Assessment Of Creditworthiness Research Articles

Classification for Dividend Payout in Vietnam Stock Exchange Market: A Comparative Review of Machine Learning Algorithms

This study explores the application of machine learning models to predict dividend payouts for publicly listed companies in the Vietnamese stock market. The authors compared various machine learning algorithms to identify the most suitable one for this task. Based on our evaluation, the test shows that the Random Forest algorithm outperformed other methods in terms of accuracy, F1 score, and time efficiency. Furthermore, we analyzed the feature’s importance to understand the key factors driving dividend payouts. The results can help investors, managers, and government agencies make informed decisions and improve financial market transparency. The study also highlights the potential of using machine learning algorithms to automate and enhance the credit rating process, leading to more accurate and real-time assessments of business creditworthiness in Vietnam.

Strategi Penyelesaian Pembiayaan Bermasalah pada Akad Murabahah di Pt Bank Aceh Syariah Cabang Jeuram

This research investigates the strategies for resolving problematic financing in murabahah contracts at PT Bank Aceh Syariah, Jeuram Branch, utilizing a qualitative approach. Primary data was collected through structured interviews and direct observation from February to May 2023. The study's focus includes the main requirements for customers in murabahah contracts, the application of the 5C principle, and methods for resolving problematic financing. The primary informants were the staff of Bank Aceh Syariah, Jeuram Branch, including Mr. Muhammad Junaidi, Mr. Nasrusdi, Mr. Teuku Asnawi, and Mr. Zikran Niam. The results indicate that the murabahah financing process requires comprehensive documentation and financial proof from customers. The application of the 5C principle, particularly focusing on the character of prospective customers, is a crucial step in creditworthiness assessment. Strategies for resolving problematic financing include restructuring stages such as rescheduling and reconditioning, as well as a musyawarah approach with customers. The bank also implements preventive and curative strategies, including comprehensive analysis and evaluation by Account Officers. As a final measure, the sale or auction of collateral is adopted as a resolution solution. In conclusion, the strategies applied by Bank Aceh Syariah, Jeuram Branch, in handling problematic financing demonstrate a comprehensive approach aligned with Sharia principles.

Risk transmission, systemic fragility of banks’ interacting customers and credit worthiness assessment

The analysis of monetary flows’ correlation resulting from clients’ mutual transactions is crucial for small/local banks in assessing customers’ creditworthiness. This paper offers a new method based on a complex network (customers are the nodes and their mutual financial flows the links). We detect the presence of vulnerable and dangerous clients within the contagion and propagation of external shocks mechanisms and exploit the informative content of the in- and out-paths of the network, with specific reference to those associated with the geodesic patterns. We test the model over a high-quality dataset referred to 2021. The results might support banks’ customers’ creditworthiness analysis.

Assessing the Scholarly Landscape: A Bibliometric Journey through Credit Rating Agency Research

Credit Rating Agencies play a crucial role in the financial markets by providing independent assessments of borrowers' creditworthiness. Rating agencies give useful information about performance and creditworthiness of companies, which aids in reducing information asymmetry and it serve as a signal for the likelihood of default which allows investors and market participants to make informed decisions . It is considered as powerful institutions capable of influencing bond and stock prices. The credibility of rating agencies has been question due to their role in the 2008 financial crisis. Their credibility may be impacted by a number of reasons. The study reviewed literature added in credit-rating agency domain from January 2004 to October 2023. Bibliometric analysis is used to comprehend the existing literature. The review recouped 237 research articles on Credit Rating Agency from the Scopus database and envisioned the data using VOS viewer software and Biblioshiny from R studio. We found that most of the studies emerged as after-effects of financial crisis reported in 2008. We have provided a feasible research agenda to further explore credit-rating agency domain. The study not only enhanced the understanding of the scholarly landscape within the scope of the study but also provided a comprehensive assessment of the literature.

