Defaultable Bonds Research Articles

Comparative analysis of machine learning models for bond default forecasting based on financial data of Chinese listed companies

At a time when bond defaults become frequent and market confidence is undermined, the subject of how to accurately predict bond defaults merits investigation. This paper combined popular machine learning methods to predict bond defaults by selecting financial data of 23 listed companies in China that defaulted on credit bonds from 2013 to 2022 and 230 financial data of listed companies that did not default on credit bonds during the same period, using logistic regression, random forest, support vector machine (SVM), and K Nearest Neighbors (KNN) to estimate the probability of bond defaults by listed companies and compare the predictive performance of these methods. The financial data are found to be quite good at predicting bond defaults of listed companies, and the SVM model performs the best.

Research on Corporate Bond Risk Premium and Default Based on Voluntary Dual Ratings Selection

ABSTRACT This study examines the key influencing factors of voluntary dual ratings selection in corporate bond financing and the effect of dual ratings on risk premium and default risk, based on corporate bond data issued from 2016 to 2021. It shows that the worse the bond issuers’ credit qualifications, the more likely they are to seek dual ratings before issuance. Compared to a single credit rating, the risk premium for a bond with dual ratings is lower, and the effect becomes more significant in the low-rated and non-listed company samples. There are dual ratings before bond issuance, and the higher the average credit rating level of the bond, the lower the bond’s default risk. The research findings provide a theoretical basis and empirical evidence for the practice of voluntary dual ratings in China, expand research on the influencing mechanism of bond issuance pricing in the context of voluntary dual ratings selection, and examine the information content of credit ratings from the perspective of their ability to predict bond default.

Explainable Machine Learning for Financial Distress Prediction: Evidence from Vietnam

The past decade has witnessed the rapid development of machine learning applied in economics and finance. Recent evidence suggests that machine learning models have produced superior results to traditional statistical models and have become the driving force for dramatic improvement in the financial industry. However, a much-debated question is whether the prediction results from black box machine learning models can be interpreted. In this study, we compared the predictive power of machine learning algorithms and applied SHAP values to interpret the prediction results on the dataset of listed companies in Vietnam from 2010 to 2021. The results showed that the extreme gradient boosting and random forest models outperformed other models. In addition, based on Shapley values, we also found that long-term debts to equity, enterprise value to revenues, account payable to equity, and diluted EPS had greatly influenced the outputs. In terms of practical contributions, the study helps credit rating companies have a new method for predicting the possibility of default of bond issuers in the market. The study also provides an early warning tool for policymakers about the risks of public companies in order to develop measures to protect retail investors against the risk of bond default.

The intra-regional spillover effects of bond defaults: Evidence from the Chinese corporate debt market

Taking the first bond defaults in each province in China as credit events, we adopt a staggered difference-in-difference model and find that credit spreads of other corporate bonds in the same province increase by 15 basis points, suggesting spillover effects. The spillover effects are stronger on local state-owned enterprises (LSOEs) and non-state-owned enterprises (Non-SOEs) than on central state-owned enterprises (CSOEs). Moreover, the defaults of LSOEs trigger the greatest spillover effects among all types of defaults. Provinces with higher guarantee capability experience fewer spillover effects. Our findings suggest intra-regional spillover effects from investors' shaken beliefs on implicit government guarantees.

Peringkat Obligasi Korporasi: Faktor Internal Perusahaan

Purpose - Bonds are one of the sources of corporate funding. This funding is very efficient and more efficient than funding through banks, significantly since the issuance of corporate bonds fluctuates yearly, which means there is active issuance of corporations. Therefore, there is a lot of interest from investors in choosing corporate bonds. As one of the long-term investment instruments. From this background, the researcher aims to analyze how much and how much influence (1) company size to bond rating, (2) profitability against bond ratings, (3) leverage on bond ratings.
 Research Method - The method in this study belongs to the type of causality with a quantitative analytical application, the population in this study is non-bank corporate bonds and financial institutions that are still traded in 2021, with a sample of 230 corporate bonds from 37 issuing companies. Used is ordinal logistic regression, with SPSS 25 analysis tool.
 Findings - The results of this study indicate that company size harms corporate bond ratings, profitability projected by return on assets, and leverage launched by debt-equity ratio does not affect corporate bond ratings.
 Implication - From the results of this study, it is hoped that issuers can prepare and fix the factors that can improve bond ratings so that the bonds issued are low in default risk and for investors to consider by analyzing the factors that have been studied in this study in investing and avoiding the risk of default bonds and can determine healthy bonds in the long term.

