Bank Credit Risk Research Articles

Development and Implementation of a Multilayer Deep Learning-Based Bank Credit Risk Forecasting System

The complexity of the financial environment and the international community makes the capital flow face various challenges, and it is difficult to obtain accurate credit prediction results in the actual application environment. Considering the complex non-linear characteristics of customer information, the Analytic Hierarchy Process is studied to meet the needs of bank credit risk assessment. On this basis, a depth neural network with different complexities was selected for the three indicators built to classify the features. The composition of the neural network module and the number of neurons were determined by experiment, and Dropout was used to prevent overfitting of the test dataset. Stability and ablation experiments showed that the model can control the error between datasets to 0.021. The ablation experiment showed that the numbers of hidden layers and neurons were the best. Simulation tests showed that the sensitivity and accuracy of this method were 85.25% and 92.55%, respectively, which were superior to other classification methods. The real data of banks in the past four years were tested. The results could accurately classify the risks of enterprises and individual customers, and the results of stress test showed that the model is stable. It is found that traditional credit risk assessment models rely on statistical means and rule decisions, and these methods may not fully reveal the complex non-linear relationship and the internal relationship of financial indicators in high-dimensional data. The combination of deep learning technology and hierarchical analysis can better deal with and explain the complex non-linear problems in bank risk assessment.

Risk and reward: unraveling the link between credit risk, governance and financial performance in banking industry

Purpose This study aims to investigate the moderating role of corporate governance (CG) on the relationship between credit risk (CRs) and financial performance (FP) of banks listed in the Palestine Securities’ Exchange (PEX) and Amman Securities’ Exchange (ASE). Design/methodology/approach This study used a hypothesis-testing research design to collect data from the annual reports of 21 banks listed on (PEX) and (ASE). Secondary data, annual reports and disclosures were used between from 2009 to 2019. Descriptive and inferential statistics were used, along with correlation analysis to evaluate linear relationships between variables. Data was collected based on panel data, the VIF was used to test multicollinearity and binary logistic regression was used to develop the research model. Findings The regression results showed the association between CR and firm performance depends on the measurement of each factor applied. The results showed mixed results between loans to total assets (LTA) and nonperforming loans to total loans (NPLs) with FP. LTA has a significant and positive effect on TOBINSQ and return on equity (ROE), but an insignificant and positive effect on return on assets (ROA). On the other hand, NPLs have a significant and negative effect on ROA, whereas NPLs have a weak and positive effect on TOBINSQ. However, there is an insignificant and positive effect of NPLs on ROE. Moreover, the results demonstrated that CG moderated the relationship between CRs and FP of banks. The practical contribution of this paper, for bank policymakers and authorities, the study’s implications are noteworthy. Understanding the varied impacts of different CR measures on FP can help regulators and policymakers design more tailored and effective risk management frameworks for banks. Research limitations/implications This study had limitations that future research might be able to address. First, the small size of the sample used in the study included 21 banks listed on the PEX and ASE. Likewise, the ASE and PEX are considered developing stock exchanges, so the results of this study may differ from those of other stock exchanges. Second, only CRs were considered in this study when examining the association between the profitability of Palestinian banks and ASE. Other studies can be undertaken on other nonfinancial risks, such as operational risk, to measure the differences between them and examine their effects on the profitability of Palestinian and Jordanian banks. Other studies might be performed to compare CRs and its impact on profitability in Palestinian and Jordanian banks with those in other Western and Eastern banks. Furthermore, in addition to TOBINSQ, ROA and ROE, researchers can use other financial indicators to measure profitability. This will contribute to substantiating the present study’s findings. Originality/value Although several studies have examined the relationship between CRs and FP in developed and developing countries, the results have been mixed. However, this study is one of the few studies that examined the moderating role of CG in association with CRs and FP, especially on Palestinian and Jordanian contexts. Finally, the findings offer policymakers and practitioners of Palestinian and Jordanian contexts.

