Showing papers on "Credit risk published in 2023"
TL;DR: In this article , a model to price and hedge basket credit derivatives and collateralised loan obligation is presented, which allows a specification of the joint dynamics of credit spreads and default intensities, including a speci¯cation of infection dynamics which cause credit spreads to widen at defaults of other obligors.
Abstract: In
this paper we present a model to price and hedge basket credit derivatives and collateralised
loan obligation. Based upon the copula-approach by Schonbucher and Schubert (2001)
the model allows a specification of the joint dynamics of credit spreads and
default intensities, including a speci¯cation of the infection dynamics which
cause credit spreads to widen at defaults of other obligors. Because of a high
degree of analytical tractability, joint default and survival probabilities and
also sensitivities can be given in closed-form which facilitates the
development of hedging strategies based upon the model. The model uses a generalisation
of the class of Archimedean copula functions which gives rise to more realistic
credit spread dynamics than the Gaussian copula or the Student-t-copula which
are usually chosen in practice. An example speci¯cation using Gamma-distributed
factors is provided.
51 citations
TL;DR: In this paper , the impact of the COVID-19 pandemic on the financial performance, credit risk and capital adequacy of the banks in the Middle East and North Africa (MENA) region, with the determinants of banks' financial performance before and during the pandemic investigated.
Abstract: This article discusses the impact of the COVID-19 pandemic on the financial performance, credit risk and capital adequacy of the banks in the Middle East and North Africa (MENA) region, with the determinants of the banks’ financial performance before and during the pandemic investigated. The data were collected from the Orbis Bank Focus database and banks’ annual financial reports, with descriptive statistics, t-tests and multiple regressions employed to analyse the data. The results revealed that the pandemic negatively and significantly affected the financial performance of the banks, increasing the credit risk, but that it had no significant impact on capital adequacy. Furthermore, the findings indicated that the managerial efficiency, the bank’s size and the gross domestic product had a significant positive impact on the bank’s financial performance in both periods, while in contrast, the credit risk had a negative and significant impact on the banks’ financial performance. Finally, the liquidity risk, capital adequacy, inflation and oil prices had no significant impact on the banks’ financial performance. The findings of this study are important for the banks in the MENA countries given the uncertain future with the recurrent emergence of global crises. Overall, it is recommended that the banks implement strategies to control the credit risks and thus maintain their profitability during such crises.
2 citations
TL;DR: In this article , a neural network with a selective option to increase interpretability of logistic regression models was introduced to distinguish whether linear models can explain the dataset, and the results showed that shallow neural network model leads to much better accuracy without significantly sacrificing interpretability.
2 citations
TL;DR: The authors employed a multivariate extreme value regression model that incorporates a LASSO-type estimator to investigate the tail dependence of the global sovereign credit default swap market conditional on climate change.
2 citations
TL;DR: In this article , the impact of non-interest income on bank credit risk was investigated and a comparative analysis between before and during the COVID-19 pandemic periods was performed, showing that the magnitude of the impact is higher in the pre-pandemic period and significantly reduces during the pandemic period.
2 citations
TL;DR: In this paper , the authors examined the implications of mandatory International Financial Reporting Standards (IFRS) implementation on the rational investment decisions of lenders and borrowers in the emerging market (e.g., the Iraqi credit market).
Abstract: Banks are usually assessed credit risk based on borrowers’ financial statements to monitor credit risk over the life of the lending contract (Beatty, 2008; Golubeva, 2020). Thus, this research examines the implications of mandatory International Financial Reporting Standards (IFRS) implementation on the rational investment decisions of lenders and borrowers in the emerging market (e.g., the Iraqi credit market). Quantitative data were collected, nearly 137000 credit/loan contracts and 500 debenture contracts of almost 750 individual companies. We separate the dataset into two periods, earlier and later IFRS implementation using interaction variables to extract other economic factors’ impact on loan contract stipulation. Even though enhancing the quality of financial statements is the most rational objective of IFRS adoption and implementation, the results show insignificant improvement. IFRS implementation has a limited effect in enhancing financial statements’ quality during the conversion period. This finding supports the view that economic advantages do not essentially contribute to the application of IFRS but depend on other considerations and the level of disclosure practices
2 citations
TL;DR: In this article , the impact of credit risk on bank-specific factors (BSF) and banks in the event of conventional and Islamic banks of Pakistan is investigated from 2007 to 2017, where the failure examination of non-performing loan (NPL) proportion and Z-score is utilized to discover the connections of BSF's on chosen banks.