Security Warning Model of Chinese Corporate Bond Defaults Based on Deep Neural Networks

The Chinese bond market has achieved rapid development over the years. However, since the “rigid payment” in China was broken in 2014, the number and size of bond defaults have climbed up promptly and caused huge volatility in bond and even stock markets. To better manage and control the risk of the Chinese corporate bonds market, deep learning can be used as a helpful tool to predict the corporate default risk. This paper constructs a security warning model based on deep neural networks after a reasonable selection of characteristic indicators. By comparing Multi-Layer Perceptron (MLP) with the logistic regression method, it is found that MLP is more suitable in the security warning model to predict the default risk. And, hyper-parameter analyses and ablation study are conducted to explore the performance and accuracy of the best MLP settings. The experimental results show that the deep learning method accommodating the widely chosen factors in the security warning model is effective in predicting corporate bond defaults in China.

Does reputation matter? Evidence on spatial competition in China's bond market

AbstractThis study investigates the effect of market competition on the reputational concerns of credit rating agencies (CRAs) in the Chinese bond market. We find credit ratings increase when the market share distance between an incumbent CRA and its closest peer competitor decreases. This spatial competition effect only exists at the provincial level. We also find the market competition deteriorates the ability of ratings to predict future bond defaults, while the correlation between credit ratings and market‐implied credit spreads is unaffected. Our findings suggest that because of the market inefficiency in emerging economies, CRAs privilege current profits over reputational concerns.

Decoding Default Risk: A Review of Modeling Approaches, Findings, and Estimation Methods

Default risk permeates the behavior of corporate bond returns and spreads, credit default swap spreads, estimation of default probabilities, and loss in default. Pertinent to this review are salient empirical findings and implications of default process estimation from 1974 to 2021. Both structural and reduced-form models are covered. In structural models, default occurs if the value of assets falls below some threshold obligation. The reduced-form models involve assumptions about the default process combined with recovery in default. Default process estimation and measurements of default probability have improved by exploiting data on defaultable bonds, credit default swaps, tally of default realizations, and options on individual equities. Empirical investigations continue to address the relevance of stochastic asset volatility, jumps in asset values, and modeling of default boundary and firm leverage process.

RETRACTED ARTICLE: Application of artificial intelligence technology in financial data inspection and manufacturing bond default prediction in small and medium-sized enterprises (SMEs)

RETRACTED ARTICLE: Application of artificial intelligence technology in financial data inspection and manufacturing bond default prediction in small and medium-sized enterprises (SMEs)

A Giant Falls: The Impact of Evergrande on Asian Stock Indexes

The economic growth of China has been driven by the development of its real estate market, especially after the 2008 crisis. This growth is mostly related to the huge housing bubble and growing amounts of sovereign debt that have been redirected to corporations in the sector. Evergrande is one of those corporations; it is a Chinese company in the construction and real estate sector, a global giant with investments in many parts of the world. Its bond default in September 2021 sounded alerts in financial markets. Several news outlets spoke of the “next Lehman Brothers”, and apprehension was very high, especially in Asian markets. This research work aims to evaluate the impact of Evergrande’s bond default on six Asian stock markets, using an event study approach. The results show a strong reaction from the markets towards the event in study, even anticipating it. Furthermore, it is worth mentioning a quick reversion to “normal” behavior, indicating the rapid absorption of information by the markets.

VIX’s Impact on Chinese Corporate Bond Default

In recent year, Chinese corporate bond default rate continues to grow. Besides international and domestic affects, infection of external risks could cause changes in Chinese corporate bond market. Regarding this issue, this paper investigates the systematic mechanism of global risk infection through the study of VIX’s impact on Chinese Corporate bond default. More specifically, this paper uses VIX index to measures the global risk, and separately use the amount and dollar amount of Chinese corporate bond default rate to measure the condition of the Chinese corporate bond market. The findings of this study show that the default index rises with the increase of the VIX index.