Innovative Application of Artificial Intelligence Technology in Bank Credit Risk Management

With the rapid growth of technology, especially the widespread application of artificial intelligence (AI) technology, the risk management level of commercial banks is constantly reaching new heights. In the current wave of digitalization, AI has become a key driving force for the strategic transformation of financial institutions, especially the banking industry. For commercial banks, the stability and safety of asset quality are crucial, which directly relates to the long-term stable growth of the bank. Among them, credit risk management is particularly core because it involves the flow of a large amount of funds and the accuracy of credit decisions. Therefore, establishing a scientific and effective credit risk decision-making mechanism is of great strategic significance for commercial banks. In this context, the innovative application of AI technology has brought revolutionary changes to bank credit risk management. Through deep learning and big data analysis, AI can accurately evaluate the credit status of borrowers, timely identify potential risks, and provide banks with more accurate and comprehensive credit decision support. At the same time, AI can also achieve real-time monitoring and early warning, helping banks intervene before risks occur and reduce losses.

The role of Sharia governance in minimizing credit risk in Islamic banking: a systematic literature review

Purpose The purpose of this paper is to engage in a systematic examination of previous scholarship on the relationship between Sharia governance (SG), which is represented by the Sharia Supervisory Board (SSB), and the Internal Sharia Review (ISR), to determine whether the ISR can minimize financing risk in Islamic banking. Design/methodology/approach The literature search consisted of two steps: a randomized and systematic literature review. The methodology adopted in this article is a systematic literature review. Findings To reduce the risk of financing in Islamic banking, SG must be implemented optimally by making rules regarding the role of the SSB in supervising customer financing. In addition, it is a necessary to establish an entity that assists the SSB in the implementation of SG, namely, the ISR section, but there is still very little research on the role of the SSB and ISR in minimizing financing risk. Practical implications Establishing an ISR to assist the SSB in carrying out its duties has direct practical implications for Islamic banking: minimizing financing risks and compliance with Islamic Sharia principles. In addition, new rules regarding the role of SSBs and the ISR in reducing credit risk include monitoring customers to ensure that they fulfill their financing commitments on time. This new form of regulation and review can be used as a reference by the Otoritas Jasa Keuangan or Finance Service Authority to create new policies or regulations regarding SG, especially in Indonesia. Originality/value Subsequent research may introduce other more relevant variables, such as empirically testing the competence, independence or integrity of SSB and the ISR team as it attempts to minimize the risk of financing in Islamic banks. In addition, further research is expected to examine whether the SSB or the ISR team has a positive or negative influence on the risk of financing Islamic banks with secondary data.

Does BRRD mitigate the bank-to-sovereign risk channel?

We investigate the effectiveness of the Bank Recovery and Resolution Directive (BRRD) in mitigating the transmission of credit risk from banks to their sovereign, using CDS spreads to capture bank and sovereign credit risk for a sample of 43 banks in 8 Euro Area countries over the period 2009-2020. If the BRRD bail-in framework is credible, changes in bank default risk should not be transmitted to sovereign risk. In a novel approach we use banks earnings announcements to identify exogenous shocks to bank credit risk and investigate to what extent bank risk is transmitted to sovereign risk before and during the BRRD era. We find that bank-to-sovereign risk transmission has diminished after the introduction of the BRRD, suggesting that financial markets judge the BRRD framework as credible. The decline in bank-sovereign risk transmission is particularly significant in the periphery Euro Area countries, especially Italy and Spain, where the bank-sovereign nexus was most pronounced during the sovereign debt crisis. We report that the lower bank-to-sovereign credit risk transmission is associated with the parliamentary approval of the BRRD and not with the OMT program launched by the ECB to affect sovereign yield spreads, nor with specific bail-in or bailout cases which occurred during the BRRD era. Finally, we document that the reduction in risk transmission is most pronounced for banks classified as a Global Systemically Important Bank (G-SIB), stressing the importance of additional capital buffers imposed by Basel III.

