Probability Of Default Research Articles

Risk premium in a real business cycle framework

A real business cycle framework with financial and informational frictions is developed for a small open economy in order to analyze the implications of risk premium shocks for aggregate fluctuations. The frictions in the dynamic, stochastic, general equilibrium model necessitate financial intermediation and the uncertainty in the production process requires collateralized borrowing in the economy. Sovereign risk exists in the model due to a government that borrows domestically with a partial default risk. The associated risk premium that the government is subject to is captured both endogenously and exogenously, which constitutes one of the major contributions of this study to the literature. It is shown that a positive, temporary risk premium shock leads to an increase in government borrowing and a decrease in government spending due to the rise in the cost of borrowing for the government. The model also predicts a fall in output, labor supply and loans as well as a rise in the default probability of the government. The results confirm the findings of the literature with respect to the expected effects of a positive risk premium shock on a small open economy in a novel framework, where financial and informational frictions as well as sovereign risk as key features of emerging economies are captured and analyzed.

Comparing lifetime estimates of probability of default for refinancing operations with survival analysis and ensemble methods

We compare different models on estimating the probability of default over a time horizon, considering censored data. Models were fitted from a survival analysis perspective, considering both classic models (Cox Proportional Hazard) with penalized variations and ensemble machine learning methods (boosting and bagging). Using a dataset of credit card refinancing operations, we assess accuracy performance in both out-of-sample and out-of-time observations. We assess well-established metrics, such as the concordance index, and measures that indicate calibration power (integrated Brier score and time-dependent dynamic AUC). Results show that a boosting approach with component-wise regression as base learner outperform other models for short term operations (36 months), in contrast to longer term transactions (60 months), where Cox Proportional Hazard (with and without penalization) depicted better results.

Benchmarking alternative interpretable machine learning models for corporate probability of default

<abstract> <p>In this study we investigate alternative <italic>interpretable machine learning</italic> ("IML") models in the context of <italic>probability of default</italic> ("PD") modeling for the large corporate asset class. IML models have become increasingly prominent in highly regulated industries where there are concerns over the unintended consequences of deploying black box models that may be deemed conceptually unsound. In the context of banking and in wholesale portfolios, there are challenges around using models where the outcomes may not be explainable, both in terms of the business use case as well as meeting model validation standards. We compare various IML models (deep neural networks and explainable boosting machines), including standard approaches such as logistic regression, using a long and robust history of corporate borrowers. We find that there are material differences between the approaches in terms of dimensions such as model predictive performance and the importance or robustness of risk factors in driving outcomes, including conflicting conclusions depending upon the IML model and the benchmarking measure considered. These findings call into question the value of the modest pickup in performance with the IML models relative to a more traditional technique, especially if these models are to be applied in contexts that must meet supervisory and model validation standards.</p> </abstract>

The development of an ESG-rating model to assess the probability of default of corporate borrowers

Nowadays, Russian banks are developing and updating models for assessing the probability of default (PD) for various risk segments of corporate borrowers. This is to enable the use of rating models when assessing regulatory capital, in compliance with the requirements of the Regulations of the Bank of Russia. The application of rating models allows credit institutions to more accurately distribute regulatory and economic capital among borrowers, calculate reserves according to RAS and IFRS, set interest rates for transactions with borrowers as part of the pricing procedure, and conduct stress testing of both borrower portfolios and individual borrowers. The results of stress testing can then be incorporated into strategic planning.One of the Regulator’s requirements is to consider assessments of sustainable development and responsible financing ESG (environmental, social, and corporate governance) indicators as part of the credit risk management procedure, particularly in the development of models for assessing the probability of default. This research focuses on the development of an integral module (ESG rating) that includes ESG indicators. The aim is to improve the accuracy of existing models for assessing the probability of default (PD models) for corporate borrowers through the use of ESG factors. The findings of this research can be utilized by Russian banks to enhance the discriminatory and predictive capabilities of their own PD models, and by the regulator to understand the set of ESG indicators that impact the creditworthiness of corporate borrowers.

An Analysis of Influential Elements of Microcredit Repayment in Covid 19 Crisis: Evidence from Bangladesh

This study investigates the status of microcredit repayment due to the COVID-19 crisis in Bangladesh. The study inspects several socioeconomic factors to discover the probability of default and to avoid delinquency regarding repayments rate. This study focuses on 194 respondents from Bangladesh and apply logistic regression model for executing the analysis. It found several influencing variables from the analysis with significant differentiation that has effects on the microcredit repayments rate. From the predictors, household yearly income in the COVID-19 pandemic was the strongest predictor that was reported as an odds ratio of 1.620. Two other independent variables that made statistically unique significant contributions to the model are difficulty of COVID-19 and number of loans taken by the credit holder. Microcredit Regulations Authority (MRA) and the government of Bangladesh need to implement several policies in order to drive the difficulty of the financial crisis as well as to boost up the repayments rate in crisis periods.

