Likelihood Of Default Research Articles

Government should be merciful or strict: Penalizing defaulting suppliers in emergency supply chains

The potential for profit-seeking suppliers in emergency supply chains (ESCs) to default and how to penalize defaulting suppliers has not been adequately discussed. In this paper, we construct an ESC consisting of a supplier and a government, in which the supplier pre-stocks supplies for the government for a pre-disaster contract period, and the government orders supplies from the supplier after the disaster based on actual demand. Our research question is how to choose an appropriate penalty measure (PM) in the face of default by suppliers who stock different types of supplies. The results show that the higher storage cost for supplies not be ordered after the contract period can reduce suppliers’ incentives to pre-stock supplies and even lead to supplier default, and that a reduction in the quantity ordered by the government from suppliers can reduce the likelihood of supplier default. The government should take merciful PMs to penalize the defaulting supplier who pre-stocks supplies with high marketability or high market price, and strict PMs to penalize the defaulting supplier who pre-stocks supplies with low marketability or low market price. In addition, although it is difficult to accurately measure the losses incurred by default, we can still penalize defaulting suppliers based on the default quantity. Finally, we also find that constructing compromise PMs allows the government to find a balance between strictness and mercy. By adjusting the degree of compromise, the government can choose the penalty strength appropriate to the situation.

Addressing Legal Loopholes in Consumer Credit Markets

The global financial landscape has undergone significant transformations over the past decade, particularly in the consumer credit market. However, despite regulatory advancements, legal loopholes persist that jeopardize consumer protection and risk exacerbating the problem of over-indebtedness. This letter seeks to address these concerns by highlighting existing gaps in legislation and proposing strategic reforms to strengthen consumer rights and prevent irresponsible lending practices. To address these challenges, I propose several key reforms: Revision of the Consumer Credit Directive: Enhance the directive to include stricter guidelines on affordability assessments, mandating that lenders conduct thorough background checks that consider a consumer’s long-term financial stability. Standardization of Risk Assessment Procedures: Develop standardized procedures for assessing credit risks that include behavioral and socioeconomic factors to reduce the likelihood of default and over-indebtedness. Enhanced Oversight of Credit Bureaus: Implement stricter regulatory oversight of credit bureaus to ensure that credit scoring systems are transparent and equitable. Cap on Interest Rates and Fees: Introduce caps on interest rates and fees to protect consumers from predatory lending practices and prevent systemic usury. Consumer Education Programs: Increase investment in consumer education programs to ensure that borrowers are fully aware of the terms of credit agreements and the implications of debt. These recommendations aim to fortify the legal framework surrounding consumer credit, ensuring that it not only supports the financial system but also safeguards consumer interests, particularly those of the most vulnerable. By closing these legal loopholes, we can foster a more equitable and responsible credit market.

Applying Machine Learning Techniques to Evaluate Climate-Related Risks in Real Estate Mortgage Valuations

Facing the escalating effects of climate change, the real estate industry faces risks from physical perils and shifting towards a low-carbon economic model. These risks have substantial consequences for the assessment and effectiveness of real estate mortgage portfolios. Conventional approaches to evaluating mortgage risk frequently fail to capture the intricate, non-linear connections between climate variables and loan results. In this paper, we present a new machine-learning framework that aims to quantify climate-related risks in real estate finance. We utilize neural networks and gradient-boosting algorithms to forecast the likelihood of mortgage defaults and the potential loss resulting from defaults in different climate stress scenarios. A robust and forwardlooking risk assessment is developed by integrating property-level exposure data, loan characteristics, and macroeconomic indicators. The empirical findings prove that our models perform superior to conventional econometric methods regarding predictive precision and computational effectiveness. The framework offers a robust instrument for investors, lenders, and regulators who aim to effectively address climate risks and enhance their ability to withstand and adapt to an unpredictable future.

Assessing the Scholarly Landscape: A Bibliometric Journey through Credit Rating Agency Research

Credit Rating Agencies play a crucial role in the financial markets by providing independent assessments of borrowers' creditworthiness. Rating agencies give useful information about performance and creditworthiness of companies, which aids in reducing information asymmetry and it serve as a signal for the likelihood of default which allows investors and market participants to make informed decisions . It is considered as powerful institutions capable of influencing bond and stock prices. The credibility of rating agencies has been question due to their role in the 2008 financial crisis. Their credibility may be impacted by a number of reasons. The study reviewed literature added in credit-rating agency domain from January 2004 to October 2023. Bibliometric analysis is used to comprehend the existing literature. The review recouped 237 research articles on Credit Rating Agency from the Scopus database and envisioned the data using VOS viewer software and Biblioshiny from R studio. We found that most of the studies emerged as after-effects of financial crisis reported in 2008. We have provided a feasible research agenda to further explore credit-rating agency domain. The study not only enhanced the understanding of the scholarly landscape within the scope of the study but also provided a comprehensive assessment of the literature.

