Showing papers on "Credit risk published in 2021"
TL;DR: In this article, the authors assess the impact of carbon-neutral lending on the credit risk in the Eurozone and find that the exposure to carbon neutral lending is negatively related to the default risk.
129 citations
TL;DR: In this article, an explainable Artificial Intelligence model is proposed for credit risk management and, in particular, in measuring the risks that arise when credit is borrowed employing peer-to-peer lending platforms.
Abstract: The paper proposes an explainable Artificial Intelligence model that can be used in credit risk management and, in particular, in measuring the risks that arise when credit is borrowed employing peer to peer lending platforms. The model applies correlation networks to Shapley values so that Artificial Intelligence predictions are grouped according to the similarity in the underlying explanations. The empirical analysis of 15,000 small and medium companies asking for credit reveals that both risky and not risky borrowers can be grouped according to a set of similar financial characteristics, which can be employed to explain their credit score and, therefore, to predict their future behaviour.
93 citations
IBM1
TL;DR: A quantum algorithm is presented and analyzed to estimate credit risk more efficiently than Monte Carlo simulations can do on classical computers and how this translates into an expected runtime under reasonable assumptions on future fault-tolerant quantum hardware is analyzed.
Abstract: We present and analyze a quantum algorithm to estimate credit risk more efficiently than Monte Carlo simulations can do on classical computers. More precisely, we estimate the economic capital requirement, i.e. the difference between the Value at Risk and the expected value of a given loss distribution. The economic capital requirement is an important risk metric because it summarizes the amount of capital required to remain solvent at a given confidence level. We implement this problem for a realistic loss distribution and analyze its scaling to a realistic problem size. In particular, we provide estimates of the total number of required qubits, the expected circuit depth, and how this translates into an expected runtime under reasonable assumptions on future fault-tolerant quantum hardware.
86 citations
01 Jan 2021
TL;DR: In this paper, the impact of macro economic factors on stock price of Vingroup (VIC), a big Vietnam real estate firm, in the context Viet Nam and the US economies receive impacts from global economic crisis.
Abstract: After the global economic crisis 2007–2011 and the recent post-low inflation 2014–2015, Viet Nam economies, its financial and stock market as well as real estate market experienced indirect and direct impacts on their operation, system and stock price. Although some economists have done researches on the relationship among macro economic factors such as: consumer price index (CPI), inflation, GDP…, this paper aims to consider the interaction between macro economic factors such as Viet Nam inflation and GDP growth rate, US inflation, exchange rate, risk free rate and other macro factors, and esp. their impacts on stock price of Vingroup (VIC), a big Vietnam real estate firm, in the context Viet Nam and the US economies receive impacts from global economic crisis. This is one main objective of this research paper. This research paper finds out VIC stock price has a negative correlation with risk free rate in VN and deposit rate of VN commercial banks, but has a positive correlation with lending rate in Vietnam. And the statistical analysis will generate results which help us to suggest macro policies in favor of the local stock and financial market. Real estate industrial risk over years has been affected much by macro economic risk, credit risk, and legal risk; therefore, government bodies need to issue proper macro economic legal, financial and credit policies in order to stimulate, develop stock market and reduce workload pressure for Vietnam bank system.
77 citations
TL;DR: The experimental test results indicated that the proposed deep learning ensemble model was generally more competitive when addressing imbalanced credit risk evaluation problems than other models.
77 citations
Journal Article•
TL;DR: This article developed a new technique to estimate vector autoregressions with a common factor error structure by quantile regression and applied their technique to study credit risk spillovers among a group of 17 sovereigns and their respective financial sectors.
Abstract: We develop a new technique to estimate vector autoregressions with a common factor error structure by quantile regression. We apply our technique to study credit risk spillovers among a group of 17 sovereigns and their respective financial sectors between January 2006 and December 2017. We show that idiosyncratic credit risk shocks propagate much more strongly in both tails than at the conditional mean or median. Furthermore, we develop a measure of the relative spillover intensity in the right and left tails of the conditional distribution that provides a timely aggregate measure of systemic financial fragility and that can be used for risk management and monitoring purposes.
76 citations
TL;DR: In this article, the authors investigate the importance of digital financial inclusion, utilizing information and communications technology (DFI-ICT) techniques to promote sustainable growth via economic stability, and the experimental result shows that the classification risk level ratio is achieved to 18.9%, and the error rate of classification of the model is checked.
