Loan Performance Research Articles

Does social capital positively influence loan performance even during a crisis?

Theoretically, it is unclear whether group loans outperform individual loans in terms of delinquency, especially during a crisis. It is difficult to test the hypothesis due to differences in the types of borrowers of the group and individual loans and likely differences in their behavior between crises and normal times. We overcome the challenge by comparing simultaneous group and individual loans of the same individual before and during the Covid-19 crisis in India. We find that the delinquency rate of group loans is significantly lower. Further tests suggestively indicate that the outperformance is due to the “peer pressure” channel.

Fintech model performance analysis in credit loans: evidence from China city commercial banks

ABSTRACT The analysis of bank loan performance has consistently been a central issue in banking research. With the impact of the COVID-19 pandemic, we have witnessed a significant increase in online loans. Our study employs fintech models to develop a big data credit analysis system, evaluating model efficiency and the effect of ‘data organization’ on predictive performance for city commercial bank loans. Our results show that training data size, timeliness, and inter-bank ‘data sharing’ significantly affect model predictions. We also find that traditional econometric models (Logit and Probit) have the weakest predictive ability. However, ‘most advanced’ deep learning models perform worse than machine learning models with lower algorithmic complexity, such as Random Forest. Besides, ‘sharing training data’ generally increases model efficiency, but there are exceptions for larger city commercial banks. This paper provides ample empirical evidence for the application of the fintech model in bank loan credit. It highlights several characteristics of training data, such as size and timeliness, which greatly affect model efficiencies. We also provide policy recommendations for fintech transition and collaboration among municipal banks.

Digital transformation, information and lending distance -Evidence from Chinese bank branch data

This research aims to empirically investigate the relationship between bank digital transformation and lending distance. In traditional financial geography theory, banks have a natural geographical proximity preference in their credit decision-making, which might lead to suboptimal credit allocation. Can the rapid development of digitalization improve the situation that banks are only capable of undertaking ex ante due diligence and ex post monitoring of proximate borrowers, given that fintech has greatly improved the overall efficiency of the financial industry? Using bank loan data of listed enterprises in China from 2013 to 2021, this paper finds that the digital transformation of banks can significantly extend the lending distance between banks and enterprises. The moderating effect analysis suggests that distance extending effect of bank digitalization is more pronounced for firms with poor information quality and in competitive banking sector. Further, digital transformation extends the lending distance without increasing risk preferences, as evidenced by the empirical finding that the non-performing loan ratio remains unaffected by the increased distance. Also, geographical expansion in lending distance reduces loan concentration. The research in this paper supports the conclusion that banks' digital transformation positively impacts corporate credit allocation and is beneficial to achieving financial stability by improving loan performances.

Predicting borrower default risk using support vector machine AI models

Precise prediction on the likelihood of borrower default is pivotal for credit institution and decision makers to mitigate the loss of capital and rationalize decision process. This article reviewed the Effects of Support Vector Machine (SVM) models with radial basis function (RBF) kernel in predicting the mortality rate of borrowers. By integrating with a dataset of approximately 100,000 borrowers profile harvested through historical loan performance, we set up the SVM model, and employed a feature-distribution method utilizing grid search and cross-validation technique to fine-tune the predictive model of SVM. Results indicated that the model accomplished an excellent performance with accuracy of 92%, precision of 89%, the recall and F1-score of 85% and 87%, respectively, alongside an Area Under the Curve -Receiver Operating Characteristic (AUC-ROC value of 0.95). It was evinced that the model performed substantially better than traditional logistic regression and decision trees in discriminating defaulter from non-defaulter. The outcome informs that an in-depth process should be implemented on data preprocessing, featureselection, and parameter tuning to achieve a robust predictive model for credit risk assessment. The article concludes the potentials of AI based on the resort to artificial technology in revolutionising the risk assessment scheme within the financial industry.

An Empirical Study of the Impact of Non-performing Assets on Bank Shareholder Value and Investor Confidence

This empirical study investigates the impact of Non-Performing Assets (NPAs) on bank shareholder value and investor confidence using secondary data analysis. The research synthesizes insights from existing literature and employs a structured approach to analyze NPAs' effects across different types of banks. Drawing on studies that explore NPA management efficiencies, financial performance in cooperative banks, stock market returns mediated by loan performance, and macroeconomic influences on NPAs respectively, this study aims to provide a nuanced understanding of how NPAs influence shareholder value and investor confidence globally. The methodology involves comprehensive data collection from financial statements, stock market data, and regulatory filings. Analytical techniques include regression analysis, correlation studies, and event studies to quantify and interpret the impact of NPAs on stock prices and investor sentiment. The findings will contribute valuable insights into effective NPA management strategies for enhancing bank performance and maintaining investor trust in international financial markets.

