Loan Default Research Articles

A Benchmark for Collateralized Loan Obligations

We build a benchmark for AAA-rated tranches of collateralized loan obligations (CLOs) using business development companies (BDCs), which hold a diversified portfolio of loans as CLOs do. BDCs are publicly listed, and their share price, equity volatility, and borrowing cost can be easily obtained. Applying a structural model to BDCs, we extract market-implied correlation in their loan portfolio, compare spreads on CLO tranches and BDC-implied benchmark, and find that observed large credit spreads on CLO senior tranches after the financial crisis are a fair reflection of the systematic risk of correlated loan defaults. This paper was accepted by Lukas Schmid, finance. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.00097 .

Bank failures, capital buffers, and exposure to the housing market bubble

AbstractWe develop housing overvaluation measures that are separate from local economic conditions and show that banks with greater exposure to such overvalued markets have higher mortgage delinquency and charge‐off rates and significantly higher probabilities of failure during the 2007–2009 financial crisis even after controlling for bank characteristics. While high house prices relative to fundamentals present a greater likelihood of house price correction, we find no evidence that banks managed this risk by building capital. We also show that our overvaluation measures are important in explaining individual mortgage loan defaults and could be used to improve bank risk management.

Economic outcomes among microfinance group members receiving community-based chronic disease care: Cluster randomized trial evidence from Kenya

BackgroundPoverty can be a robust barrier to HIV care engagement. We assessed the extent to which delivering care for HIV, diabetes and hypertension within community-based microfinance groups increased savings and reduced loan defaults among microfinance members living with HIV. MethodsWe analyzed cluster randomized trial data ascertained during November 2020–May 2023 from 57 self-formed microfinance groups in western Kenya. Groups were randomized 1:1 to receive care for HIV and non-communicable diseases in the community during regular microfinance meetings (intervention) or at a health facility during routine appointments (standard care). Community and facility care provided clinical evaluations, medications, and point-of-care testing. The trial enrolled 900 microfinance members, with data collected quarterly for 18-months. We used a two-part model to estimate intervention effects on microfinance shares purchased, and a negative binomial regression model to estimate differences in loan default rates between trial arms. We estimated effects overall and by participant characteristics. ResultsParticipants’ median age and distance from a health facility was 52 years and 5.6 km, respectively, and 50% reported earning less than $50 per month. The probability of saving any amount (>$0) through purchasing microfinance shares was 2.7 percentage points higher among microfinance group members receiving community vs. facility care. Community care recipients and facility care patients saved $44.90 and $25.24 over 18-months, respectively, and the additional amount saved by community care recipients was statistically significant (p = 0.036). Overall and in stratified analyses, loan defaults rates were not statistically significantly different between community and facility care patients. ConclusionsReceiving integrated care in the community was significantly associated with modest increases in savings. We did not find any significant association between community-delivered care and reductions in loan defaults among HIV-positive microfinance group members. Longer follow up examination and formal mediation analyses are warranted.

Analyzing Loan Default Trends and their Influence on Bank Profitability

Banks boost the e­conomy's growth. But, banks have major issues with overdue­, unpaid loans called Non-Performing Assets (NPAs). Many re­ports show NPAs are rising rapidly, showing the problem's se­riousness. Researche­rs study NPAs, looking at their status, causes, impacts, and effe­cts. On a large scale­, the rising bad debts hinder e­conomic growth and affect diverse pe­ople, businesses, and banks. This article­ gives a brief summary of banking, explains bad de­bts, and looks at possible reasons for their incre­ase. Our main goal is to clarify the major impacts of many bad debts on banks. We­ carefully study each potential e­ffect using existing rese­arch. Studies show NPAs hurt banks. Our re­search uses data already colle­cted to understand NPA problems in India. We­ carefully examined pape­rs and statistics. NPAs cause major issues for banks. Profits go down. Credit ratings worse­n. Banks cannot lend as much. Funding becomes more­ costly. We cite rese­arch to explain each effe­ct. This gives a full picture of how NPAs impact banks. To conclude, this pape­r combines the effe­cts of bad loans and suggests ways banks might take to fix this problem. It stre­sses how crucial immediate actions and smart plans are­ to get through this tough situation and protect the banking industry's stability and stre­ngth. KEY WORDS Banking sector, NPAs, economic growth, deterioration, financial stability, credit risk, crisis, research findings, bank profitability, credit rating.

Loan Default Prediction Using Machine Learning

By anticipating loan defaulters, the bank is able to reduce its non-performing assets. Three primary predictive analytics techniques—I Data Collection, II Data Cleaning, and III Performance Assessment—are used to research the prediction of loan defaulters. Experimental investigations reveal that when it comes to loan forecasting, the KNN model performs better than the Decision tree model. Key Words: Machine learning, Loan prediction, Banking, KNN.