Abstract:
The impact of credit risk (CR) on bank-specific factors (BSF’s) and banks in the event of conventional and Islamic banks of Pakistan is an essential motivation behind this learning. These banks are chosen by their value commitment. The financial explanation investigation of chosen Islamic and conventional banks is contemplated from 2007 to 2017. Relapse examination of non-performing loan (NPL) proportion and Z-Score is utilized to discover the connections of BSF’s on chosen banks. The Islamic banking system consists of (return on equity (ROE), ROA, liquidity, spread and bank size) having a significant relationship toward credit risk. Therefore, the impact of the Z-score is less for Islamic banks relatively compared to conventional banks. The increased risk of bank debt reflects a strong NPL. In this examination bank, certain factors, for instance, efficiency, return on assets (ROA) and bank dimension, have a significant liaison through credit card risk in the conventional selected banking system, and this process affects overall banking performance. These findings provide valuable insights for policymakers, regulators, and banking professionals to manage credit risk effectively in the context of Pakistan's banking system. The originality of this study lies in its focus on the comparison between conventional and Islamic banks in Pakistan, which has yet to be extensively explored in the literature.
2 citations
TL;DR: In this paper , the authors investigated the relationship between employee training and bank risk to verify whether and to what extent an increase in employee training, as a soft component of total quality management (TQM), affects bank risk.
Abstract: PurposeThis paper aims to investigate the relationship between employee training and bank risk to verify whether and to what extent an increase in employee training, as a soft component of total quality management (TQM), affects bank risk.Design/methodology/approachThe research adopts a panel regression, based on a unique dataset of a sample of Italian banks over the period 2011–2018, to test whether employee training affects bank risk, measured alternatively in terms of Z-score, a proxy of bank stability and non-performing loans (NPLs)/gross loans ratio as a proxy of credit risk.FindingsResearch findings reveal that increasing employee training leads to growing bank stability. In contrast, credit risk is not affected by employee training. However, by investigating training heterogeneity, this study found that the increase in the number of managerial training hours, as a proxy for soft skills training, negatively impacts credit risk. Therefore, an increase in soft skills leads to a reduction in bank credit risk.Research limitations/implicationsThis study provides empirical evidence in support of the relationship between employee training and bank risk, which seems novel in the literature. From a managerial point of view, this study highlights the need for banks to pay attention to the skills, particularly soft skills, that banks' employees must possess to effectively manage bank risk and, more specifically, the core bank risk.Originality/valueEmpirical evidence on the relationship between employee training, soft/hard skills and bank risk appears limited if not absent. Therefore, the findings provide insights for a more nuanced interpretation of variables that affect bank risk.
2 citations
TL;DR: In this article , the effect of credit default swaps (CDS) initiation on reference firms' cost management strategies was examined, and it was found that CDS initiation is associated with a decline in reference firms's cost stickiness.
2 citations
TL;DR: In this article , the authors present a novel computational framework for portfolio-wide risk management problems, where the presence of a potentially large number of risk factors makes traditional numerical techniques ineffective.
Abstract: In this paper, we present a novel computational framework for portfolio-wide risk management problems, where the presence of a potentially large number of risk factors makes traditional numerical techniques ineffective. The new method utilizes a coupled system of BSDEs for the valuation adjustments (xVA) and solves these by a recursive application of a neural network–based BSDE solver. This not only makes the computation of xVA for high-dimensional problems feasible, but also produces hedge ratios and dynamic risk measures for xVA, and allows simulations of the collateral account.
2 citations
TL;DR: In this article , two methodologies for logistic regression with or without two-stage least squares were developed for selecting default risk factors pertaining to Japanese firms given their ESG scores.
TL;DR: In this paper , the effects of the 2008 crisis and Basel III guidelines on the content of the financial reports of Israeli banks were studied, which indicated that already at the time of the crisis, banks had shifted the focus of their reports from market risk to credit and liquidity risks.