Determinants of Credit Default in Banking in Nigeria

Purpose: The aim of the study was to examine the determinants of credit default in banking in Nigeria.
 Methodology: The study adopted a desktop methodology. Desk research refers to secondary data or that which can be collected without fieldwork. Desk research is basically involved in collecting data from existing resources hence it is often considered a low cost technique as compared to field research, as the main cost is involved in executive’s time, telephone charges and directories. Thus, the study relied on already published studies, reports and statistics. This secondary data was easily accessed through the online journals and library
 Findings: The determinants of credit default in Nigerian banking encompass a range of factors, including economic stability, regulatory oversight, risk management practices, loan portfolio quality, and macroeconomic conditions. Addressing these factors is crucial for banks to effectively manage credit risk and reduce the likelihood of credit defaults.
 Unique Contribution to Theory, Practice and Policy: Agency Theory, Pecking Order Theory and Information Asymmetry Theory may be used to anchor future studies on the examining determinants of credit default in banking in Nigeria. banks should initiate financial literacy programs for borrowers to improve their understanding of financial products and responsibilities. Regulators should encourage the adoption of advanced credit risk assessment models and provide guidelines on best practices in risk management.

Tax planning and financial default: role of corporate life cycle

PurposeDrawing on the resource-based view (RBV), this study investigates how tax planning affects the likelihood of financial default in different stages of the corporate life cycle.Design/methodology/approachCollecting a large sample of US firms between 1989 and 2016, hypotheses are tested using a hazard model. Several robustness and endogeneity checks corroborate the main findings.FindingsThe results show that tax-planning firms are less likely to default in the introduction and decline stages, while they are more likely to default in the growth and maturity stages. The findings suggest that introductory and declining firms use cash resources obtained from tax planning efficiently to meet their needs and acquire other useful resources. In growing and mature firms, tax aggressiveness generates unnecessary slack resources, weakens managerial discipline and increases reputational risks.Practical implicationsThe results shed light on the benefits and costs associated with tax planning throughout firms' life cycle, holding great significance for managers, investors, lenders and other stakeholders.Originality/valueThis study contributes to the literature that examines resource management at different life cycle stages by showing that cash resources from tax planning are managed in distinctive ways in each life cycle stage, having a varied impact on the likelihood of default. The authors shed light on underexplored cash resources. Furthermore, this study shows the potential linkages between the agency theory and RBV.

Risk Management, Expectations and Global Finance

Abstract What impact do past experiences have on the expectation formation of banks? This article analyses the risk management of Germany’s largest bank during the 1970 and 1980s. In this period, financial deregulation and globalization increased the likelihood of credit defaults and forced banks to implement new strategies of risk assessment. The Herstatt failure of 1974 triggered a series of new regulations, partly based on initiatives of the banks themselves. After the sovereign debt crisis of the 1980s, banks introduced a comprehensive strategy of country-risk assessment. They systematically professionalized their information resources and integrated risk and liability management. Economic forecasting was often based on historical data used for the classification and diversification of risks. However, learning from past experiences had limitations, as recent events were often overrated. This had the effect that the banks’ country risk assessment focused mainly on developing countries while the industrial world was not included in the schemes. This might explain why many banks have continually underestimated the financial risks present in developed countries since the 1990s.

Loan survival: Are Black farmers more likely to default?

AbstractThis paper discusses differences in the likelihood of loan default between Black and other farmers who took out USDA direct operating loans from 2011 to 2020. By controlling for financial, demographic, and other factors using a Cox proportional hazards model, we found that Black farmers have a higher incidence of default than other farmers. We advanced the research on the relative loan performance of different racial/ethnic minority groups, revealing heterogeneity in the likelihood of default that indicates using a single grouping for all minorities obscures important differences. There could be multiple contributing factors to higher rates of default among Black borrowers that deserve future attention and study, though it is beyond the scope of this paper to identify a causal mechanism.