Evaluation of multimodal data-driven financial risk prediction methods for corporate green credit

With the rapid economic development and increasingly serious environmental problems, many regions have launched green credit policies. Green credit can reduce the loan interest rate of the environmental protection industry and lower the financing threshold. Traditional risk prediction methods cannot comprehensively evaluate the green credit risk of the enterprise based on the degree of green environmental protection and the industry environment in which the enterprise is located, resulting in the inconsistency between the credit financial risk prediction and the actual results, which increases the bank credit risk. In order to strengthen the management level of green credit and reduce the probability of non-performing loans, a scientific risk assessment method was constructed by using a combination of automatic encoding network and bidirectional long short-term memory neural network model to predict the financial risks of green credit, driven by multi-modal data. Through the study of multimodal data, this paper took green credit financial risk as the research object, aggregated the information of various enterprises to improve the bank’s capital utilization rate, and also promoted enterprises to take the initiative to transform into the direction of green environmental protection. Finally, the experiment proved that multimodal data fusion model was more superior than random forest in risk prediction, reducing the bank’s non-performing loan rate by 3.1% and improving the bank’s risk control level.

Evolution and future directions of banking risk management research: A bibliometric analysis

This bibliometric analysis examines the evolution of academic research on banking risk management over the past four decades. The research maps publication trends, influential works, authorship, geographical distribution, conceptual themes, and future research directions using quantitative analysis of 286 English-language articles from the Scopus database. Since the 1990s, publication output and citations have been on the rise, with peaks in 2012 and 2019, indicating a rise in scholarly interest. The focus of research has expanded beyond credit risk to include operational, liquidity, and other key risks. Governance and culture are also expanding areas of emphasis. Geographic diffusion is revealed by bibliometric mapping, shifting from the early dominance of U.S. and European scholars to the increasing contributions of Asia and other emerging economies. Analysis of frequently occurring keywords illustrates the importance of fundamental risk management concerns. Six conceptual domains are identified by cluster analysis: operational risks, governance, liquidity risks, commercial bank risks, credit risks and performance, and market risk interactions. Based on the bibliometric analysis and research findings, three promising future research directions are proposed: the impact of pandemics and natural disasters on bank risk management; emerging threats such as cybercrime and climate change; and the impact of risk culture and governance on outcomes. AcknowledgmentIt is crucial to recognize everyone who contributed to the success of this study, notably the Ho Chi Minh University of Banking, Vietnam.

Capital market openness and bank credit risk: Evidence from listed commercial banks

This paper utilizes the quasi-natural experiment of the "Shanghai-Shenzhen-Hong Kong Stock Connect" to examine the impact of capital market openness on bank credit risk. A multi-period difference-in-difference model is employed to explore the effects and underlying mechanisms based on data from 2007 to 2022. The findings indicate that capital market openness leads to a notable rise in the banks' credit risk, mainly due to the substantial enhancement in liquidity. Furthermore, the impact of capital market openness is more pronounced on banks with greater market strength and a higher level of digital transformation, resulting in a more substantial positive effect.

Capital inflow liberalization and bank credit risk

Using a panel of annual data, covering 2207 banks operating in 45 emerging, and developing economies, over the period of 2009–2020, we study the impact of liberalization on capital inflows. Our results indicate that capital inflow liberalization has a robust and positive impact on bank credit risk, as measured by non-performing loans. Upon further examination, we find that the positive effect is more pronounced when bond, money, and financial credit markets, which broaden firms’ financing channels, are liberalized. The liberalization intensifies competition and risk appetite among banks, leading to increased credit risk. The findings suggest that openness reduces banks’ credit growth while improving non-interest income. As expected, this positive effect is mitigated within large and competitive banks, and banks with more assets. Furthermore, we find that tightening macroprudential policies, especially countercyclical capital buffers, can help moderate the positive impact of capital inflow liberalization on bank credit risk.

