Credit Portfolio Research Articles

Loan Eligibility Prediction Using Machine Learning

Banks and other financial institutions compete for customers by providing a wide range of services and products. Most banks, however, make the vast majority of their money from their credit portfolio. Loans accepted by borrowers might lead to interest charges. The loan portfolio, and customers' repayment habits in particular, can have a substantial impact on a bank's bottom line. The financial institution's Non-Performing Assets can be reduced if it can accurately predict which borrowers are likely to default on their loans. Therefore, there is substantial scholarly value in exploring the prediction of loan endorsement. In order to make accurate predictions, it is crucial to use Machine Learning methods. Based on a person's past loan qualification history, this research uses a machine learning methodology to predict the person's likelihood of consistently making loan repayments. The primary aim of this research is to foretell how likely it is that a given individual will be granted a loan.

Efficient credit portfolios under IFRS 9

AbstractIn this paper, we devise a forward‐looking methodology to determine efficient credit portfolios under the IFRS 9 framework. We define and implement a credit loss model based on prospective point‐in‐time probabilities of default. We determine these probabilities of default and the credits' stage allocation through a credit stochastic simulation. This simulation is based on the estimation of transition matrices. Using data from 1981 to 2019, in a non‐homogeneous Markov chain setting, we estimate transition matrices conditional on the global real gross domestic product growth. This allows considering the effects of the economic cycle, which are of great importance in bank management. Finally, we develop a robust optimization model that allows the bank manager to analyze the trade‐off between the annual average portfolio income and the corresponding portfolio volatility. According to the proposed bi‐objective model, we compute the efficient credit portfolios constructed based on 10‐year maturity credits. We compare their structure to those generated by the IAS 39 and CECL accounting frameworks. The results indicate that the IFRS 9 and CECL frameworks generate efficient credit portfolios whose structure penalizes riskier‐rated credits. In turn, the riskier efficient credit portfolios under the IAS 39 framework concentrate entirely on speculative‐grade credits. This pattern is also encountered in efficient credit portfolios constructed based on credits with different maturities, namely 5 and 15 years. Moreover, the longer the maturity of the credits that enter into the composition of the efficient portfolios, the more the speculative‐grade credits tend to be penalized.

BVN REGULATORY FRAMEWORK AND BANKING SYSTEM STABILITY IN NIGERIA

This study examined the effect of BVN Regulatory Framework on banking system Stability in Nigeria. The study adopted a survey research design and Primary data for this study were obtained through questionnaires, which were administered to 213 management staff of the ten (10) selected banks. The data was analyzed using descriptive statistics while spearman rank correlation was used to test the hypotheses. The result indicates that BVN Regulatory Framework have a significant effect on bank capital adequacy, bank liquidity and asset quality in Nigeria. The study concludes that BVN Regulatory Framework have a significant effect on banking system stability in Nigeria. It was recommended that Banks must ensure that Customers Bank Accounts are protected from unauthorized access while implementing BVN regulatory framework so as to avoid running into liquidity problem; In other to maintain a sound capital base, banks must ensure that staff comply strictly to BVN regulatory framework in it operation and Banks should continue to make effective use of BVN regulatory framework in the course of lending and administration so as to maintain high credit portfolio while avoiding cases of non-performing loan.

Мінімізація кредитного ризику та підвищення якості кредитного портфеля банку

The article considers the main factors that form credit risk and determines the role of credit risk in the process of formation of the credit portfolio of a commercial bank. It is determined that bank lending involves the functioning of a complex mechanism that includes certain actions aimed at attracting cheap funds and their use in accordance with the terms of the established lending policy, taking into account the minimum risk and maximum profit. As you know, the main source of income of banks is the profit from lending. In this regard, the main problem facing the bank’s management today is the effective management of the bank’s loan portfolio. Against the background of the negative impact of the global financial crisis, the formation of an optimal loan portfolio of the bank is of particular importance in order to increase the efficiency of its activities through the appropriate credit policy. Improving the quality of lending and optimizing the structure of banks’ loan portfolios are traditionally relevant in research, as lending has always been and will remain the main economic function of banks. The article describes each stage of credit activity, which consists of sequential actions. The definition of "credit portfolio quality" as a complex concept that characterizes the efficiency of credit portfolio formation in order to determine its profitability and the degree of credit risk is considered. The development of measures to optimize credit risk is one of the ways to improve the credit process and the entire system of managing the financial flows of the bank as a whole, not just banking risks. The factors influencing the formation of credit risk are analyzed. The main approaches to credit portfolio management in a commercial bank are characterized. It is proved that most of the constructed and implemented models for optimizing the loan portfolio are based on the criterion of risk-return (rather than profitability-risk) and have certain limitations and difficulties in practical application. The quality of the loan portfolio determines the bank’s capabilities in its functioning in the market of credit products, which affects the level of its lending activity and the possibility of restoring positions in the credit market. The process associated with lending is determined by the quality of credit work in banks. Statistics on the functioning of commercial domestic and foreign banks indicates that a well-organized credit process, a well-formed loan portfolio and credit policy will ensure the bank’s prosperity in the future