Cooperative credit banks and sustainability: Towards a social credit scoring

Cooperative Credit Banks (CCBs) play a significant role in fostering social sustainability through lending decisions. In particular, CCBs are interested in supporting socially conscious cooperatives, provided that the credit scoring process classifies them as "credit-worthy". However, existing literature overlooks how cooperatives' balance sheet equilibriums, driven by their social mission rather than profit maximization, impact credit scoring. To bridge this gap, this paper examines the influence of cooperatives’ unique balance sheet equilibriums on credit scoring. Specifically, it investigates the potential risk of sub-optimal creditworthiness assessment when CCBs use a "one-size-fits-all" model for cooperatives and non-cooperatives alike. The findings demonstrate that "tailor-made" credit scoring models for cooperatives and non-cooperatives outperform a generic one, enhancing credit classification specificity and sensitivity. These models allow for more effective credit allocation, resulting in improved economic outcomes.

Mathematical Modeling and Analysis of Credit Scoring Using the LIME Explainer: A Comprehensive Approach

Credit scoring models serve as pivotal instruments for lenders and financial institutions, facilitating the assessment of creditworthiness. Traditional models, while instrumental, grapple with challenges related to efficiency and subjectivity. The advent of machine learning heralds a transformative era, offering data-driven solutions that transcend these limitations. This research delves into a comprehensive analysis of various machine learning algorithms, emphasizing their mathematical underpinnings and their applicability in credit score classification. A comprehensive evaluation is conducted on a range of algorithms, including logistic regression, decision trees, support vector machines, and neural networks, using publicly available credit datasets. Within the research, a unified mathematical framework is introduced, which encompasses preprocessing techniques and critical algorithms such as Particle Swarm Optimization (PSO), the Light Gradient Boosting Model, and Extreme Gradient Boosting (XGB), among others. The focal point of the investigation is the LIME (Local Interpretable Model-agnostic Explanations) explainer. This study offers a comprehensive mathematical model using the LIME explainer, shedding light on its pivotal role in elucidating the intricacies of complex machine learning models. This study’s empirical findings offer compelling evidence of the efficacy of these methodologies in credit scoring, with notable accuracies of 88.84%, 78.30%, and 77.80% for the Australian, German, and South German datasets, respectively. In summation, this research not only amplifies the significance of machine learning in credit scoring but also accentuates the importance of mathematical modeling and the LIME explainer, providing a roadmap for practitioners to navigate the evolving landscape of credit assessment.

Credit support for the development of the transport complex of the national economy and its sectoral differentiation

It was established that the specific weight of bank loans granted to the transport complex of Ukraine in the overall national economy is insignificant - about 3%. The largest share of bank loans in the sectoral portfolio was issued to warehousing and auxiliary activities. The second place is occupied by ground and pipeline transport, the third place is air transport. The share of water transport is negligible. The intensity of the use of loans in foreign currency is the greatest in warehousing and auxiliary activities, much less in aviation, land and pipeline transport. It was established that the share of non-performing loans in the transport complex is quite high, but smaller than in the national economy, in the national currency it is higher compared to the national economy, and in the foreign currency it is much lower. The specific weight of non-performing loans is the largest in warehousing and auxiliary activities, average - in land and pipeline transport, insignificant - in air transport, negligible - in water transport. Analysis of loans to the transport complex in terms of banking institutions made it possible to establish their exponential distribution and high concentration. TOP-3 state-owned banking institutions account for more than half of the value of loans and almost 90% of non-performing loans. TOP-14 banking institutions present almost the entire credit portfolio of the transport complex. It has been proven that one of the reasons for the high level of non-performing loans in the transport complex is the defects in assessing the creditworthiness of borrowers in the industry. Unlike other sections, a separate discriminant model was not built for section H - Transport, warehousing, postal and courier activities. The use of a single aggregated model for the transport complex and twelve other types of economic activity distorts the assessment of the borrower's creditworthiness, since the sectoral conditions of business in them differ significantly. It is proposed to build an individual model of the integral assessment of the borrower's creditworthiness according to section H with differentiation by sub-sectors.

Information acquisition and rating agencies

For decades credit rating agencies were viewed as trusted arbiters of creditworthiness and their ratings as important tools for managing risk. The common narrative is that the value of ratings was compromised by the evolution of the industry to a form where issuers pay for ratings. In this paper we consider both an investor-pays and an issuer-pays set-ups and show that if the investor-pays version can overcome the free-rider problem it is efficient, and otherwise leads to under-provision of information; while if the issuer-pays can force disclosure, it is efficient, but otherwise it leads to less revealing information because of the systematic distortion in revealed information along with over-investment in information. We show that in both these arrangements credit ratings have value in equilibrium and how reputation insures that, in equilibrium, ratings will reflect sound assessments of credit worthiness. We argue that regulatory reliance on ratings and the increasing importance of risk-weighted capital in prudential regulation have more likely contributed to distorted ratings than the matter of who pays for them.