Venturing into Risk Management: Examining Credit Risk and Performance in Pakistani Commercial Banks through Panel VAR Analysis from a Business Perspective

In Pakistan's dynamic financial sector, effective credit risk management by commercial banks is critical to maintaining financial stability. In this study, we embarked on a unique and comprehensive journey, adopting the Panel Vector Autoregressive (PVAR) analysis, a novel methodology in this context. This approach allowed us to delve into the intricate relationship between credit risk management strategies and the aggregate business performance of commercial banks. The data used in this study spans from 2010Q1 to 2022Q4, investigating the comprehensive nexus of credit risk and macroeconomic indicators using a large dataset encompassing 18 strategically critical commercial banks of Pakistan. Our study uncovers several profound insights, documenting a remarkable increase in credit risk upon increases in the interest rate. The repercussions of the non-performing loans are observed nearly two years after the successive phases of a stern posture of monetary policy have been implemented. Our research findings carry significant weight for the banking industry. We discovered that the levels of credit risk could be reined in due to the protective shield offered by phases of sudden economic booms. This underscores the reinforcing effect of the improving economic conditions on defaults of loans, providing practical and actionable insights for credit risk management strategies.

An Intelligent Model to Assess the Credit Risk in Egyptian Banks

An Intelligent Model to Assess the Credit Risk in Egyptian Banks

The Effect of Macroeconomic Factors on Banking Credit Risk Study on Commercial Banks in Indonesia

Melalui analisis kualitatif, penelitian ini menyelidiki hubungan yang rumit antara variabel makroekonomi dan risiko kredit di bank-bank komersial Indonesia. Dengan bantuan perangkat lunak NVIVO, analisis tematik dari wawancara mendalam dan analisis dokumen mengungkapkan tema-tema tingkat makro yang terkait dengan variabel-variabel ekonomi internasional serta topik-topik spesifik Indonesia terkait dengan lingkungan regulasi dan ekonomi negara. Kesimpulan utama menunjukkan bahwa risiko kredit sangat dipengaruhi oleh perkembangan ekonomi, inflasi, tingkat suku bunga, dan pengangguran, dengan poin-poin kecil yang perlu mendapat perhatian khusus. Muncul sebagai pengaruh yang menstabilkan, sistem regulasi Indonesia mengarahkan prosedur manajemen risiko. Kesulitan ekonomi tertentu, seperti ketergantungan pada komoditas dan ketidakstabilan mata uang, menyoroti perlunya penilaian risiko sektoral. Pentingnya penilaian risiko yang dinamis dan evaluasi peraturan yang sedang berlangsung ditekankan, bersama dengan implikasi untuk prosedur manajemen risiko dan saran-saran untuk pembuat kebijakan. Studi ini menyoroti interaksi antara isu-isu makroekonomi dengan kualitas sistem perbankan Indonesia yang berbeda, dan memberikan wawasan yang signifikan ke dalam area ini.

Does digital inclusive finance affect the credit risk of commercial banks?

This paper adopts the data of commercial banks from 2011 to 2021 to carry out the research on the impact of digital inclusive finance on the credit risk of commercial banks. The results show that, first, digital inclusive finance reduces credit risk of commercial banks, and has a greater mitigating effect on credit risk of national banks than regional banks. Second, economic policy uncertainty makes banks' credit risk rise. Compared with national commercial banks, economic policy uncertainty increases the credit risk of regional commercial banks more significantly. Third, the higher the profitability of banks, the more beneficial digital inclusive finance is to reduce the credit risk of commercial banks.

CREDIT RISK DETERMINANTS OF COMMERCIAL BANKING

Studies on non-performing loans in banking provide mixed results regarding the bank-specific factors that influence them. This research aims to analyze the determinants of credit risk in commercial banking in Indonesia. Testing was conducted on 32 banking companies listed on the Indonesia Stock Exchange for 2019-2021 with 96 observations using panel data regression. The research results show that increasing bank diversification and external audit quality significantly reduce the risk of credit non-performing loans (NPL). Other findings of this research show that credit growth, operational efficiency, and bank size do not significantly affect credit risk. To overcome the problem of endogeneity and dynamic panel bias, a series of robustness tests were carried out using the 2SLS, LIML, and GMM approaches provided significant results. The results of this research imply that bank risk management plays a role in reducing problem loans, which must align with the business entity's efforts to increase profits.