Political uncertainty and bond defaults: evidence from the Chinese market

ABSTRACT In this paper, we provide new evidence on how political uncertainty influences bond default, using China’s local officials’ turnover as a source of plausibly exogenous variation in uncertainty. We find that officials’ turnover increases bond defaults when political links are stronger, indicating that political turnover can destabilize government support for politically connected bonds. Additionally, off-budget resources have expanded China’s local government’s ability to bail out local bonds. Further results show that political connections create zombie bonds that ought to be out but instead to be in the market, reducing the allocative efficiency of financial resources. Our study suggests that, at least in some countries, political uncertainty influences financial risk through the mechanism of political connection.

RETRACTED ARTICLE: Applying blockchain technology in the corporate bond model for default risk assessment under the marketization principle

This work expects to solve the problem that the traditional corporate bond model for default risk assessment has low accuracy and poor data collection and storage robustness. Firstly, this work uses the mature Kealhofer, McQuown, and Vasicek (KMV) model to evaluate the default risk of corporate bonds. Secondly, Blockchain (BC) technology's Information Security (SEC) performance in default risk assessment is studied. Finally, it analyzes the default disposal mechanism of Chinese bond corporates. The Wind database is selected to verify the proposed model. The results show that the proposed BC-based corporate bond model for default risk assessment has a good fitting effect and can meet practical needs. The BC-based data encryption only needs 14.1 ms to obtain a key from an 821-bytes public key. The encryption time and decryption time of the Number Theory Research Unit (NTRU) system are 7.9 ms and 2.9 ms, respectively. Therefore, BC technology shows good performance in data encryption and can improve ISEC. According to the KMV model, corporate bonds have certain default risks. The Distance to Default (DtD) of corporate bonds is 20.8% lower than that of companies. Thus, corporates have higher default risk. Therefore, methods are needed to reduce the default risk and improve the earnings. The finding provides important technical support for effectively reducing the default risk of bond corporates in China and ensuring the healthy development of bond markets.

Perlindungan Hukum Terhadap Investor Pemegang Obligasi Atas Gagal Bayar Yang Dilakukan Oleh Emiten Selama Pandemi Covid-19

The development of the Indonesian Capital Market is currently running very rapidly. The rapid development Indonesian Capital Market can’t be separated from the role of Investors and Issuers as the main actors in the capital market. Bond as one of the investment instrument in Indonesian Capital Market which currently circulating in line with high demand among investor considering bond have lower risk than other capital market instruments. However, investing in bond is not without risk, because Issuer may fail to pay their obligation. The Coronavirus Disease 2019 (Covid-19) Pandemic has caused bond default rates to increase. Such condition can lead to a crisis of Investors confidence in Indonesian Capital Market. Therefore, this study aims to find out and understand the form of legal protection for Investors who suffer losses due to default during Covid-19 Pandemic and the legal actions that can be taken by Investors for losses arising from default. The research method used is normative juridical with descriptive analytical research specification. Based on the Indonesian Civil Code and Indonesian Capital Market Law, it can be concluded that the Issuer who issue bond is responsible for paying bond interest and returning the principal of the bond loan on the maturity date to Investors. Bond default give Investors the right to demand the return of their rights to bond interest and to the principal of maturing bond through the Trustee. Legal actions that can be taken by bondholders are internal dispute settlement, external dispute settlement through Integrated Alternative Dispute Resolution Institution, or through litigation.

China’s Systemic Financial Risk: Basic Dimensions, Key Areas, and Evolving Trends

The COVID-19 pandemic, the regulation of real estate, and external uncertainties are the core variables in the recent evolution of China’s financial risks, and overall planning and structural deployment are the key guarantees for China’s financial stability. From an aggregate perspective, China’s systemic financial risk tended to ease overall in 2021, but remained high. The risk profile of China’s financial system in 2021 presented five important features. First, the macro leverage ratio fell slightly, but exposed the hidden dangers of balance sheet recession. Second, there was a certain blockage in the transmission of financial system liquidity to the real economy. Third, the fragility of the financial system was further exposed, the bond default balance reached a new high, the structural differentiation of bonds between state-owned and private enterprises became prominent, and private enterprise default became more serious. Fourth, the contagion effect of domestic cross-market financial risks remained significant. Fifth, the international political and economic situation was volatile, and spillover effects such as the rising prices of raw materials, the inauguration of a new US administration, and the shift of the Federal Reserve’s monetary policy were significantly strengthened. In terms of key risk areas, the risks of the real estate market, hidden government debt, and small- and medium-sized domestic banks were quite prominent. in 2022, pandemic prevention and control, economic recovery, and structural upgrading will remain the main themes of China’s development. China’s financial risks are generally under control, but the country will still face major risks such as a high macro leverage ratio, tight market liquidity, increasing debt vulnerability, significant spillover effects, and rising volatility in the international market.