The Effect of Using Financial Information Service System (SLIK) on Bad Credit Rate in Fintech Peer to Peer Lending

The development of Fintech Peer to Peer Lending (P2P Lending) in Indonesia is very rapid in supporting increased financial inclusion. Along with the increase in the value of loans disbursed through P2P Lending, the ratio of bad loans or what is often referred to as Non Performing Loans (NPL) also continues to increase. Literature review article "Can the Use of a Financial Information Service System (SLIK) Affect the Level of Bad Credit in Fintech Peer to Peer Lending?" is a scientific article that aims to build a research hypothesis on how one variable influences other variables. The method used in writing this literature review article uses the library research method. The sources used as material for research are through available data from the website of the Otoritas Jasa Keuangan (OJK) & Asosiasi Fintech Pendanaan Bersama Indonesia (AFPI), academic online media, Google Scholar, Mendeley, and other online media. The results of this study provide information that can be used in efforts to minimize the occurrence of an increase in credit risk (NPL) in the P2P Lending industry, namely by taking preventive steps by making an effective creditworthiness assessment to prospective loan recipients through analysis of credit information data obtained from Sistem Layanan Informasi Keuangan (SLIK). Therefore, as an effort to restrain the rate of increase in the number of bad loans in the P2P Lending industry, a tool is needed to carry out an effective credit scoring (credit scoring) by integrating P2P Lending credit loan data into SLIK so that more credit data of prospective loan recipients can be obtained. comprehensive. More comprehensive data can provide more accurate results on credit scoring, and have a positive impact on loan repayment rates.

IMPROVEMENT OF ASSESSMENT OF CREDITWORTHINESS OF INDIVIDUALS IN COMMERCIAL BANKS OF THE REPUBLIC OF UZBEKISTAN

This article highlights the importance of creditworthiness assessment and scoring system of individuals. The expansion of lending practices to individuals by commercial banks, minimizing the risks associated with this process and preventing the occurrence of problem loans requires improving the creditworthiness of customers. In particular, today's offering of online credit services requires process automation and creditworthiness assessment taking into account all factors.

TSUKAMOTO FUZZY IN OPTIMIZING THE CREDITWORTHINESS ASSESSMENT PROCESS AT SAVINGS AND LOAN COOPERATIVES

Savings and Loan Cooperatives are ones of the non-bank institutions whose business activity is the provision of loan. In its business activities, problems often arise, namely non-performing loans which causes no turnover of funds which leads to losses. One of the causes of non-performing loans is the lack of objective creditworthiness assessment. The purpose of this study is to optimize the process of assessing the feasibility of loan applications at Savings and loan credit with assessment criteria: loan value, total income, loan term and collateral value. The tsukamoto fuzzy method was used in this study. Tsukamoto fuzzy method consists of four steps.: fuzzification, Forming fuzzy rules, application of implication functions using the MIN function and defuzzification using the weighted average calculation method. In this research, it was found that Tsukamoto's fuzzy method can be applied to the creditworthiness assessment process at the Saving and Credit Cooperatives. This is because the accuracy rate of the decision results from the tsukamoto method is 93.75%. A total of 60 data out of 64 data are in accordance with the eligibility decision at one of Saving and loan Cooperatives in West Java, Indonesia. Tsukamoto fuzzy method can optimize the credit assessment process in Savings and loan Cooperatives because the eligibility assessment process becomes more efficient and objective.

The role of credit rating of the ESG debt instruments issuers

The aim of this article is to assess whether having a creditworthiness assessment from more than one credit rating agency by issuers of ESG debt instruments affects the number of issues and the average amount issued. The empirical research was carried out using the observation method and the analysis of source documents. In the analysed period, 53.38% of issuers received ratings at least from one CRAs as S&P, Moody’s, and Fitch. The results of the conducted research indicate that the number of ESG debt instruments and the average issue amount were affected by the number of ratings given to the issuer. A database collected from Refinitiv Eikon for the period between 2012 and 2021 allows us to conclude that it is enough to have two credit ratings. The conclusions of this study can be used in the process of obtaining financing for ESG projects.