Abstract: Financial risk is unintended to lose money on an enterprise or investment. Credit risk, Liquidity risk, and operational risk are some more prevalent and unique financial concerns. This is a form of risk that can lead to a capital loss for stakeholders. Building a company from the bottom up is expensive. Any firm may need to go for cash outside to develop at some time in their lives. Financial hazards occur and influence almost every person in various forms and sizes. Digital Financial Services are financial services that rely on customer distribution and the use of digital technologies. While digital financial inclusion (DFI) is important in stimulating economic growth, there is only relatively little empirical data. But whether digital finance is the solution both the bad and the good results of financial inclusion raise. This essay will investigate the importance of digital financial inclusion, utilizing information and communications technology (DFI-ICT) techniques to promote sustainable growth via economic stability. Fast digital technology is currently being used to deliver financial services considerably reduced cost, thereby enhancing financial inclusion and allowing large-scale economic productivity improvements. Although there has been a broad-ranging mention of the benefits of digital finance—financial services offered through mobile telephones, the internet, or cards—we try to measure the size of the economic effect. The experimental result shows that the classification risk level ratio is achieved to 18.9%, and the error rate of classification of the model is checked.
72 citations
TL;DR: The use of BP neural network for early warning and assessment of Internet credit risk has good accuracy and computing efficiency, which expands the application of BP Neural network in the field of Internet finance, and provides a new development direction.
71 citations
TL;DR: A benchmarking study of some of the most used credit risk scoring models to predict if a loan will be repaid in a P2P platform and deals with a class imbalance problem and leverage several classifiers among the mostused in the literature, which are based on different sampling techniques.
Abstract: Credit risk assessment plays a key role for correctly supporting financial institutes in defining their bank policies and commercial strategies. Over the last decade, the emerging of social lending platforms has disrupted traditional services for credit risk assessment. Through these platforms, lenders and borrowers can easily interact among them without any involvement of financial institutes. In particular, they support borrowers in the fundraising process, enabling the participation of any number and size of lenders. However, the lack of lenders’ experience and missing or uncertain information about borrower’s credit history can increase risks in social lending platforms, requiring an accurate credit risk scoring. To overcome such issues, the credit risk assessment problem of financial operations is usually modeled as a binary problem on the basis of debt’s repayment and proper machine learning techniques can be consequently exploited. In this paper, we propose a benchmarking study of some of the most used credit risk scoring models to predict if a loan will be repaid in a P2P platform. We deal with a class imbalance problem and leverage several classifiers among the most used in the literature, which are based on different sampling techniques. A real social lending platform (Lending Club) data-set, composed by 877,956 samples, has been used to perform the experimental analysis considering different evaluation metrics (i.e. AUC, Sensitivity, Specificity), also comparing the obtained outcomes with respect to the state-of-the-art approaches. Finally, the three best approaches have also been evaluated in terms of their explainability by means of different eXplainable Artificial Intelligence (XAI) tools.
71 citations
TL;DR: The supply chain financial risk assessment of SMEs is mainly explored from the perspective of banks and can provide theoretical support for reducing the probability of bank's profit damage and increasing the bank’s profitability.
65 citations
TL;DR: In this paper, the impact of green credit on the core competence of commercial banks was evaluated using Difference-in-Difference-inDifference (DDD) and Difference-In-Differences (DID) measures.
TL;DR: In this article, the authors examined whether the falling house price causes credit risk or not in China and found that bidirectional causal relationships exist in several sub-periods using sub-sample rolling window test.
TL;DR: In this paper, the authors analyzed the liquidity of the emerging market bonds during the Covid-19 fueled uncertainty using bid/offer spreads and showed that the apogee of both, liquidity and credit stresses is reached in late-March, and that although liquidity has improved since then, it has not yet returned to the pre-Covid levels.
TL;DR: This paper evaluates the predictive accuracy of models using alternative data, that may be used instead of credit history, to predict the credit risk of a new account and finds that some classifiers applied to these alternative predictors give sufficiently accurate predictions for these variables to be used when no other data is available.
Abstract: Hundreds of millions of people in low-income economies do not have a credit or bank account because they have insufficient credit history for a credit score to be ascribed to them. In this paper we evaluate the predictive accuracy of models using alternative data, that may be used instead of credit history, to predict the credit risk of a new account. Without alternative data, the type of data that is typically available is demographic data. We show that a model that contains email usage and psychometric variables, as well as demographic variables, can give greater predictive accuracy than a model that uses demographic data only and that the predictive accuracy is sufficiently high for the demographic and email data to be used when conventional credit history data is unavailable. The same applies if merely psychometric data is included together with demographic data. However, we show that different randomly selected training: test sample splits give a wide range of predictive accuracies. In the second part of the paper, using two datasets that include only email usage as a predictor, we compare the predictive performances of a wide range of machine learning and statistical classifiers. We find that some classifiers applied to these alternative predictors give sufficiently accurate predictions for these variables to be used when no other data is available.
TL;DR: In this article, the authors investigated the determinants of the green credit ratio (GCR), and the impact of green credits on the profitability and credit risk of Chinese banks using bank-level data over the period 2011-2018.
TL;DR: The results showed that FA-SVM could improve the accuracy of classification prediction compared with LIBSVM, and decrease the error rate of falseness recognize credible enterprise to untrusted enterprise.