A Hybrid Approach for Predicting Probability of Default in Peer-to-Peer (P2P) Lending Platforms Using Mixture-of-Experts Neural Network

A Hybrid Approach for Predicting Probability of Default in Peer-to-Peer (P2P) Lending Platforms Using Mixture-of-Experts Neural Network

Parametric methods for precision calibration of scoring models

Once a scoring model has been developed for use in assessing a borrower’s credit risk, under the internal ratings-based (IRB) approach, it must be calibrated to a real-world measure of default frequency. The conservativeness of the calibration is tightly controlled, if it is not violated in the allowed number of digits of the rating scale, only then the model is authorized for use. If violated, the calibration probability of default must be raised, placing additional strain on the bank’s capital and reserves. In the presented paper, two new methods to improve the calibration accuracy are proposed. The methods have been tested in practice and provide significantly positive results in certain segments of the loan portfolio.

MORTGAGE REAL ESTATE MARKET: LENDING TO HOUSEHOLDS BY COMMERCIAL BANKS OF UKRAINE DURING THE STATE OF MARTIAL

MORTGAGE REAL ESTATE MARKET: LENDING TO HOUSEHOLDS BY COMMERCIAL BANKS OF UKRAINE DURING THE STATE OF MARTIAL

ESG risks and Corporate Viability: Insights from Default Probability Term Structure Analysis <br>

ESG risks and Corporate Viability: Insights from Default Probability Term Structure Analysis <br>

Stochastic DDM with regime–switching process

This paper introduces a stochastic dividend discount model with regime–switching and conditional heteroscedasticity. We obtain formulas, corresponding to a default probability and $ \ell $-th moment of a random stock price of a company. Next, we connect option pricing, hedging, and equity–linked life insurance products to the stochastic dividend discount model. Also, the paper provides maximum likelihood estimators of parameters of the stochastic dividend discount model. Finally, we present numerical results for the equity–linked life insurance products in the case of Walmart.

Credit Default Probability Prediction Model Based on XGBoost Algorithm

Credit Default Probability Prediction Model Based on XGBoost Algorithm

The impact of ESG performance on the credit risk of listed companies in Shanghai and Shenzhen stock exchanges

<abstract> <p>A more precise and rigorous assessment of the impact of environmental, social, and governance (ESG) performance in business necessitates evaluating various firm characteristics. This study, focused on the ESG impact on enterprise credit risk, employed logistic models that incorporated the ESG rating index alongside other financial-related factors, including organizational structure, risk, and performance. The data were selected from all related listing companies in the Shanghai and Shenzhen stock exchanges. The results affirmed that (1) the risk of default decreased with improved ESG performance; (2) the return on assets, asset turnover ratio, leverage ratio, and operating income growth rate were the main financial factors affecting the default probability of enterprises; and (3) including ESG variables in the prediction model significantly improved the prediction accuracy of the model. The potential policy implications are presented in three perspectives. Businesses should prioritize developing good governance, fulfilling social obligations, and protecting the environment. Second, investors should integrate ESG ratings when making investment strategies. Third, the regulatory authorities are obligated to rapidly harmonize the ESG rating criteria and gradually develop the enterprise ESG information disclosure framework.</p> </abstract>

Spurious Default Probability Projections in Credit Risk Stress Testing Models

Spurious Default Probability Projections in Credit Risk Stress Testing Models

Climate Stress Testing for Mortgage Default Probability

Climate Stress Testing for Mortgage Default Probability

Impact of geopolitical risk on target debt ratio

Geopolitical risks (GPR) expose firms to uncertainties that can affect business operations, corporate decisions, and outcomes. We hypothesize that higher GPR is associated with a lower firm's target debt ratio (TDR) because a higher GPR increases the probability of default. Consistent with our hypothesis, we find a significant negative association between GPR and TDR. Additionally, we observe a significant negative association between GPR and distance-to-default score, supporting our view that higher GPR is linked to a greater probability of default. Further heterogeneity analysis indicates that high-tech firms are more vulnerable to the adverse impact of GPR than low-tech firms.