Nexus between small and medium-sized enterprise budgeting skills and loan repayment in South Africa

This study’s purpose is to assess the influence of small and medium-sized enterprises’ (SMEs) budgeting skills on loan repayment in South Africa. The quantitative research approach was selected as the appropriate methodology for this study, while the purposive sampling approach was selected as the appropriate way to select participants for this study. The primary data for this study came from respondents who were business owners of SMEs in the retail, hardware, construction, and manufacturing industries. SPSS was used to analyze the acquired data. A total of 380 research questionnaires were distributed, and there were 375 that were returned for analysis (which gives a response rate of 99%). Both a regression analysis and a correlation analysis using Pearson’s method were carried out. Pearson’s correlation coefficient revealed a positive and significant relationship between SMEs’ budgeting skills and loan repayment at the level of r =.250, p < 0.0005. These results were supported by the finding that there is a positive and significant association between these two factors. According to the findings of the study, it is recommended that financial providers educate their SMEs on how to prepare various types of budgets, how to follow up and compare their financial objectives to their performance, and that financial institutions and government organizations should assist SMEs with budgeting skills to decrease SME loan defaults.

Inter-Sectoral Linkages in Nigeria: Evidence from Agriculture and Manufacturing Sectors

The main purpose of the research was to establish determinants of commercial bank growth. The specific objectives of the study was to; determine the effect of default rate on loans on growth of commercial banks, determine the effect of level of interest income on growth of commercial banks and to establish the effect of forex transaction volume on growth of commercial banks listed in Nairobi Securities Exchange. The study was guided by the interest rate theory, international fisher effect theory and time preference theory. Using multiple regression analysis, we found support for the proposition that loan default rate, interest rate and forex transaction had a significant effect on growth of commercial banks. Keywords: Growth of commercial bank, default rate on loans, interest income and forex transaction volume DOI : 10.7176/DCS/9-1-06

On the Determinants of Loan Default in the Saudi Banking System

The main purpose of this paper is to examine the key determinants influencing the non-performing loans (NPLs) in the Saudi banking system. To do so, we consider a set of macroeconomic, banking, and external factors over the period 2010Q1-2023Q3. The contribution of this work to the literature includes providing fresh evidence following the COVID-19 pandemic, utilizing quarterly observations unlike preceding literature, and adopting time series econometric techniques to identify key elements influencing NPLs. A vector error correction model (VECM) is estimated to capture NPL dynamics over both the long-run and short-run. The empirical evidence reveals that NPLs are determined by a combination of macro, banking, and external factors. Specifically, macroeconomic and external variables appear to have a significant impact on NPLs, and their effects are in parallel with theoretical expectations. Likewise, the impact of return on equity on NPLs is significant as expected by theory; however, the impact of other banking factors is against expectations.

Machine Learning-Based Loan Default Prediction in Peer-to-Peer Lending

The peer-to-peer (P2P) lending market has recently undergone significant growth, transforming traditional lending practices. However, this evolution brings with it unique challenges, particularly in managing credit risk and ensuring the reliability of loan approvals. Accurate prediction of loan defaults remains a pivotal aspect of risk management in this sector. This study introduces a comprehensive approach to improve bad loan prediction in peer-to-peer (P2P) lending, sourcing Lending Club data. In the face of challenges posed by imbalanced datasets and risk management in the loan industry, our methodology significantly enhances prediction accuracy, particularly in identifying bad loans. The study implements a comprehensive process that includes data cleaning, feature engineering, feature selection, balancing the dataset and machine learning models, achieving a noteworthy accuracy rate over 92% and recall rate above 87%. This research advances academic understanding of loan prediction and generates real-world impact. The accurate models identifying explanatory provide a valuable framework for improving decision-making and strategic planning in P2P lending platforms.

Effects of Internal Control Systems on Credibility of Financial Statements in SACCOS. A Case of Kyamuhunga People’s Co-Operative Savings and Credit Society Limited Bushenyi, Uganda