TL;DR: In this article, the authors used a large range of corporate governance measures, financial ratios and macroeconomic variables in a panel data structure over a 17-year period to predict financial distress in China.
Abstract: Corporate governance is an important determinant of corporate performance. Poor corporate governance can damage the interests of shareholders, and may lead to business collapse. This paper expands the literature on credit risk management by assessing the effectiveness of aspects of corporate governance for predicting financial distress in a dynamic discrete-time survival analysis model. It is a comprehensive, up-to-date and thorough study, which uses a large range of corporate governance measures, financial ratios and macroeconomic variables in a panel data structure over a 17-year period. Furthermore, the paper addresses the relationship between government ownership and the risk of financial distress in China. The results suggest that although corporate governance alone is not sufficient to accurately predict financial distress, it can add to the predictive power of financial ratios and macroeconomic factors. In addition, the model provides insights into the role of state ownership, independent directors, institutional investors and some personal characteristics of the Chair of the board. Implications are made regarding them and the debt and bankruptcy problem in China and Asia.
TL;DR: A supply chain theory of (recourse/non-recourse) factoring and reverse factoring shows when these post-shipment financing schemes should be adopted and who really benefits from the adoption, and finds that recourse factoring is preferred when the supplier’s credit rating is relatively high, whereas non-recourses are preferred within certain medium range of ratings.
Abstract: Factoring is a financial arrangement where the supplier sells accounts receivable to the factor against a premium and receives cash for immediate working capital needs. Reverse factoring takes adva...
TL;DR: This paper studied portfolio rebalancing during the quantitative easing program from March 2015 to December 2017, using security-level holdings for all euro-area investors, and found that foreign investors outside the euro area accommodated most of the Eurosystem's purchases.
TL;DR: This article applied a structural model of credit risk to quantify the implied economic impact and distinguish the effects of underlying asset values and uncertainty, which suggests that uncertainty about SLR's future impact, rather than reduced current asset values, drives the effect on bond prices.
Abstract: Coinciding with upward revisions of sea level rise (SLR) projections, municipal bond markets begin pricing increased risk of SLR exposure in 2013. The effect is larger for long-maturity bonds and is not solely driven by near-term flood risk. We apply a structural model of credit risk to quantify the implied economic impact and distinguish the effects of underlying asset values and uncertainty. The SLR exposure premium exhibits a different trend than house prices and is unaffected by controlling for them, which suggests that uncertainty about SLR's future impact, rather than reduced current asset values, drives the effect on bond prices.
TL;DR: In this paper, the authors evaluate the importance of a country's fiscal capacity in explaining the relation between economic growth shocks and sovereign default risk, and find that financial markets penalize sovereigns with low fiscal space, impairing their resilience to external shocks.
TL;DR: The authors survey how the literature has responded to the eurozone debt crisis, placing "lessons learned" in historical perspective, and point out a growing role of sovereign-bank linkages, legal risks, domestic debt and default, and of official creditors, due to new lenders such as China as well as the increasing dominance of central banks in global debt markets.
Abstract: How will sovereign debt markets evolve in the 21st century? We survey how the literature has responded to the eurozone debt crisis, placing “lessons learned” in historical perspective. The crisis featured: (i) the return of debt problems to advanced economies; (ii) a bank-sovereign “doom-loop” and the propagation of sovereign risk to households and firms; (iii) roll-over problems and self-fulfilling crisis dynamics; (iv) severe debt distress without outright sovereign defaults; (v) large-scale “sovereign bailouts” from abroad; and (vi) creditor threats to litigate and hold out in a debt restructuring. Many of these characteristics were already present in historical debt crises and are likely to remain relevant in the future. Looking forward, our survey points to a growing role of sovereign-bank linkages, legal risks, domestic debt and default, and of official creditors, due to new lenders such as China as well as the increasing dominance of central banks in global debt markets. Questions of debt sustainability and default will remain acute in both developing and advanced economies.
TL;DR: This paper highlights the relevance of both quantitative and qualitative features of applicants and proposes a new methodology based on mixed data clustering techniques, which may prove particularly useful in the estimation of credit risk.
Abstract: Credit risk is one of the main risks faced by a bank to provide financial products and services to clients. To evaluate the financial performance of clients, several scoring methodologies have been proposed, which are based mostly on quantitative indicators. This paper highlights the relevance of both quantitative and qualitative features of applicants and proposes a new methodology based on mixed data clustering techniques. Indeed, cluster analysis may prove particularly useful in the estimation of credit risk. Traditionally, clustering concentrates only on quantitative or qualitative data at a time; however, since credit applicants are characterized by mixed personal features, a cluster analysis specific for mixed data can lead to discover particularly informative patterns, estimating the risk associated with credit granting.
