Default Risk Model Research Articles

Opportunity or opportunism? Blockchain technology adoption and corporate default risk

Blockchain technology plays a significant role in new technology infrastructure and has a significant influence on artificial intelligence, big data, and 5 G, and its application has been extended to the Internet of Things, digital asset transactions, digital finance, and so on. In financial systems, it could improve the efficiency of data processing, reduce errors, and detect fraud. However, blockchain adoption could increase the stock price and induce manipulation opportunisms. Managers could also use this advantage to mask their performance and increase corporate default risk. Using the data of Chinese listed companies from 2001 to 2021, we investigate whether blockchain technology adoption could increase or decrease corporate default risk. Using the expected default risk model to estimate the risk, the results show that the default risk increases once the firm adopts blockchain technology, which indicates managerial opportunism behavior. The effect works in firms with CEO duality and higher power consolidation. And similar results are also shown in the dual-duty companies. The results are also robust in instrumental variable tests, difference-in-difference tests (DIDs), firm-fixed effect, placebo tests, and other robustness tests.

Dự báo khả năng vỡ nợ của doanh nghiệp nhỏ và vừa tại Việt Nam: Nghiên cứu trên các mô hình học máy

This study develops a model for predicting default risk (DR) for small and medium-sized enterprises (SMEs) in Vietnam using machine learning methods such as Logistic Regression (LR), Decision Trees, XGBoost, and Artificial Neural Networks (ANN). The data is collected from the financial statements of enterprises borrowing from commercial banks and companies listed on the Vietnamese financial market from 2010 to 2022. The performance of the models is evaluated using metrics such as the F1 score and accuracy (ACC). Results show that Decision Trees, XGBoost, and ANN outperform LR. Specifically, ANN achieves an F1 score of 0.756 and an ACC of 0.9345 on the validation dataset, demonstrating excellent predictive capability. The ANN method has significant potential in identifying high-risk customers, thereby optimizing the credit risk management process. The study also identifies key predictive variables, providing insights for developing more effective DR models. Future research could apply advanced hyperparameter tuning techniques and expand the feature set to optimize the model further

Default Risk Model Using Conditional Generative Adversarial Net by High-Dimensional Financial Time-Series Generation

Default Risk Model Using Conditional Generative Adversarial Net by High-Dimensional Financial Time-Series Generation

Default Probabilities and the Credit Spread of Mexican Companies: The Modified Merton Model

This study aims to identify the model that best approximates the credit spread that should be fixed on debt instruments issued by both companies listed on the Mexican Stock Market, considering the particularities of the Mexican market. Five models were analyzed: Merton’s model, Brownian Motion Model, Power Law Brownian Motion Model, Bloomberg’s model, and the model presented in this paper, which includes the conformable derivatives, taking as a reference the change in the variable as other authors have done, and the Bloomberg corporate default risk model (DRSK) for publics firms. We concluded that the modified Merton model approximates, to a greater extent, the credit spreads that fix on a prime rate on the loans granted to Mexican non-financial companies.

Emerging Market Default Risk Charge Model

In a default event, several obligors simultaneously experience financial difficulty in servicing their debt to the point where the entire market can experience a sudden yet significant jump to a credit default. To help protect lenders against a jump-to-default event, regulators require banks to hold capital equivalent to the default risk charge as a buffer against the losses they may incur. The Basel regulatory committee has articulated and set default risk modelling guidelines to improve comparability amongst banks and enable a consistent bank-wide default risk charge estimation. Emerging markets are unique because they usually have illiquid markets and sparse data. Thus, implementing an emerging market default risk model and, at the same time, complying with the regulatory guidelines can be non-trivial. This research presents a framework for modelling the default risk charge in emerging markets in line with the regulatory requirements. The default correlation model inputs are derived and empirically calibrated using emerging market data. The paper ends with some considerations that regulators, supervisors, and banks can use to get financial institutions to adopt an emerging markets default risk charge model.

Reduced-form models of correlated default timing: a systematic literature review

PurposeThis paper aims to provide an overview, a classification of existing research groups for correlated default models using a reduced-form method and an identification of future research opportunities in the field.Design/methodology/approachA systematic literature review is used for the identification, selection, evaluation and synthesis of relevant literature using keywords regarding the reduced-form default models in the Web of Science database. The authors also add articles from cross-referencing and expert recommendations to the literature. HistCite™ program is used to generate a citation map of the literature.FindingsThe results show that reduced-form correlated default risk models are developing towards modelling credit risk with both observable and unobservable variables. The frailty correlated default model at the firm level is still a potential research field.Originality/valueThis is the first paper systematically reviewing the research on reduced-form models of default timing.