TL;DR: In this paper , a machine learning classification framework demonstrating its value analyzing 97,000 individuals and companies from the moment they obtained their first loan up to 12 months afterward, was presented to characterize each borrower according to its credit behavior, and socioeconomic relationships.
Abstract: For more than a half-century, credit risk management has used credit scoring models at each of the well-defined stages of credit risk management. Application scoring is used to decide whether to grant a loan or not, while behavioral scoring is used mainly for portfolio management and to take preventive actions in case of default signals. In both cases, social network data has recently been shown to be valuable to increase the predictive power of these models, especially when the borrower’s historical data is scarce or not available. This study aims to understand the dynamics of creditworthiness assessment performance and how it is influenced by credit history, repayment behavior, and social network features. To accomplish this, we build up a machine learning classification framework demonstrating its value analyzing 97,000 individuals and companies from the moment they obtained their first loan up to 12 months afterward. Our original and massive dataset allowed us to characterize each borrower according to its credit behavior, and socioeconomic relationships. Our study finds that credit scoring based on borrowers’ history improves performance at a decreasing rate during the first six months and then stabilizes. The most notable effect on the performance of credit scoring based on social network features occurs in loan applications; for personal scoring, this effect prevails for approximately six months, while for business scoring, social network features add value throughout the entire study period. These findings are of great value to improve credit risk management and optimize the combined use of both the traditionally exploited information and new alternative data sources.
01 Mar 2023
TL;DR: In this paper , the authors consider the role of supply chain relationships as a powerful channel for default risk contagion and show that increases in banks' default risk from the banking crisis of 2007-2008 propagated strongly to U.K. non-financial firms via supply chains.
Abstract: How does banks' default risk affect the probability of default of non-financial businesses? The literature has focused on the banks' direct corporate customers. It fails to consider the role of supply chain relationships as a powerful channel for default risk contagion. Our paper fills this gap by analyzing the direct as well as the indirect impact of banks' default risk on firms' default risk in the U.K. Relying on Input-Output tables, we devise methods that enable us to examine this question in the absence of data on firm-to-firm linkages. To capture all potential propagation channels, we account for horizontal and vertical linkages, both between the firm and upstream industries (suppliers) and between the firm and downstream industries (customers). We further examine how trade credit and contract specificity amplify or dampen the propagation of default risk. Our results show that increases in banks’ default risk from the banking crisis of 2007–2008 propagated strongly to U.K. non-financial firms via supply chains.
TL;DR: In this paper , the authors investigated the relationship between natural disasters and the reaction of sovereign CDS spread in Europe and found that the advent of a natural disaster can increase inequality between the regions due to the higher cost of credit for sovereigns and the reduced scope for manoeuvring public finances.
TL;DR: In this paper , the authors construct both traditional risk and ML-based profit models and find that profit score cutoffs generally target wealthy, high-spending, "revolving" customers, while risk score cutoff target low-activity "transacting" customers.
Abstract: Retail credit issuers traditionally assign credit based on cutoffs from risk-based models. However, in recent years, advances in technology such as AI/ML have given rise to more models that predict more complicated facets of customer behavior, such as projected NPV. These can be used to precisely target profitable but risky customers. Using a unique regulatory panel dataset of credit cards combining data from many major banks, I construct both traditional risk and ML-based profit models and find that profit score cutoffs generally target wealthy, high-spending, “revolving” customers, while risk score cutoffs target low-activity “transacting” customers. Conducting simulations using both types of cutoffs, I find that, absent risk guardrails, profit-based underwriting could potentially cause an increase in riskiness in card portfolios. However, this is highly portfolio dependent and may only occur in those that concentrate on “revolvers” in the lower end of the credit spectrum.
TL;DR: In this article , the authors reviewed the risk management structure and instruments of credit risk management in India and recommended that banks should be more pre-emptive than post-dynamic in their credit risk managements rehearses.
Abstract: The issue of risk management in banks has turned into the focal point of discussion after the new monetary emergencies. A few endeavours have been made to further develop the risk management and execution of banks including presenting the Basel Accords just as risk management rules by national banks. Thus, the State Bank of India has given risk management rules to fortify the risk management framework and to work on the exhibition of the neighbourhood banks. The purpose of the study is to review the risk management structure and instruments of credit risk management in India. This study incorporates secondary data. After gathering the significant data, the applicable data is changed over into an even structure. The statistical devices which are considered for the review are trend and ratio analysis. Based on the results, the study recommends that banks should be more pre-emptive than post-dynamic in their credit risk management rehearses.