Standardizing fairness-evaluation procedures: interdisciplinary insights on machine learning algorithms in creditworthiness assessments for small personal loans

In the current European debate on the regulation of Artificial Intelligence there is a consensus that Artificial Intelligence (AI) systems should be fair. However, the multitude of existing indicators allowing an AI system to be labeled as “(un)fair” and the lack of standardized, application field specific criteria to choose among the various fairness-evaluation methods makes it difficult for potential auditors to arrive at a final, consistent judgment. Focusing on a concrete use case in the application field of finance, the main goal of this paper is to define standardizable minimal ethical requirements for AI fairness-evaluation. For the applied case of creditworthiness assessment for small personal loans, we highlighted specific distributive and procedural fairness issues inherent either to the computing process or to the system’s use in a real-world scenario: (1) the unjustified unequal distribution of predictive outcome; (2) the perpetuation of existing bias and discrimination practices; (3) the lack of transparency concerning the processed data and of an explanation of the algorithmic outcome for credit applicants. We addressed these issues proposing minimal ethical requirements for this specific application field: (1) regularly checking algorithmic outcome through the conditional demographic parity metric; (2) excluding from the group of processed parameters those that could lead to discriminatory outcome; (3) guaranteeing transparency about the processed data, in addition to counterfactual explainability of algorithmic decisions. Defining these minimal ethical requirements represents the main contribution of this paper and a starting point toward standards specifically addressing fairness issues in AI systems for creditworthiness assessments aiming at preventing unfair algorithmic outcomes, in addition to unfair practices related to the use of these systems. As a final result, we indicate the next steps that can be taken to begin the standardization of the three use case-specific fairness requirements we propose.

MODELING SOFTWARE FOR AN EFFECTIVE BANKING SCORING SYSTEM

"The article is devoted to the scoring system of lending in second-tier banks. Namely, a decision-making system in which the integration of two scoring models (banking and insurance) leads to an assessment of the reliability of the borrower and the potential risks of the bank, as well as the use of social networks to determine the riskiness of the client. Bank and insurance scoring is compared. The article includes methodologies, processes and data that are used in the development of credit scoring. The advantages of creditworthiness assessment methodologies are described without using the data of insurance companies. Analytical methods are used, receiving data from social networks. Statistical theory is applied to real situations of credit scoring. The article is useful for working people working in the financial sector. These include credit officers, risk managers and analysts, IT-specialists. IT infrastructure, operating procedures, business processes are being studied. An overview of IT tools for the implementation of the scoring system product is given, which increases the efficiency of the scoring system. Keywords: system, scoring, model, risk, income, borrower, lending."

Credit Rationing Equilibrium Achievement in the Conditions of Digitalization

The author clarified the degree of achievement of the credit market equilibrium in the conditions of information asymmetry and active digitalization of processes in activity of credit market participants. The subject of research is the economic and technological conditions for achieving credit rationing equilibrium. The purpose of the research is to highlight the nature of the impact of digitalization on the degree of achieving equilibrium in the credit market in the context of digitalization. The author focuses on the new conditions of functioning of the credit market, when the current digitalization allows to significantly complement the credit profile of borrowers, and new participants appear in the credit market. The objective of research is assessment of compliance of theoretical postulates on achieving the credit rationing equilibrium in the context of digitalization of processes associated with the lending. The authors’ hypothesis is that the credit market has the potential to increase the return on a loan per currency unit of borrowers’ loans, and the current estimates of the of defaults borrowers’ probability, interest rates are “biased”. As the main methods, the author used systematic and logical methods, which made it possible to consider the credit market equilibrium in terms of the economic relationships between its participants and the achieved economic indicators. As a result of the analysis of theoretical concept of credit rationing equilibrium, taking into account the identified qualitative changes, that take place in the credit market in the context of digitalization. The author concludes that is the potential increase the rate of return on credit operations. Extending the borrower credit data with alternative, non-credit sources, as expected, allows to get more accurate creditworthiness assessment. The results of the research to some extent serve as a rationale for possible decisions of central banks to expand the traditional sources of borrowers’ credit histories, reconfigure the existing information exchange architecture in the credit market.

