Showing papers on "Credit risk published in 2020"

Sustainable Solutions for Green Financing and Investment in Renewable Energy Projects

Abstract: The lack of long-term financing, the low rate of return, the existence of various risks, and the lack of capacity of market players are major challenges for the development of green energy projects. This paper aimed to highlight the challenges of green financing and investment in renewable energy projects and to provide practical solutions for filling the green financing gap. Practical solutions include increasing the role of public financial institutions and non-banking financial institutions (pension funds and insurance companies) in long-term green investments, utilizing the spillover tax to increase the rate of return of green projects, developing green credit guarantee schemes to reduce the credit risk, establishing community-based trust funds, and addressing green investment risks via financial and policy de-risking. The paper also provides a practical example of the implementation of the proposed tools.

The risk of being a fallen angel and the corporate dash for cash in the midst of COVID

Abstract: Data on firm-loan-level daily credit line drawdowns in the United States reveals a corporate "dash for cash" induced by COVID-19. In the first phase of extreme precaution and heightened aggregate risk, all firms drew down bank credit lines and raised cash levels. In the second phase following the adoption of stabilization policies, only the highest-rated firms switched to capital markets to raise cash. Consistent with the risk of becoming a fallen angel, the lowest-quality BBB-rated firms behaved more similarly to non-investment grade firms. The observed corporate behavior reveals the significant impact of credit risk on corporate cash holdings.

Does bank FinTech reduce credit risk? Evidence from China

Abstract: Using data from Chinese commercial banks between 2008 and 2017, this paper explores the effects of bank FinTech on credit risk. We first construct and measure a bank FinTech index using web crawler technology and word frequency analysis. The results show that the development of bank FinTech is faster in state-owned banks than in other banks. Moreover, among the five subareas of bank FinTech, the development of internet technology is ahead of artificial intelligence technology, blockchain technology, cloud computing technology, and big data technology. Then, the impacts of bank FinTech on credit risk are examined. We find that bank FinTech significantly reduces credit risk in Chinese commercial banks, and further analyses show that the negative effects of bank FinTech on credit risk are relatively weak among large banks, state-owned banks, and listed banks.

Corporate default forecasting with machine learning

Abstract: We analyze the performance of a set of machine learning models in predicting default risk, using standard statistical models, such as the logistic regression, as a benchmark. When only a limited information set is available, for example in the case of an external assessment of credit risk, we find that machine learning models provide substantial gains in discriminatory power and precision, relative to statistical models. This advantage diminishes when confidential information, such as credit behavioral indicators, is also available, and it becomes negligible when the dataset is small. Moreover, we evaluate the consequences of using a credit allocation rule based on machine learning ratings on the overall supply of credit and the number of borrowers gaining access to credit. Machine learning models concentrate a greater extent of credit towards safer and larger borrowers, which would result in lower credit losses for their lenders.

The Risk of Being a Fallen Angel and the Corporate Dash for Cash in the Midst of Covid

Abstract: Data on firm-loan-level daily credit line drawdowns in the United States expose a corporate “dash for cash” induced by the COVID-19 pandemic. In the first phase of the crisis, which was characterized by extreme precaution and heightened aggregate risk, all firms drew down bank credit lines and raised cash levels. In the second phase, which followed the adoption of stabilization policies, only the highest-rated firms switched to capital markets to raise cash. Consistent with the risk of becoming a fallen angel, the lowest-quality BBB-rated firms behaved more similarly to non-investment grade firms. The observed corporate behavior reveals the significant impact of credit risk on corporate cash holdings.

Financial Defaulter Detection on Online Credit Payment via Multi-view Attributed Heterogeneous Information Network

Abstract: Default user detection plays one of the backbones in credit risk forecasting and management. It aims at, given a set of corresponding features, e.g., patterns extracted from trading behaviors, predicting the polarity indicating whether a user will fail to make required payments in the future. Recent efforts attempted to incorporate attributed heterogeneous information network (AHIN) for extracting complex interactive features of users and achieved remarkable success on discovering specific default users such as fraud, cash-out users, etc. In this paper, we consider default users, a more general concept in credit risk, and propose a multi-view attributed heterogeneous information network based approach coined MAHINDER to remedy the special challenges. First, multiple views of user behaviors are adopted to learn personal profile due to the endogenous aspect of financial default. Second, local behavioral patterns are specifically modeled since financial default is adversarial and accumulated. With the real datasets contained 1.38 million users on Alibaba platform, we investigate the effectiveness of MAHINDER, and the experimental results exhibit the proposed approach is able to improve AUC over 2.8% and Recall@Precision=0.1 over 13.1% compared with the state-of-the-art methods. Meanwhile, MAHINDER has as good interpretability as tree-based methods like GBDT, which buoys the deployment in online platforms.