Keywords: Advances, banks, loans, management, practices, risk;
01 Jan 2023
TL;DR: In this article , the authors analyzed the impact of non-performing loans on the economy and proposed appropriate recommendations for maintaining financial sustainability based on the results of a regression model and a correlation matrix.
Abstract: Credit risk is particularly important for the banking system and any financial institution. The risk associated with lending affects not only financial institutions but also other sectors with a “domino” effect. Therefore, it is important to assess the impact of loans, including non-performing loans, their degree of risk, and based on their analysis, it is necessary to draw fair conclusions in terms of forecasting. The aim of the paper is to analyze the impact of non-performing loans on the economy. The paper examines foreign trends and Georgia’s reality regarding non-performing loans. It has been assessed how risky the credit portfolio of commercial banks in Georgia is. The article assesses the impact of the pandemic on the share of non-performing loans and the financial system. In our research, a separate analysis of the influence of factors affecting non-performing loans and interrelationships between variables is made using a regression model and a correlation matrix. Based on the results, the article draws conclusions and offers appropriate recommendations for maintaining financial sustainability.
TL;DR: Wang et al. as discussed by the authors constructed FinTech development indicators of commercial banks through web crawler, and used the data of 138 Chinese commercial banks from 2013 to 2021 to investigate the impact of the development of FinTech on bank credit risk.
TL;DR: In this paper , the authors investigated the impact of environmental, social, and governance (ESG) ratings on sovereign credit risk using a market-based, structural and an analyst-based approach, while ESG scores are obtained from three different rating agencies.
TL;DR: In this article , a clustering based fuzzy classification (CBFC) method for credit risk assessment is proposed, where membership values obtained as a result of the fuzzy k-means clustering algorithm are used for the purpose of better capturing the structure of an existing system.
Abstract: Credit scoring is a crucial indicator for banks to determine the financial position and the eligibility of a client for credit. In order to assign statistical odds or probabilities to predict the risk of nonpayment in relation to many other factors, the scoring criterion becomes an important issue. The focus of this study is to propose a clustering based fuzzy classification (CBFC) method for credit risk assessment. We aim to illustrate the beneficial use of machine learning (ML) methods whose prediction power is increased by adopting fuzzy theory to calculate the default risk with a better selection of the features contributing to it. An important feature of the CBFC method is that membership values obtained as a result of the fuzzy k-means clustering algorithm are used for the purpose of better capturing the structure of an existing system. An extensive comparison is performed to show how CBFC performs compared to the traditional ones for the datasets having different characteristics in terms of the variable types. Five different real-life datasets are studied to expose the contribution of fuzzy approach on improving the ML use. Our findings show that the proposed CBFC models can produce the promising classification results in credit risk evaluation which aid the practitioners and decision makers for issuance of credit purposes.
TL;DR: Li et al. as mentioned in this paper proposed a credit-risk-prediction model for listed companies based on a CNN-LSTM and an attention mechanism, their approach is based on the benefits of the long short-term memory network (lSTM) model for long-term time series prediction combined with a convolutional neural network (CNN) model.
Abstract: The financial market has been developing rapidly in recent years, and the issue of credit risk concerning listed companies has become increasingly prominent. Therefore, predicting the credit risk of listed companies is an urgent concern for banks, regulators and investors. The commonly used models are the Z-score, Logit (logistic regression model), the kernel-based virtual machine (KVM) and neural network models. However, the results achieved could be more satisfactory. This paper proposes a credit-risk-prediction model for listed companies based on a CNN-LSTM and an attention mechanism, Our approach is based on the benefits of the long short-term memory network (LSTM) model for long-term time-series prediction combined with a convolutional neural network (CNN) model. Furthermore, the advantages of being integrated into a CNN-LSTM model include reducing the complexity of the data, improving the calculation speed and training speed of the model and solving the possible lack of historical data in the long-term sequence prediction of the LSTM model, resulting in prediction accuracy. To reduce problems, we introduced an attention mechanism to assign weights independently and optimize the model. The results show that our model has distinct advantages compared with other CNNs, LSTMs, CNN-LSTMs and other models. The research on the credit-risk prediction of the listing formula has significant meaning.