On the dynamics of credit history and social interaction features, and their impact on creditworthiness assessment performance

For more than a half-century, credit risk management has used credit scoring models at each of the well-defined stages of credit risk management. Application scoring is used to decide whether to grant a loan or not, while behavioral scoring is used mainly for portfolio management and to take preventive actions in case of default signals. In both cases, social network data has recently been shown to be valuable to increase the predictive power of these models, especially when the borrower’s historical data is scarce or not available. This study aims to understand the dynamics of creditworthiness assessment performance and how it is influenced by credit history, repayment behavior, and social network features. To accomplish this, we build up a machine learning classification framework demonstrating its value analyzing 97,000 individuals and companies from the moment they obtained their first loan up to 12 months afterward. Our original and massive dataset allowed us to characterize each borrower according to its credit behavior, and socioeconomic relationships. Our study finds that credit scoring based on borrowers’ history improves performance at a decreasing rate during the first six months and then stabilizes. The most notable effect on the performance of credit scoring based on social network features occurs in loan applications; for personal scoring, this effect prevails for approximately six months, while for business scoring, social network features add value throughout the entire study period. These findings are of great value to improve credit risk management and optimize the combined use of both the traditionally exploited information and new alternative data sources.

ДОСЛІДЖЕННЯ КЛЮЧОВИХ ЕЛЕМЕНТІВ ПРОЦЕСУ ФОРМУВАННЯ ТА РЕАЛІЗАЦІЇ КРЕДИТОСПРОМОЖНОСТІ ПОЗИЧАЛЬНИКІВ БАНКУ

The article considers issues related to the analysis of approaches to assessing the creditworthiness of bank borrowers. The article analyses various views of scientists and allocates main components of the concept of "creditworthiness", which comprehensively reveal the content of the concept and its main characteristics, both in relation to individuals and legal entities. The article offers a structure of assessment of creditworthiness of clients on the basis of the world and domestic practice, which includes two components: criteria of creditworthiness of a client and methods of assessment of creditworthiness of a client. Based on a comparative analysis of the main 10 foreign models for assessing the creditworthiness of borrowers, it is concluded that the indicators of "borrower's reputation" and "ability to repay the loan" are present in a larger number of models. The article considers foreign and domestic methods of assessing the borrower's creditworthiness and concludes that they have both common and distinctive features, but there is no single ideal method among them that would be suitable for a larger number of banking institutions. It is shown that there is a need to select instruments that will reflect the risks of potential losses. By determining the optimal system for assessing the borrower's creditworthiness, the bank reduces the risks of loan default and, in the future, bankruptcy of the institution. It is determined that the methods used in the practice of domestic banks generally assess financial indicators, but there is a gap in the use of qualitative characteristics in assessing the borrower's activities that do not have a quantitative expression, which are considered in detail in foreign methods for assessing the creditworthiness of a supplier. To make such an assessment, banking institutions need to pay attention to the analysis of the external environment, which will help in determining credit risks. It is the combination of qualitative and quantitative indicators that will help banks conduct a comprehensive multifactorial analysis and minimise credit risk. Therefore, based on the recommendations of the National Bank of Ukraine, each banking institution should choose an acceptable methodology or system for analysing and assessing creditworthiness in order to ensure the correctness of this assessment. It is concluded that there is currently no single methodology for assessing the creditworthiness of borrowers.