Machine Learning model based on the Light Gradient Boosting Machine to predict the probability of default in customers of the Credit Card portfolio

Bank loans are a widely used means of payment in recent times, more and more people are accessing products such as credit cards, loans, etc. Banks have implemented classic prediction models, the vast majority based on logistic regression since it allows great interpretability for the business and the effect of the model variables. The purpose of this research is to perform a predictive analysis on the probability of customer default in the credit card portfolio using a risk score. The dataset used is the so-called default of credit card clients Data Set from the UCI Machine Learning DB, the approach is quantitative and the methodology is descriptive analytics, techniques based on gradient boosters will be used to make the prediction, among the trained algorithms We have Logistic Regression with WOE, CatBoost, As a result, the light gradient enhancement machine (LightGBM) tuned with a Bayesian search was obtained, obtaining a GINI of 57.4, which improves by +6 points to the Logistic Regression with Woe and by +3p to XgBoost and CatBoost. Finally, obtaining the Gain and Shapley values made up for the lack of interpretability of the variables, allowing better decision making when evaluating clients. Likewise, as future work, it is intended to add unstructured variables that allow the Model's indicators to be improved.

Political turnover and corporate credit spread: Evidence from China

Using hand-collected data on changes of government officials in 288 Chinese cities from 2002 to 2018, we examine how political turnover affects corporate credit spread in China. We find that political turnover leads to an increase in corporate credit spread. This result is robust after using PSM method and Heckman method to control the endogeneity concerns. The effect is more significant in bonds close to maturity, SOEs and Local SOEs, areas with officials not be promoted and unexpected, and during a market boom. Moreover, we examine whether this effect is a reasonable choice for creditors. We find that political turnover can increase both the default probability and the financial risk of companies.

Mispricing of debt expansion in the eurozone sovereign credit market

We find evidence consistent with risk mispricing in the eurozone sovereign credit market for crisis and non-crisis countries alike, using a novel variable of sovereign debt expansion (DE) that we construct. DE predicts increased default probability, but panel regressions from 2002 to 2017 show a negative association with risk premia, even when controlling for risk appetite and the known determinants of sovereign risk premia. As expected, the negative association was only briefly interrupted by the 2010 Deauville Summit, but it resumed by the onset of the 2011 eurozone crisis. The introduction of quantitative easing in 2015 mutes the negative association, raising the concern of what will happen once quantitative easing ends. Our finding is robust to several model specifications.

Are Bankruptcy Prediction Models Effective for Predicting Ratings? An Empirical Investigation of Altman’s Model in Indian Corporate Sector

The alternative method for predicting credit ratings by employing bankruptcy prediction models is the main subject of the present article. Rating agencies utilize an extremely intricate rating methodology, which differs from agency to agency, and the ratings given by agencies are less reliable in anticipating short-term defaults and react slowly to credit events, as demonstrated by the failure of agencies during the crisis of 2008. Both credit rating assignment and bankruptcy prediction focused on the probability of default, but the methodology used by the two varies significantly: corporate bankruptcy prediction models predict the future default probability of a company as a whole, whereas credit rating only access the default risk associated with a specific instrument. Therefore, it is preferable to employ bankruptcy prediction algorithms to access a company’s future ratings. The present study used Altman’s framework in order to assess whether bankruptcy prediction models can be applied to access a company’s future ratings in advance or not and found that it can be used as an alternative method to predict the future credit ratings, which can be used by investors and banks to make better investment and lending decisions.

Determinants of Repayment Performance of Agricultural Loans Clients of RBDI, Abuyog Branch

The study aimed to present the profile of the agricultural loan clients of RBDI, describe the loan assessment process, describe the loan monitoring process in RBDI, identify the determinants of loan repayment performance of RBDI agricultural loan clients and to recommend courses of action to improve loan application assessment, loan monitoring, and loan collection activities of RBDI. The study used the Logit Regression Analysis and the model Y = β0 + β1X1 + β2X2 + β3X3 + β4X4 + . . . . . . . βnXn + e was developed. The binary response is non-payment (default) and payment (non-default). The determinants were the socio-demographic and socio-economic characteristics of the agricultural loan clients, as well as the loan application and monitoring activities of the bank. The profile of the agricultural loan clients of RBDI showed commonalities of the clients in terms of age (63% are above 45 years old), most of them were not able to finish college (53% secondary level) and most are married (77%) with more than 3 dependents (73%). Age was determined as a statistically significant factor affecting the non-payment or loan default. The increase in family size and schooling dependents also raises the probability of default. The result that higher educational level and increase in dependents reduces the probability of default has to be further verified. As the size of land increases and the farming experience increases, the probability of loan default decreases.