Credit Debt Default Risk Assessment Based on the XGBoost Algorithm: An Empirical Study from China

The bond market is an important part of China’s capital market. However, defaults have become frequent in the bond market in recent years, and consequently, the default risk of Chinese credit bonds has become increasingly prominent. Therefore, the assessment of default risk is particularly important. In this paper, we utilize 31 indicators at the macroeconomic level and the corporate microlevel for the prediction of bond defaults, and we conduct principal component analysis to extract 10 principal components from them. We use the XGBoost algorithm to analyze the importance of variables and assess the credit debt default risk based on the XGBoost prediction model through the calculation of evaluation indicators such as the area under the ROC curve (AUC), accuracy, precision, recall, and F1-score, in order to evaluate the classification prediction effect of the model. Finally, the grid search algorithm and k -fold cross-validation are used to optimize the parameters of the XGBoost model and determine the final classification prediction model. Existing research has focused on the selection of bond default risk prediction indicators and the application of XGBoost algorithm in default risk prediction. After optimization of the parameters, the optimized XGBoost algorithm is found to be more accurate than the original algorithm. The grid search and k -fold cross-validation algorithms are used to optimize the XGBoost model for predicting the default risk of credit bonds, resulting in higher accuracy of the proposed model. Our research results demonstrate that the optimized XGBoost model has a significantly improved prediction accuracy, compared to the original model, which is beneficial to improving the prediction effect for practical applications.

A two‐layer stochastic differential investment and reinsurance game with default risk under the bi‐fractional Brownian motion environment

This paper is concerned with the investment and reinsurance problem between two insurance companies and a reinsurance company by constructing a two‐layer stochastic differential game. Insurance companies invest in a risk‐free asset, a defaultable bond, and a risky asset under the bi‐fractional Brownian motion environment; reinsurance companies invest in a risk‐free asset and a risky asset under the bi‐fractional Brownian motion environment. In order to maximize the expected utility of the insurance companies' relative wealth and the expected utility of the reinsurance company's wealth at the terminal time, we solve the Hamilton–Jacobi–Bellman (HJB) equations by using the differential game theory and stochastic optimal control theory and obtain the equilibrium investment–reinsurance and reinsurance premium strategies. Finally, we investigate the influence of the parameters on the equilibrium strategy through numerical examples and analyze its economic implications.

Pricing defaultable bonds under Hawkes jump-diffusion processes

In this paper, we propose a reduced-form model for the embedded credit risk in corporate bonds. We specify the default hazard rate as an affine function of a series of influential variables. To capture the clustering property in some extreme situations, Hawkes jump-diffusion processes are adopted to model the variables. We derive the semi-analytical pricing formula for defaultable bonds. The empirical results from U.S. bond market illustrate the significance of jump clustering when pricing low credit-rating bonds.

A defaultable bond model with cyclical fluctuations in the spread process

A defaultable bond model with cyclical fluctuations in the spread process

On a convergent power series method to price defaultable bonds in a Vasicek-CIR model

In this paper, we prove that the price of a defaultable bond, under a Vasicek short rate dynamics coupled with a Cox-Ingersoll-Ross default intensity model, is a real analytic function, in a neighborhood of the origin, of the correlation parameter between the Brownian motions driving the processes, used to express the dependence between the short rate and the default intensity of the bond issuer. Employing conditioning and a change of numéraire technique, we obtain a manageable representation of the bond price in this non-affine model which allows us to control its derivatives and assess the convergence of the series. By truncating the expansion at the second order, a quadratic approximation formula for the price is then provided. Finally, practical applications of the result are highlighted by performing a numerical comparison with alternative pricing methodologies.