FEATURES OF ASSESSING THE CREDIT CAPACITY OF BUILDING COMPLEX ENTERPRISES

The article defines the risks of crediting the construction complex and further developed the methodology for assessing the creditworthiness of construction enterprises, taking into account the specifics of construction projects. The main purpose of the study is to identify the peculiarities of lending in the construction industry and to detail the available creditworthiness assessment methods, taking into account the specifics of the functioning of the construction organization and the characteristics of construction projects.
 The systematization of literary sources and approaches to solving this problem showed that in the works of domestic and foreign scientists, many methodological approaches to assessing the creditworthiness of enterprises have been developed, in banking practice, a methodology for assessing the creditworthiness of the borrower has been developed, which takes into account the type of economic activity and the size of the enterprise. However, the existing methods of assessing the creditworthiness of the enterprise, which include a system of generalized indicators of the financial condition, need to be detailed taking into account the specifics of the functioning of the construction organization and the characteristics of construction projects.
 The urgency of solving this scientific problem lies in the fact that in the conditions of modern challenges of an unstable economy, the problem of assessing and managing the creditworthiness of construction enterprises remains a priority both for creditor banks and for the developers themselves. The study of the problem was carried out in the following logical sequence: first, the financial indicators of the enterprises of the construction complex in Ukraine were analyzed; the specific features of construction production were identified and the corresponding risks of lending to this sector of the economy were outlined; modern methods of assessing the creditworthiness of economic entities, which form quantitative and qualitative approaches to assessing the creditworthiness of the enterprise, are given; their advantages are determined; a system of indicators for assessing the creditworthiness of builders is proposed, which includes five blocks of indicators: an assessment of the current financial condition of the builder, an expert assessment of the construction project, an assessment of the business reputation of the construction company, an analysis of the adequacy of the provision, a description of the construction industry in the region.
 The methodological tools of the research were: systematic approach, methods of analysis and synthesis, logical generalization, comparison, etc. Enterprises of the construction complex of Ukraine were chosen as the object of the study, and the indicators of their creditworthiness were the subject.
 The results of the study can be used when assessing the creditworthiness of developers by their management and banks. The application of the proposed approach will increase the efficiency of crediting decisions, reduce banking risks and contribute to the effective development of the construction industry

Corporate social responsibility disclosure and corporate creditworthiness: Evidence from the UK

AbstractThis study investigates the way in which corporate social responsibility (CSR) practices are perceived by the U.K. bond market. In this respect, we distinguish between the two ambiguous subdimensions – that is, CSR disclosure and CSR performance. We analysed the association between CSR disclosure and the cost of corporate bonds by means of a multi‐theoretical framework combining economics with social theories. We also examine the moderating effect of the CSR performance on this relationship. We estimate a random‐effects GLS regression and random‐effects ordered probit regression using a sample of companies belonging to the FTSE 100 index during the 2013–2017 period. We find that bondholders and credit rating agencies incorporate CSR disclosure into their assessment and evaluation of the firms' creditworthiness. Mainly, our results show that bondholders encourage and value CSR reporting primarily for companies with weak CSR performance, but stop doing so once the company reach a certain level of CSR performance. We further examined each CSR disclosure subdimension and aspects of corporate creditworthiness through a disaggregated analysis. Both environmental and community relations disclosures are significant in corporate creditworthiness, whereas only responsibility disclosure is related to credit ratings. Finally, results highlight that disclosure of CSR information is especially relevant to financially healthy firms. Our findings have several implications for academics, practitioners, and policymakers in understanding the consequences of CSR disclosure and CSR performance on bond markets and credit rating.

On the combination of graph data for assessing thin-file borrowers’ creditworthiness

Thin-file borrowers are customers for whom a creditworthiness assessment is uncertain due to their lack of credit history. To address missing credit information, many researchers have used borrowers’ social interactions as an alternative data source. Exploiting social networking data has traditionally been achieved by hand-crafted feature engineering, but lately, graph neural networks have emerged as a promising alternative. Here we introduce an information-processing framework to improve credit scoring models by blending several methods of graph representation learning: feature engineering, graph embeddings, and graph neural networks. In this approach, we aggregate the methods’ outputs to be fed to a gradient boosting classifier to produce a final creditworthiness score. We have validated this framework over a unique multi-source dataset that characterizes the relationships, interactions, and credit history for the entire population of a Latin American country, applying it to credit risk models, application, and behavior. It also allows us to study both individuals and companies. Our results show that the methods of graph representation learning should be used as complements; they should not be seen as self-sufficient methods, as it is currently done. We improve the creditworthiness assessment performance in terms of the measures of Area Under the ROC Curve (AUC) and Kolmogorov–Smirnov (KS), outperforming traditional methods of exploiting social interaction data. In the area of corporate lending, where the potential gain is much higher, our results confirm that the evaluation of a thin-file company cannot solely consider the company’s own characteristics. The business ecosystem in which these companies interact with their owners, suppliers, customers, and other companies provides novel knowledge that enables financial institutions to enhance their creditworthiness assessment. Our results let us know when and on which population to use graph data and the expected effects on performance. They also show the enormous value of graph data on the credit scoring problem for thin-file borrowers, mainly to help companies with thin or no credit history to enter the financial system.