Modelling of corporate exposure at default (EAD) in emerging financial markets: The case for counters listed on the Zimbabwe stock exchange (ZSE) in the dollarization era

This study explores the exposure at default (EAD) emanating from credit events undertaken by listed banking corporations trading on emerging markets, such as Zimbabwe’s Stock Exchange (ZSE) or Market in the dollarization era, namely period 2010-12. The dollarization of the Zimbabwean economy in 2009 coincided with the recovery of the global financial economy from the worst worldwide economic recession ever experienced in this world. The study used audited and published data drawn from financial statements of two banking corporations for the period 2010 to 2012 that were accessible on ZSE website. These data were presented and analyzed using Eviews7. The study revealed that there was a lot of non-performing loans drawn from EADs of banking corporations trading on the ZSE in the period under review. The study further noted that credit exposures issued by commercial banks in the period 2010-2012 were also exposed to risk from the nature of the borrowers, banks’ internal and external market variables. The variables that impacted on banks’ credit exposures include political, social, industrial, unemployment, technological challenges, state of financial markets, their capitalization and liquidity statuses. We therefore conclude that banks in emerging markets need to efficiently and effectively manage their credit portfolios in their desire to grow towards sustainable development. The study also concludes that banks in emerging markets that are into lending activities should adopt and implement financial econometric (EAD) models that are easy to apply, practical, pragmatic and adjusted for market friction. The study recommends that listed banking corporations in emerging markets need to adhere to the requirements of the Basel II and III Capital Accords if they are to make meaningful business out of their credit exposure operations. It also recommends that banks should come up with capitalization and investment strategies that suit their economic conditions if they are to grow and develop sizeable market shares and wealth from their lending businesses. Finally the study recommends that banks in emerging economies should adapt to international business standards, strategies, ethics and corporate governance parameters if they are to grow towards greater similarity with those in developed nations in their service delivery to the stakeholders and contribution to nation building and sustainable development.

АНАЛІЗ КРЕДИТНОЇ ПОЛІТИКИ БАНКІВСЬКОГО СЕКТОРУ УКРАЇНИ

The article is devoted to issues of the banking system of Ukraine. In modern conditions regarding the functioning and development of banking in the country, the creation of the credit policy of Ukraine occupies an important place. If the bank's credit policy is effective, then the banking risk is reduced and the bank's profit increases, even in crisis conditions of economic development. To assess credit policy, such categories as: credit portfolio, amount of non-performing loans and compliance with NBU regulations were analyzed. The dynamics of the entire amount of loans issued was studied, as well as the structure of the credit portfolio of the banking sector of Ukraine by type of borrower during 2018-2022 was analyzed. The causes of credit risk were analyzed, this stage is important, because it helps to identify ways to overcome threats to a specific institution or in general system, and also minimizes the likelihood of risks. In the course of the research, the issue of non-performing loans was considered, this is an integral category of the bank lending process. A low-quality loan portfolio is characterized by a high proportion of non- performing loans, which is negative and requires immediate reduction. Control of their value allows to prevent serious problems of the bank's financial condition, contributes to improving the stability of both a specific institution and the banking system in general. In addition, the amount of reserves for outstanding liabilities was analyzed, the amount of reserved funds characterizes the credit risk management process. When implementing credit activities, it is important to comply with the economic standards of the National Bank of Ukraine, which provide an opportunity to analyze the accepted credit risk from a different perspective. That is why the dynamics of these indicators during 2018-2022 were considered, where special attention was paid to the group of credit risk indicators.