The impact of green credit distribution on bank performance and influencing factors

This research aims to analyze the impact of green credit distribution by banks on bank performance and identify factors that can influence green credit. The study utilizes data from 46 banks in Indonesia during the 2018-2022 period, by using the panel data regression method. The findings indicate (i) that green credit does not have a significant influence on credit risk, as measured by the NPL (Non-performing Loan). The distribution of more green credit allocations does not result in a decrease in bank credit risk. Additionally, sustainable business borrowers do not exhibit better debt repayment performance compared to the non-sustainable business category. (ii) In terms of bank profitability, green credit does not impact ROE (Return on Equity) and NIM (Net Interest Margin), but it does have a negative effect on ROA (Return on Assets). Banks that allocate a significant portion of their credit distribution to green initiatives tend to experience a decline in their profits. (iii) Bank size has a positive impact on the allocation of green credit, with larger banks dedicating a greater portion to the distribution of green credit. Larger banks possess more capital and extensive networks, making them better equipped to address potential risks compared to smaller banks. (iv) Meanwhile, government ownership and good corporate governance in banks do not influence the proportion of green credit distribution. The author recommends that the government make corrections to existing green financing programs, to cultivate a green credit ecosystem in Indonesia. One concrete step that can be taken is to support government-owned banks in becoming pioneers in the distribution of green credit in Indonesia.

Analysing the Influence of Macroeconomic Factors on Credit Risk in the UK Banking Sector

Macroeconomic factors have a critical impact on banking credit risk, which cannot be directly controlled by banks, and therefore, there is a need for an early credit risk warning system based on the macroeconomy. By comparing different predictive models (traditional statistical and machine learning algorithms), this study aims to examine the macroeconomic determinants’ impact on the UK banking credit risk and assess the most accurate credit risk estimate using predictive analytics. This study found that the variance-based multi-split decision tree algorithm is the most precise predictive model with interpretable, reliable, and robust results. Our model performance achieved 95% accuracy and evidenced that unemployment and inflation rate are significant credit risk predictors in the UK banking context. Our findings provided valuable insights such as a positive association between credit risk and inflation, the unemployment rate, and national savings, as well as a negative relationship between credit risk and national debt, total trade deficit, and national income. In addition, we empirically showed the relationship between national savings and non-performing loans, thus proving the “paradox of thrift”. These findings benefit the credit risk management team in monitoring the macroeconomic factors’ thresholds and implementing critical reforms to mitigate credit risk.

Assessment of credit risk management practice in Dashen Bank

Financial stress is affecting all types of businesses across industries, but it particularly affects banks because they are a major source of capital and taking risk is an essential and unavoidable part of the banking business. Indeed, taking risk is embedded with reward, and financial crises have become a serious problem for the world in recent years. These papers evaluate Dashen Bank's approach to credit risk management. This study's primary objective is to evaluate Dashen Bank's credit risk management practices and determine how they are managed. Its primary focus is on credit evaluation in Dashen Bank. The researcher used descriptive research design, distributed questionnaires to officers. In addition to this the researchers used in- depth interview with management bodies. Both primary and secondary data collection method were used, census method were used, the study findings indicate that the bank doesn’t provide enough training for employees, the offsite follow up method placed by the bank is not successful, the credit risk management of the bank is weak also the credit collection system is not effective are among the main findings. The researcher suggest that the bank should provide strong and consecutive training for the employee, better follow up mechanism should apply new procedure should put in place to assess the capacity the client who need the long term loan.