Economic Disruptions in Repayment of Peer Loans

Economic disruptions can alter the likelihood of defaults on peer-to-peer loans, causing those impacted to adjust. The option to declare economic hardship and temporarily reduce the payment burden can provide some relief. When this occurs, the borrower’s financial qualifications have changed. The qualities instrumental in successfully securing the original loan terms must be reanalyzed to manage risk. This is a critical point in the life of the loan because the declaration of financial hardship can signal that the borrower’s ability to repay has diminished. We present a novel default detection scheme for borrowers experiencing an economic disruption based on the Two-Class Support Vector Machine, a data classification algorithm for supervised learning problems. The method utilizes data from actual loan records (15,355 loans from 2016 through 2020), specifically from borrowers who declared economic hardship. We provide a detailed description of the default detection process and present results that show defaults among borrowers experiencing financial hardship can be predicted accurately.

Knowledge graph driven credit risk assessment for micro, small and medium-sized enterprises

Micro, Small, and Medium-sized Enterprises (MSMEs) are essential for the growth and development of the country's economy, as they create jobs, generate income, and foster production and innovation. In recent years, credit risk assessment (CRA) has been an essential process used by financial institutions to evaluate the creditworthiness of MSMEs and determine the likelihood of default. Traditionally, CRA has relied on credit scores and financial statements, but with the advent of machine learning (ML) algorithms, lenders have a new tool at their disposal. By and large, ML algorithms are designed to classify borrowers based on their credit history and transactional data while leveraging the entity relationship involved in credit transactions. This study introduces an innovative knowledge graph-driven credit risk assessment model (RGCN-RF) based on the Relational Graph Convolutional Network (RGCN) and Random Forest (RF) algorithm. RGCN is employed to identify topological structures and relationships, which is currently nascent in traditional credit risk assessment methods. RF categorises MSMEs based on the enterprise embedding vector generated from RGCN. Extensive experimentation is conducted to assess model performance utilising the Indian MSMEs database. The balanced accuracy of 92% obtained using the RGCN-RF model demonstrates a considerable advancement over prior techniques in identifying risk-free enterprises.

RTS,S/AS01E vaccine defaults in Ghana: a qualitative exploration of the perspectives of defaulters and frontline health service providers

BackgroundWhile Ghana has a good track record in the Expanded Programme on Immunization, there are substantial challenges with regards to subsequent vaccinations, particularly after the first year of life of the child. Given that the last dose of the RTS, S/AS01E vaccine against malaria is administered at 24 months, there is a high likelihood of default. Hence, it is imperative to understand the dynamics and reasons for the defaults to enable the development of effective implementation strategies. This study explored why caregivers default on the RTS, S/AS01E vaccine from the perspective of health service providers and caregivers.MethodsThis study employed an exploratory, descriptive approach. Using a purposive sampling technique, caregivers who defaulted and health service providers directly involved in the planning and delivery of the RTS, S/AS01E vaccine at the district level were recruited. A total of five health service providers and 30 mothers (six per FGD) participated in this study. Data analysis was done using NVivo-12 following Collaizi’s thematic framework for qualitative analysis. The study relies on the Standards for Reporting Qualitative Research.ResultsReasons for defaulting included the overlap of timing of the last dose and the child starting school, disrespectful attitudes of some health service providers, concerns about adverse side effects and discomforts, travel out of the implementing district, the perception that the vaccines are too many, and lack of support from partners.ConclusionTo reduce the occurrence of defaulting on the RTS, S/AS01E vaccine programme, stakeholders must reconsider the timing of the last dose of the vaccine. The schedule of the RTS, S/AS01E vaccine should be aligned with the established EPI schedule of Ghana. This will significantly limit the potential of defaults, particularly for the last dose. Also, the findings from this study underscore a need to encourage male partner involvement in the RTS, S/AS01E vaccine programme. Health promotion programmes could be implemented to raise caregivers’ awareness of potential adverse reactions and discomforts—this is necessary to prepare the caregiver for the vaccine process psychologically.