АДАПТИВНИЙ ФІНАНСОВИЙ МЕХАНІЗМ УПРАВЛІННЯ ІНВЕСТИЦІЯМИ І КРЕДИТНИМ ПОРТФЕЛЕМ ПІДПРИЄМСТВА

The article provides a definition of the adaptive financial mechanism for managing investments and the enterprise's credit portfolio as a set of forms and methods of influence of the managing entity on the object, represented by real and financial investments, long- and short-term bank loans, taking into account changes in the internal and external environment by using methods risk forecasting and analysis. It is shown that the adaptive financial mechanism is a tool for the implementation of a flexible financial policy, the implementation of which will contribute to the growth of the enterprise's resistance to destructive changes in the external environment, the strengthening of financial stability and competitiveness, and the improvement of the well-being of its owners and workers. The content of the legislation that determines the legal status of investment activity, the regime of foreign investment, the inadmissibility of discrimination in taxation of business entities created using property and funds of domestic origin is summarized. It is shown that the legal basis for managing the credit portfolio of a business entity is the legislation on banks and banking activities, as well as regulatory acts that determine the procedure for determining the amount of credit risk by banks of Ukraine for active banking operations. The procedure for displaying investments and loans in the enterprise's balance sheet in accordance with national accounting standards has been considered, namely, investments are reflected in assets, bank loans – in liabilities. The legal characteristics of investments and loans that affect the adaptability of the enterprise are defined, in particular, the form of investment (real, financial), the subject of investment (domestic, foreign), the duration of using a bank loan (long-term, short-term), the credit history of the borrower, the presence collateral, its value and availability of insurance contracts. It is proven that taking into account the selected characteristics will allow the business entity to conduct a flexible investment and credit policy and effectively adapt to changes in the internal and external environment.

FORMATION OF A QUALITY CREDIT PORTFOLIO OF UKRAINIAN BANKS: STATE AND STRUCTURE OF THE CREDIT PORTFOLIO OF PRIVATBANK JSC BY DIFFERENT SECTORS OF THE ECONOMY

The purpose of the article is to consider the state and structure of the credit portfolio of JSC CB "PrivatBank" in various sectors of the economy. Analyzing the financial indicators, it has been proven that one of the priority directions in the activities of this Bank is the development of lending while maintaining the high quality of the loan portfolio. The Bank's strategic goal is to build a high-quality credit portfolio of retail and SME loans.As a result of the research, an analysis of the main analytical indicators of credit portfolio management was carried out, the structure of the credit portfolio and the structure of the credit quality of the bank's portfolio were determined during 2019–2021. The practical activities of JSC CB "PrivatBank" were studied and it was established that large loans granted to large enterprises mean big risks for the bank and its millions of depositors. But adhering to this balanced credit policy, the Bank still manages to increase its own credit activity, as evidenced by analytical calculations.To achieve the goal, the research used general scientific research methods: observation (systematic study of the bank, obtaining primary information in the form of financial reporting indicators for the analyzed period), comparison (comparison of the analyzed parameters, coefficients, balance sheet items with each other or with a basic indicator, normative value), abstraction (departure in the definition of categories from non-essential properties and selection of several essential characteristics), grouping method (when considering the classification of loans); various methods of statistical methods, in particular comparison - when comparing actual data for the relevant periods; observations were used to study and assess the financial condition of JSC CB "PrivatBank", methods of analysis and synthesis, induction and deduction.It has been analyzed and proven that the decline in business activity since the beginning of the full-scale war has led to a drop in business demand for loans. At the same time, the deterioration of macroeconomic expectations significantly reduced the risk appetite of banks. Accordingly, financial institutions have tightened lending standards for businesses. Therefore, the growth of the loan portfolio almost stopped: the amount of foreign currency loans decreased, while hryvnia loans increased several times slower than last year, and the hryvnia net corporate loan portfolio increased by 8% since the beginning of the full-scale war.Ways to solve the problems of improving and improving the quality of the bank's credit activity remain prospects for further research

Saddlepoint Approximations for Credit Portfolios With Stochastic Recoveries

Saddlepoint Approximations for Credit Portfolios With Stochastic Recoveries

Estimating correlation parameters in credit portfolio models under time-varying and nonhomogeneous default probabilities

Estimating correlation parameters in credit portfolio models under time-varying and nonhomogeneous default probabilities

Procjena profitabilnosti banke u evroizovanim ekonomijama

Financial euroization is a significant phenomenon in developing countries. The key financial institutions for macroeconomic stability in these countries are the banks. Conversion of most of the financial assets and liabilities into foreign currency creates a currency mismatch between the assets and liabilities in domestic and foreign currency. Banks in the role of intermediaries between depositors and borrowers face the risks of accepting foreign currency deposits and placing foreign currency loans. With this, financial euroization can impact the performance of banks. The paper's main objective is to analyze the impacts of euroization on the performance of banks in North Macedonia, Serbia, and Bosnia and Herzegovina for the period from 2010 to 2020. For performance measure, we use bank profitability. The paper uses a pre-set empirical model, in which the dependent variable is ROA (annual data for the return on assets - as a variable for measuring the profitability of banks) and a set of independent variables, including the degree of euroization. The results suggest that the model is robust, and the variables are statistically significant. In conclusion, this outcome can be ascribed to the segmentation of the bank credit portfolio in credit denominated in domestic versus foreign currency credit denomination. Moreover, the degree of euroization proved to be statistically significant for predicting the performance of banks, hence is high bank management decision-making information.