High and Low Credit Risk in SME Portfolios: Evidence from Regulatory Risk Grade Dissemination

Purpose: SME sector credit risk has received attention in research from several dimensions of the financial system. SME sector’s funding is mainly supplied by financial institutions and SME sector is both diversified and large sector in both well developed and less developed economies. Specific research on assessing SME as Financial Institution’s (FI’s) individual counterparties and SMEs as portfolios have developed from a theoretical and empirical perspective. To supplement current research on the area, we approach SME risk from perspective of FIs own risk assessments and compare it to how SME risk rating and measurement compares to other counterparties. Design/methodology/approach: We use published risk rating data from large financial institutions in Europe including globally operating FIs and compare shares of credits in different risk grades and overall portfolio risks within an institution’s own risk classification system and risk measurement system. The data consists of 89 comparable portfolios with over 25 million credits. Findings: Our results show that comparison to households and large corporates originates from higher default rate estimates for SME, which shows as smaller share of credits in the investment grade. SME risk is further raised as even within speculative grades SME’s receives higher default estimates in comparison to households and large corporates. An equally notable finding is that the other relevant parameter for risk calculation, loss given default (LGD), does not differ between SME’s and other counterparties. A part of SME credits is found to be in a low-risk regime in portfolio credit risk estimation. Research limitations/implications: Coverage and detail of data restricts to a specified geographical coverage and aggregated data on SME-companies is not as exact as unit level data. The data represents mostly European institutions as it is collected from institutions which have a head quarter in Europe and are applying Basel regulation in a single rule book environment for banking regulation. In a global scopethere may be differences between jurisdictions or between geographical areas. Data published by institutions is an aggregated data on a rating grade level a and not on a unit level data that institutions have for their exact calculations. Comparison methods for SME sector are selected accordingly so that methods apply to class level instead of unit level data. Originality/value: Higher capital requirements for SME’s may restrict the price and availability of finance. According to our results there can be separated a low-risk SME finance without higher capital requirements compared to peers. Results may also be used to support counterparty level default risk model results showing higher risk for SME’s which can be seen in smaller shares of investment grade credits and in a higher default rate for speculative grade credits.

Merton Model of Default Risk and Stock Return: Evidence from Indonesian Stock Market

The study of the characteristics of risk and return has received great attention. Several studies in finance literature have tested whether default risk influences firms’ stock returns, but the results are often conflicting. Previous research derives varying empirical results because they refer to default risk indicators and samples from different equity markets. The main objective of this study is to evaluate the effect of default risk on stock return using data taken from non-financial companies on the Indonesia Composite Index (IDX Composite) in Indonesia for the 2008-2017 research period. This study uses Merton’s (1974) model as done by Vassalou & Xing (2004) to build a proxy for the risk of default. The advantage of this model is that it considers the volatility of firms’ assets in estimating default risk. Companies can have similar equity and debt levels but possibly have very different default probabilities. The results of the study show that default risk has a positive and significant effect on equity returns.

A latent class Cox model for heterogeneous time-to-event data

Credit risk plays a vital role in the era of digital finance and it is one of primary interests to identify customers with similar types of risk categories so that personalized financial services can be offered accordingly. Motivated by the bourgeoning need for default risk modeling in finance, we propose herein a latent class Cox model for heterogeneous time-to-event data. The proposed model naturally extends the Cox proportional hazards model to flexibly take into account the heterogeneity of covariate effects as often manifested in real data. Without a priori specification of the number of latent classes, it simultaneously incorporates the commonalities and disparities of individual customers’ risk behaviors and provides a more refined modeling technique than existing approaches. We further propose a penalized maximum likelihood approach to identify the number of latent classes and estimate the model parameters. A modified expectation–maximization algorithm is then developed for its numerical implementation. Simulation studies are conducted to assess the finite-sample performance of the proposed approach. Its illustration with a real credit card data set is also provided.

Valuation of Reverse Mortgages with Default Risk Models

Valuation of Reverse Mortgages with Default Risk Models

Profit-based credit models with lender’s attitude towards risk and loss

Profit scoring represents a shift from default risk modeling. Here, lenders align their lending strategies to reflect their profitability objective. This paper proposes models that address the lender’s profit maximization objective. We develop varying cutoff functions that inform lending decisions while considering a lender’s attitude towards risk and loss. We derive two propositions about the properties of the variable cutoff functions for risk-averse and loss-averse lenders. Using a proprietary consumer loan data set, we show the effect of cutoff functions in lending decisions and find that both risk-averse and loss-averse lenders are profitable if they use parameter estimators that support their profitability objective.

