended that the company should settle the debt obtained for the acquisition to reduce the interest expense on borrowing, reduce the credit risk, engage with promotion for its services, use a performance-based payment method for directors, and have a better expense management system for this company

A credit risk assessment model of borrowers in P2P lending based on BP neural network.

Peer-to-Peer (P2P) lending provides convenient and efficient financing channels for small and medium-sized enterprises and individuals, and therefore it has developed rapidly since entering the market. However, due to the imperfection of the credit system and the influence of cyberspace restrictions, P2P network lending faces frequent borrower credit risk crises during the transaction process, with a high proportion of borrowers default. This paper first analyzes the basic development of China’s P2P online lending and the credit risks of borrowers in the industry. Then according to the characteristics of P2P network lending and previous studies, a credit risk assessment indicators system for borrowers in P2P lending is formulated with 29 indicators. Finally, on the basis of the credit risk assessment indicators system constructed in this paper, BP neural network is built based on the BP algorithm, which is trained by the LM algorithm (Levenberg-Marquardt), Scaled Conjugate Gradient, and Bayesian Regularization respectively, to complete the credit risk assessment model. By comparing the results of three mentioned training methodologies, the BP neural network trained by the LM algorithm is finally adopted to construct the credit risk assessment model of borrowers in P2P lending, in which the input layer node is 9, the hidden layer node is 11 and output layer node is 1. The model can provide practical guidance for China and other countries’ P2P lending platforms, and therefore to establish and improve an accurate and effective borrower credit risk management system.

Credit risk modeling on data with two timestamps in peer-to-peer lending by gradient boosting

It is extremely important for a Peer-to-Peer (P2P) lending platform to provide their lenders with a reliable model to predict borrowers’ credit risk. This study introduces four different gradient boosting methods to model the credit risk of borrowers in P2P platforms and estimates the performance of models in a more practical scenario. The timeliness of observations and features is fully investigated in modeling. Each observation is associated with two timestamps that guide the splitting of data set for training and testing models, while no timestamp or only one timestamp was used in most previous research. The hyperparameters of gradient boosting models are optimized by the Bayesian approach, and the models are evaluated in different scenarios. The importance of features implied by gradient boosting models is examined as well. The empirical result shows that the models’ performance from k−fold cross validation is overestimated in comparison to that from rolling windows guided by two timestamps of observations, which indicates that the timestamps plays a significant impact on evaluating the performance of credit risk models in P2P lending.

Valuating consumer credit portfolios

This paper proposes a model in which the borrower credit risk is associated with the cash flow method to assess the economic value of a consumer credit portfolio. A Monte Carlo simulation applying the method in an illustrative loan reveals that the lending standards of the institution, captured in the model by the expected and unexpected losses of the contract according to the Basel II Internal Rating Based Approach, is a key driver for the intrinsic value of the portfolio, lending support to the evidence that a bank’s credit policy and bank valuation are associated

Community Membership and Reciprocity in Lending: Evidence from Informal Markets

We study how wholesalers assess borrower credit risk and extend trade credit to retailers in economies where formal market institutions, such as financial reporting systems, auditing, and courts, are nonexistent or function poorly. Using the setting of a large market in India, we find that community membership plays a strong role in the access to credit. Wholesalers are more likely to provide trade credit and to offer less restrictive credit terms to within-community retailers, are more lenient when these retailers default, and are less likely to experience defaults from them. Our analyses suggest that this cooperation between same-community wholesalers and retailers is achieved through an indirect reciprocity mechanism, which is sustained by within-community information flows and provides insurance against income shocks.

Personal Credit Risk Evaluation Model of P2P Online Lending Based on AHP

With the rapid development of the P2P (peer-to-peer) online lending industry, which is facing significant credit risk, personal credit evaluation is an important method to reduce credit risk. Based on the various indexes of personal credit risk evaluation of domestic and foreign commercial banks, and according to the characteristics of P2P online lending, this paper analyzes the factors that affect the credit risk of P2P online borrowers, introduces the unique risk factors in the field of Internet information, and constructs an index system of personal credit risk evaluation of P2P online lending, which combines qualitative and quantitative indexes, including six major indexes and 21 small indexes. It then quantifies each index and defines the judgment standard of the evaluation results. Using analytic hierarchy process (AHP), expert scoring method, and fuzzy comprehensive evaluation method, this paper establishes a personal credit risk evaluation model of P2P online lending based on AHP method. The public information of two borrowers on the “PaiPai Lending” platform are selected for experimental verification. The results show that the improved personal credit risk evaluation model has better applicability and can evaluate the borrower’s credit status more scientifically, accurately, and comprehensively; thus, it is an effective method of personal credit risk evaluation of P2P online lending.

Housing Choice Under Borrowing Constraints

ABSTRACT A dramatic decline in the maximum loan amount eligible for Federal Housing Administration (FHA) mortgage insurance in the Salt Lake City, Utah, metropolitan statistical area between 2013 and 2014 provides a natural experiment in the impact of borrowing constraints on housing decisions. Using a difference-in-differences design within a seemingly unrelated regression model, we estimate the impact of this constraint on the size and location of homes purchased by FHA borrowers. We find that borrowers likely constrained by the new loan limits purchased smaller homes with larger downpayments than similar borrowers prior to the loan limit decline. Likely constrained borrowers do not appear to compromise on location, including the quality of local schools. The net effect of the housing choices compelled by the reduction in loan limits does not appear to change the credit risk of borrowers.

The Relevance of Relationship Lending in Times of Crisis

Exploring the Paycheck Protection Program, a setting that allows clear identification of relationship lending effects during the COVID-19 crisis, we find that relationship borrowers receive economically significant larger loans and faster approvals. In the absence of lenders' information advantage motivation documented in prior literature, because the program disregards borrower's credit risk, we examine alternative channels for these benefits. We find that lenders prioritize relationship borrowers mainly due to concerns with the increasing risk of default on borrowers' pre-crisis debt in their portfolios. The benefits we document come with costs. Borrowers are more likely to violate PPP rules when a relationship exists.

Capped borrower credit risk and insurer hedging during the COVID-19 outbreak

In this paper, we apply the risk-neutral valuation methodology to evaluate a life insurer's equity. We model the features capped by the explicit treatment of the borrowing firm's credit risk, the optimal guaranteed rate-setting, and the coronavirus disease (COVID-19) outbreak. The results show that the severe effect of the COVID-19 epidemic on the borrowing firm harms its insurance business but that stringent capital regulation helps. The severe impact of COVID-19 on both the borrowing firm and the insurer hedging harm policyholder protection, thereby adversely affecting insurance stability.

Too Big to Diversify: A Stress Test on Collateralized Loan Obligations

Using detailed loan holding data of Collateralized Loan Obligations (CLOs), we document empirical evidence for systemic risk due to leverage constraints on CLOs. Constrained CLOs fire sell loans downgraded to CCC or below, and thus loans widely held by constrained CLOs experience temporarily lower prices. This instability is exacerbated over time. As the CLO market grows, each CLO's effort to diversify its portfolio leads to similarity in loan holdings among CLOs, such that their leverage constraint binds simultaneously. CLOs' overlapping loan holdings transform idiosyncratic credit risk of large borrowers to systemic risk in the leveraged loan market.