Factors determining default in P2P lending

PurposeThe research documented in this paper aims to examine multiple factors related to borrowers' default in peer-to-peer (P2P) lending in the USA. This study is motivated by the hypothesis that both P2P loan characteristics and macroeconomic variables have influence on loan performance. The authors define a set of loan characteristics, borrower characteristics and macroeconomic variables that are significant in determining the probability of default and should be taken into consideration when assessing credit risk.Design/methodology/approachThe research question in this study is to find the significant explanatory variables that are essential in determining the probability of default for LendingClub loans. The empirical study is based on a total number of 1,863,491 loan records issued through LendingClub from 2007 to 2020Q3 and a logistic regression model is developed to predict loan defaults.FindingsThe results, in line with prior research, show that a number of borrower and contractual loan characteristics predict loan defaults. The innovation of this study is the introduction of specific macroeconomic indicators. The study indicates that macroeconomic variables assessed alongside loan data can significantly improve the forecasting performance of default model. The general finding demonstrates that higher percentage change in House Price Index, Consumer Sentiment Index and S&P500 Index is associated with a lower probability of delinquency. The empirical results also exhibit significant positive effect of unemployment rate and GDP growth rate on P2P loan default rates.Practical implicationsThe results have important implications for investors for whom it is of great importance to know the determinants of borrowers' creditworthiness and loan performance when estimating the investment in a certain P2P loan. In addition, the forecasting performance of the model could be applied by authorities in order to deal with the credit risk in P2P lending and to prevent the effects of increasing defaults on the economy.Originality/valueThis paper fulfills an identified need to shed light on the association between specific macroeconomic indicators and the default risk from P2P lending within an economy, while the majority of the existing literature investigate loan and borrower information to evaluate credit risk of P2P loans and predict the likelihood of default.

Lost in a black‐box? Interpretable machine learning for assessing Italian SMEs default

AbstractAcademic research and the financial industry have recently shown great interest in Machine Learning algorithms capable of solving complex learning tasks, although in the field of firms' default prediction the lack of interpretability has prevented an extensive adoption of the black‐box type of models. In order to overcome this drawback and maintain the high performances of black‐boxes, this paper has chosen a model‐agnostic approach. Accumulated Local Effects and Shapley values are used to shape the predictors' impact on the likelihood of default and rank them according to their contribution to the model outcome. Prediction is achieved by two Machine Learning algorithms (eXtreme Gradient Boosting and FeedForward Neural Networks) compared with three standard discriminant models. Results show that our analysis of the Italian Small and Medium Enterprises manufacturing industry benefits from the overall highest classification power by the eXtreme Gradient Boosting algorithm still maintaining a rich interpretation framework to support decisions.

Overview of an alternative trigger for DCL

In this research letter, we suggest a novel trigger for Dynamic Control of Leverage (DCL). These instruments are analogous to conventional Contingent Convertible (CoCo) bonds, employed to constrain a firm’s leverage within specified limits, thus minimizing the likelihood of default. Our proposed trigger enables continuous leverage monitoring, bringing in the desired flexibility allowing the conversion to be triggered ahead of the cash payment. This alternative design, building upon the DCL mechanism, has been shown to further reduce the probability of default while preserving the desirable mean-reverting behaviour of the leverage dynamic. We provide evidence of the model’s effectiveness and discuss the implications of its implementation.

Downside variance premium, firm fundamentals, and expected corporate bond returns

We find a strong and robust positive relationship between individual downside variance premia (DVP)–the difference between risk-neutral and physical expected downside variances–and future corporate bond returns. The spread portfolio that longs the high DVP bond portfolio and shorts the low DVP bond portfolio earns a statistically significant excess return of 0.37% (0.42%) per month in value- (equal-)weighted returns. The alpha estimates from various factor models remain statistically significant and economically substantial. The predictive power of the downside variance premium is stronger in noninvestment-grade (long-maturity) corporate bonds than in investment-grade (short-maturity) bonds. We show that the downside variance premium positively relates to the likelihood of future default and cash flow uncertainty and negatively relates to future cash flows.

Improving Credit Risk Assessment through Deep Learning-based Consumer Loan Default Prediction Model

This study aims to enhance credit risk identification, improve loan borrower review efficiency, and increase default prediction accuracy rate using data mining and machine learning techniques. The study also employs deep learning to develop a consumer loan default prediction model that minimizes credit risks and ensures consistent development. The researchers collected data from a survey of 1000 participants, stratified into local and foreign banks, and selected the top 11 banks based on turnover and customer volume. To construct the machine learning model, Keras, a neural network library that runs on TensorFlow, was utilized. The model predicts loan applicant default likelihood. The study's practical implications demonstrate a noteworthy success rate of customer default prediction, which can significantly benefit banks. The model was evaluated on a test set of 250 records and achieved a test set accuracy of 95.2%, correctly predicting the default state of 238 out of 250 respondents.