A credit rationing model of the medium risk borrowers with low valued collateral

ABSTRACT This paper investigates how the risk and the collateral values are jointly affecting the credit rationing. We propose a credit rationing model of continuous default risk and collateral values and show that the medium risk borrowers with low valued (or high transaction cost) collateral are most vulnerable to the credit rationing.

THE ECONOMIC EXPLAINABILITY OF MACHINE LEARNING AND STANDARD ECONOMETRIC MODELS-AN APPLICATION TO THE U.S. MORTGAGE DEFAULT RISK

This study aims to bridge the gap between two perspectives of explainability−machine learning and engineering, and economics and standard econometrics−by applying three marginal measurements. The existing real estate literature has primarily used econometric models to analyze the factors that affect the default risk of mortgage loans. However, in this study, we estimate a default risk model using a machine learning-based approach with the help of a U.S. securitized mortgage loan database. Moreover, we compare the economic explainability of the models by calculating the marginal effect and marginal importance of individual risk factors using both econometric and machine learning approaches. Machine learning-based models are quite effective in terms of predictive power; however, the general perception is that they do not efficiently explain the causal relationships within them. This study utilizes the concepts of marginal effects and marginal importance to compare the explanatory power of individual input variables in various models. This can simultaneously help improve the explainability of machine learning techniques and enhance the performance of standard econometric methods.

Uncovering the mesoscale structure of the credit default swap market to improve portfolio risk modelling

One of the most challenging aspects in the analysis and modelling of financial markets, including Credit Default Swap (CDS) markets, is the presence of an emergent, intermediate level of structure standing in between the microscopic dynamics of individual financial entities and the macroscopic dynamics of the market as a whole. This elusive, mesoscopic level of organisation is often sought for via factor models that ultimately decompose the market according to geographic regions and economic industries. However, at a more general level, the presence of mesoscopic structure might be revealed in an entirely data-driven approach, looking for a modular and possibly hierarchical organisation of the empirical correlation matrix between financial time series. The crucial ingredient in such an approach is the definition of an appropriate null model for the correlation matrix. Recent research showed that community detection techniques developed for networks become intrinsically biased when applied to correlation matrices. For this reason, a method based on Random Matrix Theory has been developed, which identifies the optimal hierarchical decomposition of the system into internally correlated and mutually anti-correlated communities. Building upon this technique, here we resolve the mesoscopic structure of the CDS market and identify groups of issuers that cannot be traced back to standard industry/region taxonomies, thereby being inaccessible to standard factor models. We use this decomposition to introduce a novel default risk model that is shown to outperform more traditional alternatives.

Asymmetric effects of noise in Merton default risk model: Evidence from emerging Asia

This study extends the application of the Merton (1974) model in six emerging Asian markets to estimate corporate default risk. First, we find that the Merton (1974) model suffers from disproportionate scaling between the book value of debt and the market value of equity due to illiquid corporate bond prices, which we refer to as market-bias. Second, the market-bias is predominantly observed in growth stocks with high price-to-book (PB) value ratios since they are significantly overpriced due to noise-trading. Hence, in the study, we propose the novel approach to control market-bias in the Merton (1974) model by disentangling the asymmetric effects of noise from growth stocks. Third, the analysis uncovered that default probabilities derived from the noise-adjusted Merton model are significantly higher than the Merton model for high and medium-grade firms. Our results provide useful insights to the lenders to ensure financial monitoring and control and the regulators to formulate proactive policies to safeguard economic stability. Besides, our results also benefit investors to assess the default risk of high net worth firms to pre-estimate the portfolio tail risk.

The Bloomberg Corporate Default Risk Model (DRSK) for Public Firms

The DRSK public model estimates forward-looking real-world default probabilities for publicly traded firms. The model also assigns credit grades based on the estimated default probabilities. The product covers firms in all regions and sectors of operation for which the necessary data is available. The DRSK public model was last updated in 2015. This year we are releasing an updated model which improves on the previous model's performance in a variety of ways. The new model's accuracy ratio is above 92%, adjusted pseudo R-squareds have improved, and performance is more in line with observed historical default rates. We describe the new model, analyze its performance in various ways and compare it to the previous model.