TL;DR: This article found that deteriorating deficits are associated with increased financial distress of the banking sector and higher levels of loan-loss provisions, especially for banks with a strong aversion to underprovisioning and robust to a battery of tests and the identification of fiscal shocks using military-spending data.
Abstract: Fiscal deficits represent an important variable for banks’ aggregate credit risk, revealing governments’ ability to curb banks’ losses in bad states, either with direct cash infusions or with macroeconomic stabilization policies. Deteriorating deficits are associated with increasing financial distress of the banking sector and higher levels of loan-loss provisions. The effect is more pronounced for banks with a strong aversion to underprovisioning and is robust to a battery of tests and to the identification of fiscal shocks using military-spending data. This association represents an additional source of negative comovement between provisions and economic conditions, with implications for financial stability.
TL;DR: In this paper, the authors investigated the impact of machine learning and artificial intelligence in credit risk assessment and found that artificial intelligence and machine learning have a strong impact on credit risk assessments using alternative data sources such as public data to deal with the problems of information asymmetry, adverse selection, and moral hazard.
Abstract: In banking and finance, credit risk is among the important topics because the process of issuing a loan requires a lot of attention to assessing the possibilities of getting the loaned money back. At the same time in emerging markets, the underbanked individuals cannot access traditional forms of collateral or identification that is required by financial institutions for them to be granted loans. Using the literature review approach through documentary and conceptual analysis to investigate the impact of machine learning and artificial intelligence in credit risk assessment, this study discovered that artificial intelligence and machine learning have a strong impact on credit risk assessments using alternative data sources such as public data to deal with the problems of information asymmetry, adverse selection, and moral hazard. This allows lenders to do serious credit risk analysis, to assess the behaviour of the customer, and subsequently to verify the ability of the clients to repay the loans, permitting less privileged people to access credit. Therefore, this study recommends that financial institutions such as banks and credit lending institutions invest more in artificial intelligence and machine learning to ensure that financially excluded households can obtain credit.
TL;DR: In this paper, auteurs etudient le lien entre l-exposition des entreprises au risque systematique and l-echeance de leur dette, ainsi que les incidences conjointes of ces deux facteurs sur la structure par terme des ecarts de credit.
01 Jan 2021
TL;DR: In this paper, the authors evaluate explainable AI models for credit risk estimation in real Small and Medium Enterprises data, obtained from official italian repositories, and may form the basis for the employment of such XAI models for post-processing features extraction.
Abstract: In credit risk estimation, the most important element is obtaining a probability of default as close as possible to the effective risk. This effort quickly prompted new, powerful algorithms that reach a far higher accuracy, but at the cost of losing intelligibility, such as Gradient Boosting or ensemble methods. These models are usually referred to as "black-boxes", implying that you know the inputs and the output, but there is little way to understand what is going on under the hood. As a response to that, we have seen several different Explainable AI models flourish in recent years, with the aim of letting the user see why the black-box gave a certain output. In this context, we evaluate two very popular eXplainable AI (XAI) models in their ability to discriminate observations into groups, through the application of both unsupervised and predictive modeling to the weights these XAI models assign to features locally. The evaluation is carried out on real Small and Medium Enterprises data, obtained from official italian repositories, and may form the basis for the employment of such XAI models for post-processing features extraction.
TL;DR: In this paper, the authors investigate the effect of carbon emissions on firms' default risk and identify the ROA and cash flow volatility as potential channels through which emissions affect the default risk.
TL;DR: Long-term reversals in corporate bonds are economically and statistically significant in a comprehensive sample spanning the period 1977 to 2017 as mentioned in this paper, and such reversals are stronger for bonds with high credit risk and more binding regulatory, capital, and funding liquidity constraints.
TL;DR: In this article, the authors explored the correlation between firm risk and capital structure using datasets from the sugar and cement sectors of Pakistan as a developing economy, and found that credit risk and liquidity risk are significantly correlated with leverage.
Abstract: The role of risk assessment and capital structure is vital for the sustainable growth of firms and increasing the shareholders’ wealth. This research explores the correlation between firm risk and capital structure using datasets from the sugar and cement sectors of Pakistan as a developing economy. This study is unique as it involved two firms of different nature (sugar firms operate seasonally while cement firms operate yearly) to view the real picture on the impact of risk and structure assessment on firms’ credibility and shareholders’ wealth. For this purpose, 15-year data (2000–2014) containing the financial statements of the target sectors were collected and the ANOVA analysis was applied with credit risk, liquidity risk, systematic risk, and firm size were used as the regressor variables, firm growth and dividend payout ratio as the control variables, and leverage as the regression variable. The findings showed that credit risk and liquidity risk are significantly correlated with leverage. This suggests that decision-makers pertaining to firms’ risk and efficiency must focus more on risk to pursue a stronger and sustainable increase in shareholder wealth.