Non-performing loans and bank lending behaviour

Gjeçi, Ardit; Marinč, Matej; Rant, Vasja

doi:10.1057/s41283-022-00111-z

Cited by 6 publications

(5 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, for a solid experimental conclusion, another 4-fold cross-validation experiment was also studied. No sampling (original data) Logistic regression 0.9882 (12) 0.9920 (10) 0.9506 (12) 0.9709 (12) 0.9639 (12) Random forest 0.9979 (4) 0.9999 (3) 0.9902 (6) 0.9951 (4) 0.9938 (4) Gradient boosting 0.9961 (9) 0.9999 (3) 0.9812 (10) 0.9905 (9) 0.9882 (9) Over-sampling Logistic regression 0.9914 (11) 0.9895 (12) 0.9685 (11) 0.9789 (11) 0.9736 (11) Random forest 0.9999 (2) 1.0000 (1) 0.9999 (2) 0.9999 (2) 0.9999 (2) Gradient boosting 1.0000 (1) 1.0000 (1) 1.0000 (1) 1.0000 (1) 1.0000 (1) Under-sampling Logistic regression 0.9950 (10) 0.9900 (11) 0.9856 (9) 0.9878 (10) 0.9847 (10) Random forest 0.9986 (3) 0.9989 (8) 0.9940 (3) 0.9965 (3) 0.9956 (3) Gradient boosting 0.9979 (4) 0.9992 (7) 0.9908 (4) 0.9950 (5) 0.9937 (5) Combined sampling Logistic regression 0.9966…”

Section: Resultsmentioning

confidence: 99%

“…When borrowers fail to repay (or default on) their loans, it brings about an NPL for the lenders. Generally, an NPL is a major task to overcome in order to reach the stability and profitability of not only financial institutions [2] but also P2P platforms. So, risk assessment measures, diversification strategies, and collection processes are always performed to minimize the NPL issue.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Supervised Model Performance in Credit Risk Classification Using Sampling Strategies and Feature Ranking

Wattanakitrungroj,

Wijitkajee,

Jaiyen

et al. 2024

BDCC

View full text Add to dashboard Cite

For the financial health of lenders and institutions, one important risk assessment called credit risk is about correctly deciding whether or not a borrower will fail to repay a loan. It not only helps in the approval or denial of loan applications but also aids in managing the non-performing loan (NPL) trend. In this study, a dataset provided by the LendingClub company based in San Francisco, CA, USA, from 2007 to 2020 consisting of 2,925,492 records and 141 attributes was experimented with. The loan status was categorized as “Good” or “Risk”. To yield highly effective results of credit risk prediction, experiments on credit risk prediction were performed using three widely adopted supervised machine learning techniques: logistic regression, random forest, and gradient boosting. In addition, to solve the imbalanced data problem, three sampling algorithms, including under-sampling, over-sampling, and combined sampling, were employed. The results show that the gradient boosting technique achieves nearly perfect Accuracy, Precision, Recall, and F1score values, which are better than 99.92%, but its MCC values are greater than 99.77%. Three imbalanced data handling approaches can enhance the model performance of models trained by three algorithms. Moreover, the experiment of reducing the number of features based on mutual information calculation revealed slightly decreasing performance for 50 data features with Accuracy values greater than 99.86%. For 25 data features, which is the smallest size, the random forest supervised model yielded 99.15% Accuracy. Both sampling strategies and feature selection help to improve the supervised model for accurately predicting credit risk, which may be beneficial in the lending business.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enhancing Supervised Model Performance in Credit Risk Classification Using Sampling Strategies and Feature Ranking

Wattanakitrungroj,

Wijitkajee,

Jaiyen

et al. 2024

BDCC

View full text Add to dashboard Cite

show abstract

“…The increase of branches in the banking sector has led to the number of NPLs escalating yearly. NPL to LA is decreased in the private sector as compared to the public sector (Naili & Lahrichi, 2022;Gjeçi et al, 2023).…”

Section: Problem Statementmentioning

confidence: 98%

Impact of Credit Risk Management on Bank Performance: An Empirical Study on Commercial Banks Listed at Pakistan Stock Exchange (PSX)

Mahmood,

Ali,

Riaz

et al. 2023

J. financ. account. res.

View full text Add to dashboard Cite

Commercial banks are involved in uncontrolled credit risk management that negatively affects their sustainable banking performance. Many guidelines, strategies, and judgments have been made, such as the Basel Accords, to control these issues and adequately manage their lending and borrowing policies. This study aims to analyse the impact of credit risk management on the sustainable performance of commercial banks. For this purpose, secondary panel data was collected from the annual financial reports of 27 commercial banks out of the 31 listed on the Pakistan Stock Exchange (PSX) for the period 2017-2021. E-views 10 software was applied to perform descriptive correlation and multiple regression analyses. In the current study’s model, credit risk management proxies, return on assets (ROA), return on equity (ROE), and net interest margin (NIM) were employed as dependent variables. At the same time, capital adequacy ratio (CAR), loan and advances (LA), non-performing loans (NPL) ratio, market profit opportunity (MPO), and bank liquidity (BL) were employed as independent variables. The study concludes that bank liquidity has a significant positive relationship with bank performance. Comparably, capital adequacy ratio, non-performing loans, bank liquidity, market profit opportunity, and loan and advances harm the sustainable performance of commercial banks. The research suggests that implementing stricter policies and strategies, such as the regulation of customer loans, is required to control these issues.

show abstract

“…Bank size is calculated as the logarithm of total assets at the end of the year. Ghosh (2023) and Gjeçi et al (2023) observe that profitable banks can attract more deposits and are better positioned to generate and retain capital, enabling them to extend more loans. Therefore, this study expects profitability, measured as net income divided by equity, to have a positive influence on bank lending behavior.…”

Section: Control Variablesmentioning

confidence: 99%

“…To test the first hypothesis examining the effect of legal origins on bank lending behavior, this study employs the following baseline model, following previous studies of Gjeçi et al (2023), Le et al (2022) and Aslan et al (2022).…”

Section: Empirical Strategymentioning

confidence: 99%

Legal origin and bank lending behavior in developing countries: The mediating role of revenue diversification

Kamau,

Simo‐Kengne

2024

J Corp Accounting Finance

View full text Add to dashboard Cite

This paper explores the relationship between legal origin, revenue diversification, and bank lending behavior. The analysis is based on a sample of 2590 commercial banks operating in 139 developing countries from 2004 to 2022. Using various panel data estimation techniques and alternative measures of bank lending behavior, the results indicate that banks in common law countries experience lower levels of loan growth compared to their counterparts in civil law countries. The study results also show that revenue diversification indirectly alleviates the negative effect of loan growth in banks originating from a common law legal origin. Notably, this effect is not observed in banks within low‐income and African countries, highlighting the importance of policies aimed at enhancing institutional capacity within their legal and judicial systems. Overall, the results of this study underscore the significance of legal origins in shaping the lending dynamics of banks in developing countries.

show abstract

Non-performing loans and bank lending behaviour

Cited by 6 publications

References 67 publications

Enhancing Supervised Model Performance in Credit Risk Classification Using Sampling Strategies and Feature Ranking

Enhancing Supervised Model Performance in Credit Risk Classification Using Sampling Strategies and Feature Ranking

Impact of Credit Risk Management on Bank Performance: An Empirical Study on Commercial Banks Listed at Pakistan Stock Exchange (PSX)

Legal origin and bank lending behavior in developing countries: The mediating role of revenue diversification

Contact Info

Product

Resources

About