Credit Risk Analysis Using Naive Bayes in Machine Learning

Abstract: A method of data analysis called machine learning automates the creation of analytical models. It is an area of artificial intelligence based on the idea that robots can learn from data, recognise patterns, and form opinions with little help from people. One of the most important and difficult tasks facing banks is the evaluation of credit risk. To prevent financial loss, accuracy is crucial in the classification of credit data. Lending money to people who need it is a major operation in the banking sector. The depositor bank receives the interest earned by the main borrowers in order to repay the principal borrowed from them. Financial risk management is increasingly focusing on credit risk analysis. The ability to estimate credit risk, monitor it, trust the model, and process loans well are essential for decision-making and transparency. In this study, we develop binary classifiers based on machine learning and deep learning models on actual data to forecast the likelihood of loan default. In the aforementioned research, we examine various methods for credit risk analysis that are used to the assessment of credit risk datasets.

Unleashing the Power of Machine Learning: A Comparative Study of Classification Algorithms for Credit Risk Assessment

Credit risk assessment is a critical task in the financial industry, enabling lenders to evaluate the likelihood of default and make informed lending decisions. This paper presents a comprehensive comparative study of classification algorithms for credit risk assessment using machine learning techniques. The paper commences by providing an overview of the importance of credit risk assessment and the challenges faced by traditional methods. It then delves into the exploration of various machine learning algorithms, including logistic regression, decision trees, random forests, support vector machines, and neural networks, highlighting their potential in credit risk assessment. The objective of this study is to compare the performance of different classification algorithms in credit risk assessment. To achieve this, a dataset comprising historical credit data, including borrower information, financial indicators, and repayment history, is collected. The dataset is preprocessed to handle missing values, outliers, and feature engineering is applied to extract relevant predictors. A comprehensive evaluation is conducted, considering performance metrics such as accuracy, precision, recall, and area under the receiver operating characteristic curve (AUC-ROC). The comparative study provides insights into the strengths and weaknesses of each algorithm and their suitability for credit risk assessment in different scenarios. The results of this study contribute to the existing literature on credit risk assessment and offer practical guidance for financial institutions in selecting appropriate machine learning algorithms. Furthermore, the paper discusses potential challenges and limitations associated with the application of machine learning in credit risk assessment and proposes future research directions.

Banking on alternative credit scores: Auditing the calculative infrastructure of U.S. consumer lending

Alternative credit scores have become an increasingly important tool for lenders to assess risk and authorize investment in consumer debt. Using alternative data and processing techniques that leverage machine learning (ML) and Artificial Intelligence (AI), these models are designed to bypass existing barriers to risk-based pricing, which is the idea that financial institutions offer different interest rates to consumers based on their likelihood of default. Through an algorithmic audit of one lender's (Upstart) credit scoring model, I find that alternative data, particularly whether an applicant has a bachelor's degree, strongly impacted loan outcomes. This raises important equity concerns about overhauling lending criteria via opaque models that restructure the logic of risk assessment. In following the logic of risk assessment generated by Upstart's model, I also audit three fintech-bank partnerships and examine the balance sheets of banks providing capital via Upstart's platform. This is done to demonstrate rising capital allocation to these types of loans at banks engaged in fintech-bank partnerships, in one case rising from 0.14% to 15.6% of the banks’ balance sheet over three years. My analysis shows that alternative credit scoring systems function as a key piece of calculative infrastructure, which allows some institutions to bypass barriers to risk-based pricing, and becomes an infrastructural site for tech startups to partner with financial institutions seeking out new sources of revenue.

EXPRESS: Revealing and Mitigating Racial Bias and Discrimination in Financial Services

Three field studies and a laboratory experiment reveal racial discrimination in financial loan services. The results show that (a) service employees provide Black (vs. White) customers with inferior service outcomes (i.e., products offered), (b) Black (vs. White) customers experience inferior service processes (employees’ warmth/competence), and (c) Black (vs. White) customers report lower loyalty intentions toward the firm. Such discrimination is not only morally wrong and illegal, but it is also bad for business. Therefore, the authors also show when and why racial discrimination is mitigated: namely, when Black customers signal higher socioeconomic status, or a Black customer’s company (for which they seek the loan) has a more complex and sophisticated legal structure (corporation vs. sole proprietorship). Exploring this mitigation effect further, the results show that a more sophisticated business structure increases the employee’s trust toward Black customers, which reduces the perceived default likelihood and increases the likelihood to offer a loan; yet, this process does not emerge for White applicants. The findings point to managerial and policy implications to mitigate racial discrimination.