The SACCO is faced with difficulties, according to KYAPS's 2021 audit report, including incredible financial reports resulting from material misstatements, material uncertainty from board members and management, loan applicants forging documents, receipts for nonexistent assets and transactions, dishonest details provided by borrowers, and a higher loan default rate. The present study aimed at establishing the relationship between monitoring and evaluation and credibility of financial statements, risk assessment on the credibility of financial statements, the relationship between Internal Audit and credibility of financial statements, a case of Kyamuhunga Peoples’ Cooperative Savings and Credit Society. Correlational research designs were used in this study. Self-administered organized survey questions and interview guides were used. 63 respondents from the KYAPS SACCO participated in this study. SPSS- version 26.0 was used for analysis to obtain descriptive statistics. Pearson linear correlation coefficient and regression analysis was used for analysis and thus there is a significant and positive relationship between monitoring and evaluation and credibility of financial statements as shown by correlation coefficient of 0.740 and P value .000<0.05., risk assessment and credibility of financial statements with 0.733 and p value .000<0.05., and internal audit and credibility of financial statements with correlation coefficient of 0.788 and p value .000<0.05. The findings of the study indicate that there is a significant positive relationship between monitoring and evaluation and credibility of financial statements in KYAPS suggesting that an improvement in monitoring and evaluation leads to improved credibility of financial statements as indicated by the findings, effective implementation of risk assessment results into Credible Financial Statements and that an improvement in Internal audit leads to attainment of credible financial statements. SACCO managers should strengthen the monitoring and evaluation to ensure improved accountability and hence credible financial statements, Risk assessment is emphasized by management to carry out business in an orderly and efficient manner and management should always keep them informed of any new internal controls introduced so as to ensure their effective implementation since they are the very people to implement the policies. Keywords: Internal Control Systems, Credibility of Financial Statements, Monitoring and Evaluation, Risk Assessment, Internal Audit

Multi-view GCN for loan default risk prediction

As a significant application of machine learning in financial scenarios, loan default risk prediction aims to evaluate the client’s default probability. However, most existing deep learning solutions treat each application as an independent individual, neglecting the explicit connections among different application records. Besides, these attempts suffer from the problem of missing data and imbalanced distribution (i.e., the default records are small samples against all the applications). We believe similar records could provide some auxiliary signals, which are of critical importance to alleviate the data missing issue and facilitate data argumentation. To this end, we propose multi-view loan application graphs, dubbed MLAGs. By evaluating the similarity between the records, a loan application graph can be constructed. Furthermore, we arrange different similarity thresholds to organize various graph structures for multi-graph constructions; thus, a variety of representations can be generated via information propagation and aggregation for small sample argumentation. Consequently, the imbalanced data distribution and missing values issues can be alleviated effectively. We conduct experiments on three public datasets from real-world home credit and P2P lending platforms, which show that MGCN outperforms both conventional and deep learning models. Ablation studies also illustrated the validity of each module design.

Imbalanced credit risk prediction based on data fillers and modified balanced random forest improved by Bayesian optimization

Based on the distribution characteristics of financial big data, credit risk prediction models often face some problems, such as unbalanced data distribution and difficult data preprocessing process. High-precision models are often accompanied by low model efficiency. Therefore, this paper constructs a complete non-equilibrium credit risk prediction model, namely BO-PBRF, and improves the algorithm to deal with common problems in financial data. In the data preprocessing stage, two missing value fillers are generated according to the original data to facilitate the subsequent new data processing. In the modeling stage, we improve the balanced random forest algorithm, so that the model can not only deal with unbalanced data sets, but also suitable for the background of the explosive development of financial big data, and improve the operation speed of the model. In addition, in the process of establishing the model, we add the Bayesian optimization algorithm to further improve the accuracy of the model, especially in the prediction of default loans. In order to verify the effectiveness of the model proposed in this paper, in the empirical research, we select the credit data from the real world, and compare the model proposed in this paper with the previous models. The experimental results show that the proposed model has the best prediction performance for default data.

Extraneous Shocks Affecting Agribusiness Loans Default Rate in Agricultural Finance Corporation, Mount Kenya Region

Extraneous Shocks Affecting Agribusiness Loans Default Rate in Agricultural Finance Corporation, Mount Kenya Region

The dual nature of “peculiar problems” in microfinancing: perspectives on market efficiency and public policy nexus

PurposeThe microfinancing sector is infamous for being prone to high credit risks due to loan defaults by its poor borrowers. Conversely, the sector is also criticized for creating debt traps for the poor. The dual nature of these peculiar problems in microfinancing causes the market failure phenomenon. Therefore, the current study explores whether public policy intervention is required to address market failure.Design/methodology/approachThe study undertakes a critical review of existing literature, the news, the policy documents and other publicly available information to shape the viewpoints in this study. Constructive criticism is used to build arguments to arrive at a conceptual framework that depicts how public policy should interact with markets to address the peculiar problems of the microfinancing sector.FindingsThe findings indicate that market failure in microfinancing is real and pressing. Therefore, public policy is invited, though in its limited form. While the policy intervention may help the formal microfinancing arena by regulating the interest rates, the policy administration in the informal sector is likely to fail. Therefore, the policy should attempt to create an environment of inclusiveness. Policies that rely on coercion are not recommended. In the long run, subsidies via policy intervention are discouraged. Instead, the policy should motivate the microfinancing sector to become self-reliant.Originality/valueThe study is one of its kind to provide perspectives on specific market failures and policy interventions in microfinancing, particularly in economies where formal and informal sectors coexist and are equally crucial.