TL;DR: In this article, stacked unidirectional and bidirectional LSTM (long short-term memory) networks are applied in solving credit scoring problems for the first time, and the proposed robust model exploits the full potential of the three-layer stacked LSTMs and BDLSTMs with the treatment and modeling of public datasets in a novel way.
Abstract: Credit scoring is one the most important parts of credit risk management in reducing the risk of client defaults and bankruptcies. Deep learning has received much attention in recent years, but it has not been implemented so intensively in credit scoring compared to other financial domains. In this article, stacked unidirectional and bidirectional LSTM (long short‐term memory) networks as a complex area of deep learning are applied in solving credit scoring problems for the first time. The proposed robust model exploits the full potential of the three‐layer stacked LSTM and BDLSTM (bidirectional LSTM) architecture with the treatment and modeling of public datasets in a novel way since credit scoring is not a time sequence problem. Attributes of each loan instance were transformed into a sequence of the matrix with a fixed sliding window approach with a one‐time step. Our proposed models outperform existing and much more complex deep learning solutions thus we succeeded in preserving simplicity. In this article, measures of different types are employed to carry out consistent conclusions. The results by applying three hidden layers on the German Credit dataset showed an accuracy of 87.19%, for Kaggle dataset accuracy reached 93.69%, and for Microcredit dataset accuracy of 97.80%.
TL;DR: The authors assesses whether a climate factor is relevant to measure default risk in a sample of main companies listed on the STOXX Europe 600 exchange from 2010 to 2020 and find that relevant differences in default risk exist before and after the Paris Agreement.
Abstract: Abstract This paper assesses whether a climate factor is relevant to measure default risk in a sample of main companies listed on the STOXX Europe 600 exchange from 2010 to 2020. The starting point is a factorial panel data model which is subsequently modified to capture the climate impact through different functional forms. We find that relevant differences in default risk exist before and after the Paris Agreement. Our analysis also indicates that this difference cannot be explained by means of traditional financial factors. Finally, we further show that a climate change risk and opportunities label is a significant factor in evaluating credit risk, both prior to and post-Paris agreement. These results are important to the extent that they suggest that companies' market performance itself allows to measure differences in credit risk between companies and to link them with climate risk factors. This approach may be useful as a complement or in combination with the traditional use of exogenous climate factors that have been widely used in the literature in this field.
TL;DR: In this paper , the role of credit risk management in performance of commercial banks in Erbil is analyzed and five research hypotheses are developed to measure the role and effect of risk management on the performance of banks.
Abstract: The current study aims to analyze the role of credit risk management in performance of commercial banks in Erbil. There is a high danger of insolvency and financial troubles for banks because of this method of loan origination. As shown by high levels of nonperforming loans, the KRG banking system's Commercial Bank Supervision Report found that most banks failed due to poor credit risk management. Due to the high level of non-performing loans, the profitability of the bank was damaged. The study developed five research hypotheses to measure the role of credit risk management in performance of commercial banks in Erbil. It was decided to use a quantitative approach to investigate the effect credit risk management has on the financial performance of commercial banks. 88 people from the Credit Risk Management departments of several commercial banks around the nation were selected as a convenience sample. These respondents included senior, intermediate, and practical level personnel. The study found that commercial banks with lower levels of nonperforming loans and capital adequacy ratios had higher returns on assets, indicating more effective methods of credit risk management. Total loans divided by the loan loss reserve ratio is the amount set aside for losses. The quality of a loan portfolio degrades as the ratio rises. The study recommended to improve credit risk identification, measurement, monitoring and controlling at selected commercial banks in Erbil.
TL;DR: In this article , the authors examined the determinants of credit risk management and their relationship with the performance of commercial banks in Nepal and found that credit appraisal measurements have a significant effect on credit riskmanagement.