Macroeconomic environment and the future performance of loans: Evidence from three peer-to-peer platforms

The literature on peer-to-peer loan market performance focuses predominantly on the microlevel variables connected to individual borrower or loan characteristics. We hypothesize that the economic environment, reflected by macroeconomic variables at the time of loan origination, should play a role in explaining loans’ future performance. Our dataset comprises two US-based platforms and one UK-based platform, which provides a rich field to verify our hypothesis with numerous loan-related variables. Specifically, we consider Lending Club with 1,169,976 individual loans and 128 variables, Prosper with 386,685 loans and 142 variables, and Zopa with 440,493 loans and 192 variables. Using linear and threshold regressions, we observe three main findings: (i) accounting for the macroeconomic environment systematically improves our understanding of the variation in the future performance of individual loans; (ii) demand-side variables, particularly the unemployment rate and industrial production, have stronger effects as supply-side and economic uncertainty variables; and (iii) the importance (effect size) of the macroeconomic environment is at least at the level of that of calendar and geographic variables but much smaller than the importance of loan or borrower characteristics. These results suggest that the economic environment might be useful in individual loan-level credit risk models.

The impact of fintech lending on credit access for U.S. small businesses

Small business lending (SBL) plays an important role in funding productive investment and fostering local economic growth. Recently, nonbank lenders have gained market share in the SBL market in the United States, especially relative to community banks. Among nonbanks, fintech lenders have become particularly active, leveraging alternative data and complex modeling for their own internal credit scoring. We use proprietary loan-level data from two fintech SBL platforms (Funding Circle and LendingClub) to explore the characteristics of loans originated pre-pandemic (20162019). Our results show that these fintech SBL platforms lent relatively more in zip codes with higher unemployment rates and higher business bankruptcy filings. Moreover, fintech platforms’ internal credit scores were able to predict future loan performance more accurately than traditional credit scores, particularly in areas with high unemployment. Using Y-14 M loan-level bank data, we compare fintech SBL with traditional bank business cards in terms of credit access and interest rates. Overall, while not all fintech firms follow the same approach, we find that fintech lenders could help close the credit gap, allowing small businesses that were less likely to receive credit through traditional lenders to access credit and potentially at lower cost.

The Dynamics of Loan Sales and Lender Incentives

Abstract How much of a loan should a lender retain, and how do loan sales affect loan performance? We address these questions in a model in which a lender originates loans that it can sell to investors. The lender reduces default risk through screening at origination and monitoring after origination, but is subject to moral hazard. The optimal lender-investor contract can be implemented by requiring the lender to initially retain a share of the loan that it gradually sells to investors, rationalizing loan sales after origination. The model generates novel predictions linking loan and lender characteristics to initial retention, sales dynamics, and loan performance.

Influence of Credit Risk Management Practices on Loan Performance: A Case of Selected Microfinance Institutions in Tanzania

This research investigates the influence of credit risk management practices on loan performance of microfinance institutions. The variables of interest in this study are credit appraisal, credit supervision, credit monitoring (as predictor variables) and loan performance (as dependent variable). However, the study includes average credit processing time as a control variable. The study focuses on five microfinance institutions operating in Tanzania. The research utilizes probability and non-probability sampling to select 140 respondents from the study population. The study collected both primary and secondary data. Data analysis was carried out by applying multiple regression analysis following the assumptions of ordinary least squares (OLS). The findings reveal that credit supervision, credit monitoring, and average credit process time are significant in influencing loan performance in microfinance institutions. Contrary, there is no evidence, whatsoever to suggest that credit supervision influences loan performance in microfinance institutions.

Rise of the Machines: The Impact of Automated Underwriting

Using a randomized experiment in auto lending, we find that algorithmic underwriting outperforms the human underwriting process, resulting in 10.2% higher loan profits and 6.8% lower default rates. The human and machine underwriters show similar performance for low-risk, less complex loans. However, the performance of human underwritten loans largely declines for riskier and more complex loans, whereas the machine performance stays relatively stable across various risk dimensions and loan characteristics. The performance difference is more pronounced at underwriting thresholds with a high potential for agency conflict. These results are consistent with algorithmic underwriting mitigating agency conflicts and humans’ limited capacity for analyzing complex problems. This paper was accepted by Will Cong, finance. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2024.4986 .