Introducing the overall risk scoring as an early warning system

Business performance is a critical field of study, which should be assessed in more than just credit risk in the banking context. However, much previous research takes business performance in the context of credit risk in banking. In this study, risks will be analyzed to measure business performance in an integrated manner within the framework of non-financial sector dynamics. To this end, brainstorming sessions, risk workshops, surveys, and face-to-face interviews were held with representatives of small medium enterprises in 11 different sectors. Through field studies, risks have been identified and assessed in terms of impact and probability, Key Risk Indicators have been determined, and risks have been scored based on financial and non-financial metrics to estimate the Overall Risk Scoring. Moreover, the Overall Risk Scoring model has been tested using Logit Regression and Artificial Neural Networks (ANN), the Naïve Bayes Algorithm, and the C4.5 decision tree model. All methods have statistically verified that the predictive power of the structure of the Overall Risk Scoring is high. Our findings reveal that when business performance is analyzed with non-financial and financial metrics, dynamic and static data, market expectations, and banking needs, the predictive power of the calculated Overall Risk Scoring increases. The created Overall Risk Scoring Model can be used as an early warning system for many objectives by business executives, suppliers, consumers, investors, financial institutions, public bodies, credit rating agencies, and entities like the Credit Guarantee Fund.

Analyzing the Influence of Bank Competition on Credit Risk: Perspectives from Indonesia's Dual Banking System

This study analyzes the effect of competition banks on credit risk in the dual banking system in Indonesia. This research was conducted using a purposive sampling technique in selecting a sample of 5 conventional commercial banks and 5 Islamic commercial banks. The method used is the Generalized Method of Moments (GMM) from 2011 to 2020. Credit risk for Conventional Banks is measured by the value of Non-Performing Loan (NPL), while Islamic Bank Financing is measured by the value of Non-Performing Financing (NPF). The results of this study indicate that Return on Assets (ROA) for Conventional Banks and Islamic Banks has a significant effect on credit risk in the dual banking system, Loan to Deposit Ratio (LDR) for Conventional Banks does not have a significant effect on Non-Performing Loan (NPL) while Financing to Deposit Ratio (FDR) of Islamic Banks has a significant level 2 influence on Non-Performing Financing (NPF). Bank size does not have a significant influence on credit risk in the dual banking system, and the Lerner Index for Conventional Banks has a significant effect on Non-Performing Loan (NPL), while the Lerner Index for Islamic Banks has no effect on Non-Performing Financing (NPF). The Central Bank in making policies can see that the level of competition for banks in the dual banking system in Indonesia is categorized as a monopolistic competition market, where each bank has its own market segment so that it has market power that is strong enough to set prices that are relatively.

Determinant of credit risk of Islamic banks in Pakistan

This study aims to investigate the influence of macroeconomic variables and bank-specific factors on the credit risk of Islamic banking in Pakistan, through the panel data regression tools. The statistical tool which is applied to the research is ordinary least square (OLS) regression model. All the assumption to be fulfilled before using OLS. The secondary data have been taken from four (04) full-fledged Islamic banks in Pakistan, from 2007 to 2021. The focus of the research is to find the impact of macroeconomic variables like Gross domestic product, inflation, and growth in the interest rate and bank-specific factors like size, return on assets, loan loss provision, capital Adequacy ratio, and Asset quality to determine the credit risk (non-performing loans) of Islamic banks in Pakistan. The result of the ordinary least square (OLS) regression model is that loan loss provisions (LLP) have a positive and significant impact on credit risk (CR) and size of bank (S), and Capital adequacy ratio (CAR) have a negative and significant impact on credit risk (CR) of Islamic Bank of Pakistan. Inflation (INF) and Gross domestic product (GDP) have a positive and insignificant impact on credit risk (CR), and growth in interest rate (INT), return on assets (ROA), and asset quality (AQ) has a negative and insignificant impact on Credit risk (CR) of Islamic Bank of Pakistan. Therefore, Islamic banks should carefully examine their specific factors, i.e. LLP, S, and CAR to manage their credit risk, particularly in monitoring loans.