The Bloomberg Corporate Default Risk Model (DRSK) for Private Firms

The Bloomberg Corporate Default Risk Model (DRSK) for Private Firms

ESG Investing in Fixed Income: It's Time to Cross the Rubicon

This research is the companion study of three previous research projects conducted at Amundi that address the issue of ESG (Berg et al., 2014; Bennani et al., 2018; Drei et al., 2019). These studies, which were focused on the stock market, showed that 2014 marks a turning point for ESG screening and the performance of active and passive management in developed equities. Indeed, ESG investing tended to penalize both passive and active investors between 2010 and 2013. Contrastingly, ESG investing has been a source of outperformance since 2014 in Europe and North America. Moreover, it appears that ESG investing and factor investing are increasingly connected. In particular, Bennani et al. (2018) and Drei et al. (2019) concluded that ESG is a new risk factor in the Eurozone. The case of fixed income is particular since it has been little studied by academics and professionals. It is true that implementing an ESG investment policy in the bond market is less obvious than in the stock market. For example, in the case of sovereign bonds using ESG filters may dramatically change the profile of the bond portfolio, particularly in terms of liquidity. In fact, it seems that ESG investors pursue two different goals when they consider equities and bonds. They invest in stocks with good ESG ratings in order to avoid extra-financial longterm risks, whereas they consider that fixed income is the field of impact investing. This explains the high demand for green and social bonds, and this also explains why ESG screening is less widely implemented in fixed income markets than in equity markets. The objective of this new study is to explore the impact of ESG investing on asset pricing in the corporate bond market. For that, we apply the methodologies that have been used by Bennani et al. (2018) for testing ESG screening in active and passive management. In particular, we consider the sorted portfolio approach of Fama and French (1992), and the index optimization method that consists in minimizing the active risk with respect to the benchmark while controlling for the ESG excess score. Three investment universes are analyzed: euro-denominated investment grade bonds, dollar-denominated investment grade bonds, and high-yield bonds. Results differ from one universe to another. In the case of EUR IG bonds, we retrieve some common patterns observed by Bennani et al. (2018) in the case of equities. Indeed, from 2010 to 2013, ESG screening has produced a negative alpha, whereas we observe an outperformance since 2014 when we implement ESG scoring in active and passive management. In the case of USD IG bonds, the results are disappointing since ESG screening produces negative alpha for the entire period. Results on high-yield bonds are difficult to interpret since ESG coverage of this market is not satisfactory. We also test how ESG has impacted the cost of corporate debt. Our results show that there is a positive correlation between ESG and credit ratings. This is normal since credit rating agencies also incorporate extra-financial risks in their default risk models. Using the approach developed by Crifo et al. (2017), we propose an integrated credit-ESG model in order to understand the marginal effects of ESG on the cost of capital. We find that there is a negative relationship between ESG scores and yield spreads. The better the ESG rating, the lower the yield spread. For instance, we estimate that the cost of capital difference is equal to 31 bps between a worst-in-class corporate and a best-in-class corporate in the case of EUR IG corporate bonds. In the case of USD IG corporate bonds, the difference is lower but remains significant at 15 bps. Moreover, the impact of ESG is more pronounced for some sectors, for instance Banking and Utility & Energy. These results are important because ESG investing and ESG financing are two sides of the same coin. In order to tackle environmental and social issues, ESG must be a winning bet for both investors and issuers.

Stress Testing and Calibration of Macroprudential Policy Tools

We present a semi-structural model of default risk, which is a function of loan and borrower characteristics, economic conditions, and the regulatory environment. We use this model to simulate bank credit losses for stress-testing purposes and to calibrate borrower-based macroprudential tools. The proposed approach is very flexible and is particularly useful when there is limited history of crisis episodes, when crises bring unanticipated shocks where past tail events offer little guidance and when structural shocks or changes in financial regulations have altered the loan default process. We apply the model to quantify mortgage lending risk in two distinct mortgage markets. For each application, we show a range of modeling adjustments that can be made to capture country-specific institutional features. The model uses bank portfolio data broken down by risk bucket and vintage, which enables us to take explicit account of the loan life cycle and to incorporate the housing and economic cycles. This feature facilitates a timely assessment of banks’ loss-absorbing capacity and the buildup of systemic risk conditional on policy. It also enables counterfactual analysis and the evaluation of macroprudential policy interventions.

Twin Defaults and Bank Capital Requirements

We examine optimal capital requirements in a quantitative general equilibrium model with banks exposed to non-diversifiable borrower default risk. Contrary to standard models of bank default risk, our framework captures the limited upside but significant downside risk of loan portfolio returns (Nagel and Purnanandam, 2020). This helps to reproduce the frequency and severity of twin defaults: simultaneously high firm and bank failures. Hence, the optimal bank capital requirement, which trades off a lower frequency of twin defaults against restricting credit provision, is 5pp higher than under standard default risk models which underestimate the impact of borrower default on bank solvency. JEL Classification: G01, G28, E44