Explainable AI in Fintech Risk Management

Abstract: The paper proposes an explainable AI model that can be used in fintech risk management and, in particular, in measuring the risks that arise when credit is borrowed employing peer to peer lending platforms. The model employs Shapley values, so that AI predictions are interpreted according to the underlying explanatory variables. The empirical analysis of 15,000 small and medium companies asking for peer to peer lending 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 and understand their credit score and, therefore, to predict their future behavior.

How Connected is the Global Sovereign Credit Risk Network

Abstract: This paper estimates the global network structure of sovereign credit risk by applying the Diebold-Yilmaz connectedness methodology on sovereign credit default swaps (SCDSs). The level of credit risk connectedness among sovereigns, which is quite high, is comparable to the connectedness among stock markets and foreign exchange markets. In the aftermath of the recent financial crises that originated in developed countries, emerging market countries have played a crucial role in the transmission of sovereign credit risk, while developed countries and debt-ridden developing countries have played marginal roles. Secondary regressions show that both trade and capital flows are important determinants of pairwise connectedness across countries. The capital flows became increasingly important after 2013, while the effect of trade flows decreased during the crisis and did not recover afterwards.

An Investigation of Credit Card Default Prediction in the Imbalanced Datasets

Abstract: Financial threats are displaying a trend about the credit risk of commercial banks as the incredible improvement in the financial industry has arisen. In this way, one of the biggest threats faces by commercial banks is the risk prediction of credit clients. Recent studies mostly focus on enhancing the classifier performance for credit card default prediction rather than an interpretable model. In classification problems, an imbalanced dataset is also crucial to improve the performance of the model because most of the cases lied in one class, and only a few examples are in other categories. Traditional statistical approaches are not suitable to deal with imbalanced data. In this study, a model is developed for credit default prediction by employing various credit-related datasets. There is often a significant difference between the minimum and maximum values in different features, so Min-Max normalization is used to scale the features within one range. Data level resampling techniques are employed to overcome the problem of the data imbalance. Various undersampling and oversampling methods are used to resolve the issue of class imbalance. Different machine learning models are also employed to obtain efficient results. We developed the hypothesis of whether developed models using different machine learning techniques are significantly the same or different and whether resampling techniques significantly improves the performance of the proposed models. One-way Analysis of Variance is a hypothesis-testing technique, used to test the significance of the results. The split method is utilized to validate the results in which data has split into training and test sets. The results on imbalanced datasets show the accuracy of 66.9% on Taiwan clients credit dataset, 70.7% on South German clients credit dataset, and 65% on Belgium clients credit dataset. Conversely, the results using our proposed methods significantly improve the accuracy of 89% on Taiwan clients credit dataset, 84.6% on South German clients credit dataset, and 87.1% on Belgium clients credit dataset. The results show that the performance of classifiers is better on the balanced dataset as compared to the imbalanced dataset. It is also observed that the performance of data oversampling techniques are better than undersampling techniques. Overall, the Gradient Boosted Decision Tree method performs better than other traditional machine learning classifiers. The Gradient Boosted Decision Tree method gives the best results while utilizing the K-means SMOTE oversampling method. Using one-way ANOVA, the null hypothesis was rejected by a p-value <0.001, hence confirming that the proposed model improved performance is statistical significance. The interpretable model is also deployed on the web to ease the different stakeholders. This model will help commercial banks, financial organizations, loan institutes, and other decision-makers to predict the loan defaulter earlier.

Three-stage reject inference learning framework for credit scoring using unsupervised transfer learning and three-way decision theory

Abstract: There has been significant research into reject inference, with several statistical methods and machine learning techniques having been employed to infer the possible repayment behavior of rejected credit applicants. This study proposes a novel three-stage reject inference learning framework using unsupervised transfer learning and three-way decision theory that integrates: (1) the rejected credit sample selection using three-way decision theory, (2) higher-level representations to transfer learning from both accepted and selected rejected credit samples; and (3) credit scoring using the reconstructed accepted credit samples. This method was found to both perform well for reject inference and handle negative transfer learning problems. The numerical results were validated on Chinese credit data, the results from which demonstrated the superiority of the proposed reject inference method for credit risk management applications.