Abstract: In recent years, after the global financial crisis, the issue of credit risk management has received increased attention from international regulators. Credit risk management frameworks are often not sufficiently integrated within the organization, there is no unified approach, and there is no holistic view of all risks. Likewise, where they exist, sound risk management practices have helped institutions to weather financial crises better than others. Therefore, the current study aimed to examine the determinants of credit risk management and their relationship with the performance of commercial banks in Nepal. It also examines the mediating role of credit risk management on the performance of commercial banks in Nepal. The results indicate that there is a positive relationship between environmental risk and credit risk management. It is also found that credit appraisal measurements have a significant effect on credit risk management. The results reveal that market risk analysis has a significant effect on credit risk management. The results show that credit risk management mediates the relationship between environmental risk, credit appraisal measurements, market risk analysis, and the performance of commercial banks. Therefore, managers should strive to impart risk prevention and control mechanisms to reduce credit risk and achieve good financial performance.
TL;DR: In this article , the authors investigated the impact of country risk on the credit risk of the banking sectors operating in Brazil, Russia, India, China, and South Africa (BRICS), emerging countries.
Abstract: Abstract This study aims to fill the gap in the literature by specifically investigating the impact of country risk on the credit risk of the banking sectors operating in Brazil, Russia, India, China, and South Africa (BRICS), emerging countries. More specifically, we explore whether the country-specific risks, namely financial, economic, and political risks significantly impact the BRICS banking sectors’ non-performing loans and also probe which risk has the most outstanding effect on credit risk. To do so, we perform panel data analysis using the quantile estimation approach covering the period 2004–2020. The empirical results reveal that the country risk significantly leads to increasing the banking sector’s credit risk and this effect is prominent in the banking sector of countries with a higher degree of non-performing loans (Q.25 = − 0.105, Q.50 = − 0.131, Q.75 = − 0.153, Q.95 = − 0.175). Furthermore, the results underscore that an emerging country’s political, economic, and financial instabilities are strongly associated with increasing the banking sector’s credit risk and a rise in political risk in particular has the most positive prominent impact on the banking sector of countries with a higher degree of non-performing loans (Q.25 = − 0.122, Q.50 = − 0.141, Q.75 = − 0.163, Q.95 = − 0.172). Moreover, the results suggest that, in addition to the banking sector-specific determinants, credit risk is significantly impacted by the financial market development, lending interest rate, and global risk. The results are robust and have significant policy suggestions for many policymakers, bank executives, researchers, and analysts.
TL;DR: In this paper , a generalized backward stochastic differential equations (BSDE) up to a random time horizon is studied, which is not a stopping time with respect to a reference filtration.
Abstract: Motivated by structural, reduced-form and hybrid models of the third party and counterparty credit risk, we study a generalized backward stochastic differential equations (BSDE) up to a random time horizon ϑ, which is not a stopping time with respect to a reference filtration. In contrast to the existing literature in the area of credit risk modeling, we do not impose specific assumptions on the random time ϑ and we study the existence of solutions to BSDE and reflected BSDE with a random time horizon through the method of reduction. For this purpose, we also examine BSDE and reflected BSDE with a làdlàg driver where the driver is allowed to have a finite number of jumps overlapping with jumps of the martingale part. Theoretical results are illustrated by particular instances of a random time and explicit BSDEs in either the Brownian or Brownian-Poisson filtration.
TL;DR: In this article , the authors designed a framework for analyzing the credit risk rate of debtors so that the default risk can be reduced by using the integration of factor analysis and Tsukamoto's fuzzy logic method.
Abstract: Giving credit to debtors can pose a default risk. This risk arises because of an error in analyzing the credit risk rate of the debtor. Therefore, this study aims to design a framework for analyzing the credit risk rate of debtors so that the default risk can be reduced. This framework is created using the integration of factor analysis and Tsukamoto’s fuzzy logic method. This integration method can group many credit assessment variables into several decisive factors. In addition, the integration method can estimate credit risk rate firmly based on the α-predicate of each basic rule. This analytical framework is simulated on credit application data at a Rural Bank, in Indonesia. The simulation results show that there are three factors and one variable to measure the credit risk rate, namely: factor 1 represents repayment capacity, business length, working capital, and liquidity value; factor 2 represents the age and the difference between the granted and the proposed loan amount; factor 3 represents the stay length, character, and credit history; and one variable represents a dependent number. This research is expected to help credit institutions measure the credit risk rate in making credit decisions for prospective debtors.