Beyond the Crisis: Tracking SME Non-Performing Loan in Indonesia Before and After the COVID-19 Stimulus

This study evaluates the impact of two Indonesian government economic stimulus packages on the performance of Non-Performing Loans (NPLs) in the Small and Medium Enterprises (SME) financing sector. It compares the NPLs in conventional and rural banks with Non-Performing Financing (NPF) in Islamic commercial and rural banks, before and after the stimulus, during the COVID-19 crisis period. The two policies are in the form of interest/margin subsidies and credit/financing restructuring for debtors in the SMEs sector. The approach used is a quantitative approach with three analytical methods consisting of ANOVA, MANOVA and DiD (Difference in Difference). The secondary data in this study were sourced from official publications of government institutions such as the Financial Services Authority and the Ministry of Finance. The results showed that there were significant differences in the performance of NPL/F of Conventional banks, Islamic Commercial Banks, Conventional Rural banks, and Islamic Rural banks before and after the government's economic stimulus policy was determined.

When climate meets real estate: A survey of the literature

AbstractWith near unanimity, climate scientists project natural disasters to increase in frequency, severity, and geographic scope over the next century. We survey academic literature at the intersection of these climate risks and real estate. Our review of physical risks includes price, loan performance, and migratory effects stemming from flooding, wildfires, and sea level rise. We review transition risks, including energy use and decarbonization, as they relate to real estate. Where possible, we explain how these topics may intersect with housing affordability, especially in historically disadvantaged communities. We conclude by highlighting critical areas for future research.

Distance lending & social connectedness

Using Facebook’s social network data for the US counties, we examine whether social connectedness reduces the informational disadvantage in lending to small businesses at a distance. We find that for a given distance, there is a pecking order of lending. Banks first lend to more socially connected counties, and later, banks expand credit to socially less connected areas. The probability of loan charge-off decreases in social connectedness and more so for the loans originated by small banks. In the cross-section, the positive effect of social connectedness on loan performance is higher for the loans originated by out of state banks. These findings suggest that loan officers get valuable information through their social networks.

Leveraging Machine Learning Algorithm to Enable Access to Credit for Small Businesses in the United States of America

The research centers on the essential function of loans in driving economic expansion and the intrinsic danger of loan defaults. Small businesses play a crucial role in generating employment and fostering economic growth, highlighting the significance of precise loan eligibility evaluations. The Small Business Administration's (SBA) 7(a) loan program seeks to assist small businesses by providing loan guarantees to mitigate risks for financial institutions (Mini et al., 2018). The study utilizes sophisticated machine learning methods, particularly the Random Forest and XGBoost algorithms, to forecast loan defaults and ascertain ideal loan amounts for small businesses. A dataset comprising 27 variables is analyzed, encompassing loan attributes, borrower details, and loan outcomes. The results highlight the effectiveness of both Random Forest and XGBoost in generating loan default predictions, with a slight edge for XGBoost. Additionally, Linear Regression is used to estimate loan amounts for qualified borrowers. The analysis identifies key factors contributing to loan defaults, with variables such as Term, Disbursement Gross, SBA Approval, and Gross Approval playing a significant role in Random Forest predictions. The study reveals intriguing patterns in loan defaults across various industrial sectors, emphasizing the complex nature of assessing loan performance within these industries (Zhou et al., 2023). This research aims to improve lending practices, benefiting both lenders and borrowers while enhancing our understanding of risk management in the context of small businesses.

Navigating Risk: A Deep Dive into Credit Risk Management Practices and Loan Performance in Kenya's Fintech Frontier

This study aimed at evaluating how credit risk management practices affect the loan performance of Fintech companies in Kenya. In particular, the study determined how credit terms, credit analysis, and credit mitigation affected loan performance. The research design used for the study was descriptive with the responders being credit officers from the Fintech companies in Kenya. Descriptive and inferential statistics were used to examine the information gathered from 62 Fintech companies through a primary data study that relied on questionnaires for data collection. Data collected was analyzed using descriptive statistics that yield tables, charts, mean and standard deviation that gave meaning to the data collected. The regression equation revealed that the predictors were significant and explained the model at an R squared of 80.5% to yield the study findings that credit risk management play a critical role in determining how well Fintech companies in Kenya operate when it comes to borrowing money and expanding their loan portfolio.