A New and Efficient Fourier Method for Risk Quantification and Allocation of Credit Portfolios

A New and Efficient Fourier Method for Risk Quantification and Allocation of Credit Portfolios

Does an Increase in Bank Credit Portfolios Push Them Towards Being More Environmentally Friendly?

Does an Increase in Bank Credit Portfolios Push Them Towards Being More Environmentally Friendly?

Research on Credit Portfolio Evaluation of Metaverse Listed Companies Based on the Fuzzy Borda Method

To objectively evaluate the credit level of Metaverse listed companies, this paper constructs a credit evaluation index system for Metaverse listed companies from five aspects: profitability, solvency, growth ability, operational ability, and the ability to introduce technological innovation, and select 12 listed companies in 2021. Based on the relevant financial data of Metaverse listed companies, based on the multi-criteria decision-making problem Fermat's fuzzy TOPSIS method and the hesitant fuzzy language PROMETHEE multi-attribute decision-making method, the credit levels of 12 Metaverse listed companies were calculated respectively, and then the fuzzy Borda method was used to compare the two. The evaluation results of a single method are combined to obtain a combined evaluation result. Compared with the single method, the combined evaluation results have higher confidence. The final results show that GoerTek, Longli Technology, Changxin Technology, and Xinguodu 4 listed companies in the Metaverse are ranked high and have good credit levels. From the perspective of banks, they can be given priority when choosing to issue loans.

Modeling path-dependent state transitions by a recurrent neural network

<abstract> <p>Rating transition models are widely used for credit risk evaluation. It is not uncommon that a time-homogeneous Markov rating migration model will deteriorate quickly after projecting repeatedly for a few periods. This is because the time-homogeneous Markov condition is generally not satisfied. For a credit portfolio, the rating transition is usually path-dependent. In this paper, we propose a recurrent neural network (RNN) model for modeling path-dependent rating migration. An RNN is a type of artificial neural network where connections between nodes form a directed graph along a temporal sequence. There are neurons for input and output at each time period. The model is informed by the past behaviors for a loan along the path. Information learned from previous periods propagates to future periods. The experiments show that this RNN model is robust.</p> </abstract>

INTERNATIONAL FINANCIAL REPORTING STANDARDS AS A TOOL FOR REGULATORY SUPPORT OF OPERATIONS WITH THE LOAN PORTFOLIO OF UKRAINIAN BANKS

The article analyzes the problem of application of information-analytical and regulatory support of operations with the credit portfolio of the Bank, which is currently relevant and Central to successful lending, and therefore to ensure the return of loans and increase the profitability of credit operations. The necessity of forming an effective and efficient system of information-analytical and legal support of operations with the credit portfolio of commercial banks, the main tool of which is the international financial reporting standards, is revealed. It is determined that the requirements of the modern level of globalization are still ahead of the adoption of integration changes regarding the rules and principles of accounting and management accounting by commercial banks of Ukraine. A universal, effective and efficient system of legal regulation of operations with the credit portfolio of a commercial Bank is built on the basis of the study. It is proved that the regulation of operations with the credit portfolio of a commercial Bank can be schematically represented as a hierarchical scheme with 4 levels, where International accounting standards and International financial reporting standards represent the main first level. It was revealed that according to the international financial reporting standards, loans provided by banks belong to the category of financial assets, which are one of the types of financial instruments. The other three levels of the system of legal regulation of operations with the credit portfolio of a commercial Bank, which are derived from the first level, are analyzed. It is concluded that for a more effective organization of accounting it is necessary to harmonize the Ukrainian legislation in accordance with the requirements of International financial reporting standards, and therefore commercial banks with the help of such a system of analytical indicators will be able to constantly monitor changes in the economic system and respond in a timely manner by making appropriate adjustments in case of unsatisfactory developments

Efficiency and productivity of the Brazilian banks: A new approach based on two-stage network DEA