Real time monitoring of asset markets: Bubbles and crises

Abstract: While each financial crisis has its own characteristics there is now widespread recognition that crises arising from sources such as financial speculation and excessive credit creation do inflict harm on the real economy. Detecting speculative market conditions and ballooning credit risk in real time is therefore of prime importance in the complex exercises of market surveillance, risk management, and policy action. This chapter provides an R implementation of the popular real-time monitoring strategy proposed by Phillips et al., 2015a , Phillips et al., 2015b , along with a new bootstrap procedure designed to mitigate the potential impact of heteroskedasticity and to effect family-wise size control in recursive testing algorithms. This methodology has been shown effective for bubble and crisis detection ( Phillips and Shi, 2017 ; Phillips et al., 2015a , Phillips et al., 2015b ) and is now widely used by academic researchers, central bank economists, and fiscal regulators. We illustrate the effectiveness of this procedure with applications to the S&P financial market and the European sovereign debt sector. These applications are implemented using the psymonitor R package ( Phillips et al., 2018 ) developed in conjunction with this chapter.

Does Austerity Pay Off

Abstract: Austerity measures are frequently enacted when the sustainability of public finances is in doubt. Such doubts are reflected in high sovereign yield spreads and put further strain on government finances. Is austerity successful in restoring market confidence, bringing about a reduction in yield spreads? We employ a new panel data set which contains sovereign yield spreads for 26 emerging and advanced economies and estimate the eects of cuts of government consumption on yield spreads and economic activity. The conditions under which austerity takes place are crucial. During times of fiscal stress, spreads rise in response to the spending cuts, at least in the short-run. In contrast, austerity pays o, if conditions are more benign.

Machine learning techniques for credit risk evaluation: a systematic literature review

Abstract: Credit risk is the risk of financial loss when a borrower fails to meet the financial commitment. While there are many factors that constitute credit risk, due diligence while giving loan (credit scoring), continuous monitoring of customer payments and other behaviour patterns could reduce the probability of accumulating non-performing assets (NPA) and frauds. In the past few years, the quantum of NPAs and frauds have gone up significantly, and therefore it has become imperative that banks and financial institutions use robust mechanisms to predict the performance of loans. The past two decades has seen an immense growth in the area of artificial intelligence, most notably machine learning (ML) with improved access to internet, data, and compute. Whilst there are credit rating agencies and credit scoring companies that provide their analysis of a customer to banks on a fee, the researchers continue to explore various ML techniques to improve the accuracy level of credit risk evaluation. In this survey paper, we performed a systematic literature review on existing research methods and ML techniques for credit risk evaluation. We reviewed a total of 136 papers on credit risk evaluation published between 1993 and March 2019. We studied the implications of hyper parameters on ML techniques being used to evaluate credit risk and, analyzed the limitations of the current studies and research trends. We observed that Ensemble and Hybrid models with neural networks and SVM are being more adopted for credit scoring, NPA prediction and fraud detection. We also realized that lack of comprehensive public datasets continue to be an area of concern for researchers.

Network based credit risk models

Abstract: Peer-to-Peer lending platforms may lead to cost reduction, and to an improved user experience. These improvements may come at the price of inaccurate credit risk measurements, which can hamper lend...

In Sickness and in Debt: The COVID-19 Impact on Sovereign Credit Risk

Abstract: The COVID-19 pandemic provides a unique setting in which to evaluate the importance of a country's fiscal capacity in explaining the relation between economic growth shocks and sovereign default risk For a sample of 30 developed countries, we find a positive and significant sensitivity of sovereign default risk to the intensity of the virus' spread for fiscally constrained governments Supporting the fiscal channel, we confirm the results for Eurozone countries and US states, for which monetary policy can be held constant Our analysis suggests that financial markets penalize sovereigns with low fiscal space, thereby impairing their resilience to external shocks

Who Supplies PPP Loans (and Does it Matter)? Banks, Relationships and the Covid Crisis

Abstract: We analyze bank supply of credit under the Paycheck Protection Program (PPP). The literature emphasizes relationships as a means to improve lender information, which helps banks manage credit risk. Despite imposing no risk, however, PPP supply reflects traditional measures of relationship lending: decreasing in bank size; increasing in prior experience, in commitment lending, and in core deposits. Our results suggest a new benefit of bank relationships, as they help firms access government-subsidized lending. Consistent with this benefit, we show that bank PPP supply, based on the structure of the local banking sector, alleviates increases in unemployment.