Empirical modeling of agricultural climate risk

Effective policies for adaptation to climate change require understanding how impacts are related to exposures and vulnerability, the dimensions of the climate system that will change most and where human impacts will be most draconian, and the institutions best suited to respond. Here, we propose a simple method for more credibly pairing empirical statistical damage estimates derived from recent weather and outcome observations with projected future climate changes and proposed responses. We first analyze agricultural production and loan repayment data from Brazil to understand vulnerability to historical variation in the more predictable components of temperature and rainfall (trend and seasonality) as well as to shocks (both local and over larger spatial scales). This decomposed weather variation over the past two decades explains over 50% of the yield variation in major Brazilian crops and, critically, can be constructed in the same way for future climate projections. Combining our estimates with bias-corrected downscaled climate simulations for Brazil, we find increased variation in yields and revenues (including more bad years and worse outcomes) and higher agricultural loan default at midcentury. Results in this context point to two particularly acute dimensions of vulnerability: Intensified seasonality and local idiosyncratic shocks both contribute to worsening outcomes, along with a reduced capacity for spatially correlated ("covariate") shocks to ameliorate these effects through prices. These findings suggest that resilience strategies should focus on institutions such as water storage, financial services, and reinsurance.

Improving the accuracy of credit scoring models using an innovative Bayesian informative prior specification method

A new Bayesian informative prior specification method (BAF method – Bayesian priors using ARIMA forecasts) is proposed to introduce additional information into credit risk modelling and improve model predictive performance. We use logistic regression to model the probability of default of mortgage loans comparing the Bayesian approach with various priors and the frequentist approach. But unlike previous literature, we treat coefficient estimates in the probability of default model as stochastic time series variables. We build ARIMA models to forecast the coefficient values in future time periods and use these ARIMA forecasts as Bayesian informative priors. We find that the Bayesian models using this prior specification method produce more accurate predictions for the probability of default as compared to frequentist models and Bayesian models with other priors.

Economic Sociology Review of Car Pawn Practices in Pinrang Regency

This thesis delves into the Economic Sociology Review of Car Pawn Practices in Pinrang Regency. The study aims to explore the practice of car pawning, factors influencing people's decision to pawn their cars, and the economic sociology perspective on car pawning. The research adopts a qualitative approach, specifically phenomenology. Data collection techniques include interviews, observations, and documentation, with data validity assessed through credibility, transferability, dependability, and confirmability. Key findings of the study include: 1) Car pawning practices are prevalent in Lanrisang and Siparappe neighborhoods in Pinrang Regency, with pawnshops operating without registration with the Financial Services Authority. The assessment of collateral is conducted by the pawnbroker, impacting the loan amount and monthly interest rates. Transactions are documented through receipt slips, and if the loan defaults, ownership of the collateral is transferred or sold by the pawnbroker. 2) People opt for car pawning due to its lenient requirements, non-restrictive operating hours, and minimal conditions for loan approval. 3) Economic actions in the context of economic sociology are characterized as irrational actions influenced by motives, interests, experiences, and expectations. These actions fall into the categories of affective and traditional actions. Keywords: Economic Sociology, Car Pawn

Unearthing Financial Wisdom Exploring the Factors Shaping Financial Literacy among Agribusiness Entrepreneurs in Zimbabwe

Unearthing Financial Wisdom Exploring the Factors Shaping Financial Literacy among Agribusiness Entrepreneurs in Zimbabwe

Network centrality and credit risk: A comprehensive analysis of peer-to-peer lending dynamics

This letter analyzes credit risk assessment in the Peer-to-Peer (P2P) lending domain by leveraging a comprehensive dataset from Bondora, a leading European P2P platform. Through combining traditional credit features with network topological features, namely the degree centrality, we showcase the crucial role of a borrower’s position and connectivity within the P2P network in determining loan default probabilities. Our findings are bolstered by robustness checks using shuffled centrality features, which further underscore the significance of integrating both financial and network attributes in credit risk evaluation. Our results shed new light on credit risk determinants in P2P lending and benefit investors in capturing inherent information from P2P loan networks.

Correction: Maximizing the lender’s profit: profit-oriented loan default prediction based on a weighting model

Correction: Maximizing the lender’s profit: profit-oriented loan default prediction based on a weighting model