This article creates a conceptual model, called a network system, to represent the Brazilian banking production system, based on its internal operational processes. The first, called the intermediation process, measures a bank's efficiency in extending loans from its available resources. The second, called the revenue process, measures a bank's efficiency in earning profit, mainly from loans granted. We adopt a two-stage DEA model. In the first stage, a relational network DEA model measures both the network system efficiency scores and internal processes. This technique, associated with the Malmquist Index, assesses performance changes over time. In the second stage, these efficiency scores are considered dependent variables, such that Tobit models can determine how the Brazilian credit market's characteristics can explain the network system and internal processes' efficiency. Results show not only a growing trend toward greater efficiency in the revenue process, but also an increase in productivity accompanied by a decline in the intermediation process technology. Given the high banking spreads in Brazil, these results indicate deterioration in the quality of the credit portfolio and the prospect of future insolvency. We discuss implications of this scenario for domestic banks and collateral policy.

Analysis of credit portfolio of commercial banks of Ukraine in modern conditions

The paper defines that the loan portfolio can be formed by several types that depend on the purpose of the bank. The portfolio type is a portfolio characteristic based on the ratio of profit and risk. The main types of loan portfolio are specified by the authors. There are three stages that determine the process of forming a loan portfolio by the bank. The purpose of the paper is to study the concept of "loan portfolio" and justify the complementary components of the concept, which makes it possible to formulate a complex definition. It is justified that the loan portfolio is an instrument that allows you to manage the active operations of the bank, which are aimed at increasing the profitability, efficiency of activities achieved by providing loans in various areas of lending, taking into account the requirements of the credit policy of the bank and banking supervision bodies. The tendencies of changes in the banking sector due to the existing economic situation in Ukraine caused by the COVID-19 pandemic are investigated.

Development of an Impairment Point in Time Probability of Default Model for Revolving Retail Credit Products: South African Case Study

A new methodology to derive IFRS 9 PiT PDs is proposed. The methodology first derives a PiT term structure with accompanying segmented term structures. Secondly, the calibration of credit scores using the Lorenz curve approach is used to create account-specific PD term structures. The PiT term structures are derived by using empirical information based on the most recent default information and account risk characteristics prior to default. Different PiT PD term structures are developed to capture the structurally different default risk patterns for different pools of accounts using segmentation. To quantify what a materially different term structure constitutes, three tests are proposed. Account specific PiT PDs are derived through the Lorenz curve calibration using the latest default experience and credit scores. The proposed methodology is illustrated on an actual dataset, using a revolving retail credit portfolio from a South African bank. The main advantages of the proposed methodology include the use of well-understood methods (e.g., Lorenz curve calibration, scorecards, term structure modelling) in the banking industry. Further, the inclusion of re-default events in the proposed IFRS 9 PD methodology will simplify the development of the accompanying IFRS 9 LGD model due to the reduced complexity for the modelling of cure cases. Moreover, attrition effects are naturally included in the PD term structures and no longer require a separate model. Lastly, the PD term structure is based on months since observation, and therefore the arrears cycle could be investigated as a possible segmentation.

Probabilistic Calibration and Genetic Algorithm-based Bank Credit Strategies for MSMEs and Enlightenment to Tobacco Enterprise Management

Objectives: To further strengthen the role of Micro, Small and Medium Enterprises (MSMEs) in maintaining the vitality of national economy, governments around the world introduced many special policies. They kept guiding the banking industry to increase the support for MSMEs and reduce their financing difficulties in banks. Basing on the analysis of the bank's credit strategy for small and medium-sized enterprises of similar size, this paper gives the management strategy for small and medium-sized enterprises in tobacco industry to obtain bank credit when they cannot expand their turnover. In this paper, we proposed a binary classification model-based probabilistic calibration algorithm to calculate the default probability of enterprises in the formation of risk measurement model, and found the optimal solution of credit strategy using an improved genetic algorithm. Firstly, we discovered the enterprise’s information and invoice data of 123 micro and medium-sized enterprises with existing credit ratings. We extracted several features from multiple perspectives, such as size, relationship in supply chain, profitability, performance ability, and level of development, and removed the correlations among the indicators using principal component analysis (PCA). Secondly, the retained principal components were used as covariates, and we determined the credit ratings of the firms and the probability of default using discrete variables such as the credit ratings of the firms and whether they defaulted. Finally, we substituted the probability of default into the credit risk model to calculate the loss expectation and profit expectation of the credit portfolio, and used the profit expectation of the credit portfolio as the objective function of the 0-1 programming equation to derive the credit strategy with the lowest risk exposure and the highest return basing on the genetic algorithm.