The performance of Islamic and conventional microfinance loans in Afghanistan: The Taliban and beyond

The Afghanistan microfinance industry has witnessed laurels in recent decades, making it crucial to closely monitor its development and sustainability. This study aims to assess the performance of Islamic and conventional microfinance loans in two aspects: first, by examining the occurrence of loan defaults, and second, by distinguishing between loan performance in areas controlled by the Taliban and those outside their control. To accomplish this, we analyze a unique dataset comprising over 9500 borrowers linked to an Afghan microfinance institution during the period spanning from January 2017 to February 2020. Our findings reveal that regions under Taliban control experienced fewer instances of loan defaults compared to areas not under their influence. Additionally, our analysis indicates that borrowers of Islamic loans in Afghanistan default more frequently than borrowers of conventional loans, particularly in Taliban-controlled areas. These observations remain largely consistent when we explore the factors influencing the number of days overdue on loan repayments. Furthermore, our conclusions find further support from both of the microfinance institution's Islamic loan products: business Murabaha loans, available to individuals of any gender, and women Murabaha loans, created as a group lending scheme exclusively for women. The results from this study offer valuable insights into how policy discussions in Afghanistan should be adjusted to facilitate a smooth transition for the microfinance industry.

Impact of Credit Risk Pricing on Commercial Banks’ Loan Performance in Nigeria

Impact of Credit Risk Pricing on Commercial Banks’ Loan Performance in Nigeria

Credit Lending Models and Loan Performance of Deposit-Taking Savings and Credit Cooperative Societies in Kenya

The study sought to determine the effect of credit lending models on loan performance of deposit-taking savings and credit cooperative societies in Kenya. Specifically, the study focused on group lending model, individual lending model, digital credit model and cooperative lending model on loan performance of deposit-taking savings and credit cooperative societies in Kenya. The study adopted a descriptive cross-sectional design. The targeted population was all DT-SACCOs as per their registration with SACCO Societies Regulatory Authority. The study population was 176. The study found out that group lending models, individual lending models, digital credit lending and cooperative lending were adopted by the DT-SACCOs to a moderate extent. The study established that the size of the DT-SACCOs and the lending models used accounted for 97.9% of changes in loan performance. The consequence is that other factors not considered in the model were responsible for only 2.1% of variances in loan performance. Further, credit lending models had a significant effect on the loan performance of DT-SACCOs in Kenya. This implied that effective implementation of the credit lending models led to improved loan performance of DT-SACCOs. The study concluded that credit lending models significantly affect the loan performance of DT-SACCOs in Kenya. Further, the DT-SACCOs adopted, on an average basis, the credit lending models. Lastly, individual lending models and total assets significantly affected loan performance. Group lending models, digital lending models, and cooperative lending models, however, do not have a significant effect on loan performance. The study recommended that the managers of the DT-SACCOs should establish mechanisms for improving individual loan processing and the development of competitive individual loan products.

Ethical Lending for Better Loan Performance: A Case for Utilitarianism in Commercial Banks

Ethical Lending for Better Loan Performance: A Case for Utilitarianism in Commercial Banks

Bank stability and fintech impact on MSMES’ credit performance and credit accessibility

The growth of financial technology (fintech) brings happiness to micro, small, and medium enterprises (MSMEs) that banks have denied access to credit. However, this condition has the potential to create a climate of intensified competition in the credit market and threaten banking stability. Therefore, this study examines the impact of banking stability and fintech on credit performance and credit access of MSMEs. This study uses a sample of 46 public commercial banks of the Republic of Indonesia and uses quarterly data from 2010 to 2022. The number of observations used for bank stability variables was 2,392, and for the fintech variables, 921 observations. This research analysis uses the fixed effect model method with robust standard errors. The results show that bank stability and fintech effect MSMEs’ credit performance and their access to credit. This finding encourages the competition-fragility theory. Bank stability reduces nonperforming loans and MSMEs’ access to credit. This indicates that stable banks encourage better MSME loan performance and thus restrict their lending to MSMEs. The existence of fintech is proven to improve MSMEs’ non-performing loans and their access to credit. Fintech that facilitates easy credit causes MSMEs` credit performance at banks to fall, which in turn opens the gate for MSME credit. The implication is that the financial services authority (OJK) needs to tighten further the online lending of fintech companies that have put more burden on MSMEs with high capital costs that can affect the ability of MSMEs to pay bank loan installments. AcknowledgmentsAppreciation is given to the Directorate General of Higher Education, Research and Technology, Ministry of Education, Culture, Research, and Technology, which has provided a fundamental research grant with contract number 182/E5/PG.02.00.PL/2023. Thanks are also given to higher education service institutions (LLDIKTI) Region 6 and the Institute of Research and Community Services (LPPM) Unisnu Jepara Indonesia, which has supported this research.