Economic consequences of high public debt: evidence from three large scale DSGE models

Abstract: The paper reviews the economic risks associated with regimes of high public debt through DSGE model simulations. The large public debt build-up following the 2009 global financial and economic crisis acted as a shock absorber for output, while in the recent and more severe COVID19-crisis, an increase in public debt is even more justified given the nature of the crisis. Yet, once the crisis is over and the recovery firmly sets in, keeping debt at high levels over the medium term is a source of vulnerability in itself. Moreover, in the euro area, where monetary policy focuses on the area-wide aggregate, countries with high levels of indebtedness are poorly equipped to withstand future asymmetric shocks. Using three large scale DSGE models, the simulation results suggest that high-debt economies (1) can lose more output in a crisis, (2) may spend more time at the zero-lower bound, (3) are more heavily affected by spillover effects, (4) face a crowding out of private debt in the short and long run, (5) have less scope for counter-cyclical fiscal policy and (6) are adversely affected in terms of potential (long-term) output, with a significant impairment in case of large sovereign risk premia reaction and use of most distortionary type of taxation to finance the additional debt burden in the future. Going forward, reforms at national level, together with currently planned reforms at the EU level, need to be timely implemented to ensure both risk reduction and risk sharing and to enable high debt economies address their vulnerabilities. JEL Classification: E62, H63, O40, E43

Bond risk premia and the exchange rate

Abstract: In emerging market economies, currency appreciation goes hand in hand with compressed sovereign bond spreads, even for local currency sovereign bonds. This yield compression comes from a reduction in the credit risk premium. Crucially, the relevant exchange rate involved in yield compression is the bilateral U.S. dollar exchange rate, not the trade‐weighted exchange rate. Our findings highlight endogenous co‐movement of bond risk premia and exchange rates through the portfolio choice of global investors who evaluate returns in dollar terms.

Design of comprehensive evaluation index system for P2P credit risk of “three rural” borrowers

Abstract: In the emerging peer-to-peer (P2P) lending industry, risks such as credit risk and default risk will bring huge losses to online lending platforms and investors. Therefore, it is necessary to design a reasonable evaluation index system of credit risk to scientifically evaluate the risk level of borrowers. This paper studies the design of comprehensive evaluation index system for P2P credit risk of “three rural” (i.e., agriculture, rural areas and farmers) borrowers. Concretely, we construct the feature set for P2P credit risk of “three rural” borrowers. Based on the traditional index system, we add the static indexes specific to the agriculture-related borrowers and the dynamic indexes reflect the Internet as the preliminary indexes of the feature set and select the borrowers data of the “Pterosaur loan” platform as the research sample. Then, 35 borrower credit features are extracted as a feature set of credit risk. Then, we present a two-stage feature selection method based on filter and wrapper to select the main features from 35 initial borrower credit features. In the stage of filter, three filter methods are used to calculate the importance of the unbalanced features. In the stage of wrapper, a Lasso-logistic method is proposed to filter the feature subset through heuristic search algorithm. In the end, 21 main independent features are selected according to the classification accuracy, which constitute the evaluation index system of credit risk of “three rural” borrowers.

Services trade and credit frictions: Evidence with matched bank–firm data

Abstract: The effects of credit supply shocks on the exports of services are not clear a priori. On the one hand, services need lower initial investment in physical capital than manufacturing. On the other hand, competitiveness for exporting services requires investments in intangible capital and in product customisation that may be subject to credit frictions. Using Italian matched bank–firm data and focusing on the sovereign debt crisis, we find an elasticity of services exports to credit supply, between 0.3 and 0.4. The effects of credit shocks are especially relevant for firms exporting complex services to countries with weaker institutions and for services that are not the main product of the firms. Overall, our results suggest that credit supply plays a relevant role for exporting services during crises.

Big data analytics on enterprise credit risk evaluation of e-Business platform

Abstract: In recent years, the research on supply chain finance has been mature, in the supply chain financial risk research, the research on credit risk is mostly. However, there is little research on online supply chain finance, especially on credit risk. Therefore, this article has carried on the detailed research to the commercial bank online supply chain financial credit risk assessment. Firstly, the article applies the literature induction method to review the supply chain financial credit risk indicators, add the “online” specific indicators to supplement, combine the indicators selection principle to determine the final indicators, and construct the commercial bank online supply chain financial credit risk assessment index system, select online The supply chain financial business carried out the concentrated SMEs in the automobile manufacturing industry as the research object, using the nonlinear LS-SVM model for empirical analysis, and compared with the logistic regression model results. Secondly, the designed index system can effectively evaluate credit risk. The classification accuracy of LS-SVM evaluation model is higher than that of Logistic regression model and it has strong generalization ability. It can comprehensively identify the credit risk of small and medium-sized financing enterprises, and provide a reasonable and scientific analysis and support tool for assessing SME credit risk. Finally, combined with the fierce competition background of supply chain finance, it is proposed that commercial banks should actively carry out online supply chain finance, comprehensive risk management and deepen cooperation with e-Business platforms and logistics platforms.

Mining Semantic Soft Factors for Credit Risk Evaluation in Peer-to-Peer Lending

Abstract: While Peer-to-Peer (P2P) lending is rapidly growing, it is also accompanied by high credit risk due to information asymmetry. Besides conventional hard information, soft information also enters int...