Search

Copyright of Journal of Economic Administrative & Legal Sciences is the property of Arab Journal of Sciences & Research Publishing (AJSRP) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This article provides an overview of modern machine learning methods in the context of their active use in credit scoring, with particular attention to the following algorithms: light gradient boosting machine (LGBM) classifier, logistic regression (LR), linear discriminant analysis (LDA), decision tree (DT) classifier, gradient boosting classifier and extreme gradient boosting (XGB) classifier. Each of the methods mentioned is subject to careful analysis to evaluate their applicability and effectiveness in predicting credit risk. The article examines the advantages and limitations of each method, identifying their impact on the accuracy and reliability of borrower creditworthiness assessments. Current trends in machine learning and credit scoring are also covered, warning of challenges and discussing prospects. The analysis highlights the significant contributions of methods such as LGBM classifier, LR, LDA, DT classifier, gradient boosting classifier and XGB classifier to the development of modern credit scoring practices, highlighting their potential for improving the accuracy and reliability of borrower creditworthiness forecasts in the financial services industry. Additionally, the article discusses the importance of careful selection of machine learning models and the need to continually update methodology in light of the rapidly changing nature of the financial market. [ABSTRACT FROM AUTHOR]

The activities of the leading international credit rating agencies Standard&Poor’s (S&P), Moody’s and Fitch, peculiarities of their work and existing differences have been considered. The relevance of the study lies in the comparative characterization of the listed agencies in the current conditions of the anti-Russian sanctions expansion and their strengthening after the beginning of the special military operation in Ukraine. The purpose of the study is to compare the activities of the world’s leading rating agencies S&P, Moody’s and Fitch in modern conditions. The subject of the study is the peculiarities of these agencies’ activities and changes that have occurred in the conditions of the anti-Russian sanctions. To achieve the set goal the following tasks have been set: the leading credit rating agencies’ activities analysis, comparison of their methodological approaches and the scales used to assess the credit rating of countries. The conclusions about the place and important role of international credit rating agencies in the modern world financial system, differences in the assessments made by the agencies, the specific attitude of S&P, Moody’s and Fitch to the credit rating of Russia in the current conditions of the anti-Russian sanctions expansion and the special military operation have been presented.

Introduction. The impact of multidirectional external macroeconomic and regional factors of the economic environment in conditions of uncertainty and increased risks causes significant difficulties in diagnosing, assessing and forecasting the creditworthiness of financial and credit support recipients and borrowers (micro, small and medium-sized enterprises) in the Russian Federation. Theoretical analysis. The author systematized the basic mathematical methods and models for assessing and forecasting the level of creditworthiness of micro, small and medium-sized businesses in foreign and Russian practice, using modern systems and technologies of artificial intelligence and machine learning methods. Empirical analysis. The author proposed the results of approbation of methodological approach for express diagnostics of the financial and economic condition and forecasting the creditworthiness of SMEs in the Krasnodar krai for the period of 2014–2017, based on expert assessment methods, economic analysis and fuzzy logic systems, which form the credit rating of SMEs considering their industry affiliation. Results. In this study, the author has determined the advantages and disadvantages of methods and models for diagnosing creditworthiness and credit scoring from the perspective of their application for various categories of SMEs. As it is shown that the most promising and mathematically reliable models for credit scoring and risk assessment of financial support and lending to various enterprises in the SME sector at different stages of their life cycle both in Russia and abroad are computerized models and expert systems, based on such methods and technologies of Artificial Intelligence, as fuzzy logic systems, artificial neural networks, support vector machines, ensemble methods (random forest method), as well as intelligent information systems, hybrid models and hybrid systems. The study reveals that their combination with each other will allow to achieve synergistic and system effects in the interaction between lenders and borrowers (SMEs) and timely avoid their bankruptcy.

Lower-income consumers who seek to increase their perceived social status or to emulate their wealthier peers may be motivated to purchase conspicuous luxury goods. Using a vehicle financing dataset, we find that non-prime consumers value vehicle prestige more than the average consumer. The stronger preferences for prestige lead non-prime consumers to purchase more expensive vehicles than they otherwise would. The preferences for prestige are driven both by status signaling and peer emulation motives. Furthermore, we show that larger vehicle purchases financed by auto loans lead to worse loan performance and credit standing for non-prime consumers. [ABSTRACT FROM AUTHOR]

As iii many other areas of financial consumer law, the European Court of Justice heralds a strong protective approach to the financier's duty to assess the creditworthiness of the consumer. But enhancing deterrence above all by means of contract law does not set afair and efficient balance between the quite diverse incentives of both parties in adjusting to the policy. [ABSTRACT FROM AUTHOR]

This study examines the existing credit rating methodology proposed in the literature to explore the development of a new credit rating model based on the financial variables of the enterprise. The focus is on the period after the financial crisis of 2018. This study aims to develop a credit rating model using neural networking and tests the same for its accuracy. The goal of this study is to address the issue brought up by previous research on subjectivity in the data used to determine creditworthiness. The database for the study includes financial data up to July 2022 from December 2018. A model is created to assess an enterprise's creditworthiness using neural networking. This study first evaluated the existing credit rating models proposed in the literature. Next, based on financial data and neural networking, a model is developed. It was evident that the model developed in this study has an accuracy of 85.16% and 76.47% on train and test data respectively. There exist several models to determine the creditworthiness of borrowers but all failed to address the concern of subjectivity in the data. The model created in this study made use of cutting-edge technology such as neural networking and financial data. This paper's unique approach and model construction based on a comparison of existing models is rare in the literature and justify the originality of this paper with a practical value at the global level.

This study examines the existing credit rating methodology proposed in the literature to explore the development of a new credit rating model based on the financial variables of the enterprise. The focus is on the period after the financial crisis of 2018. This study aims to develop a credit rating model using neural networking and tests the same for its accuracy. The goal of this study is to address the issue brought up by previous research on subjectivity in the data used to determine creditworthiness. The database for the study includes financial data up to July 2022 from December 2018. A model is created to assess an enterprise's creditworthiness using neural networking. This study first evaluated the existing credit rating models proposed in the literature. Next, based on financial data and neural networking, a model is developed. It was evident that the model developed in this study has an accuracy of 85.16% and 76.47% on train and test data respectively. There exist several models to determine the creditworthiness of borrowers but all failed to address the concern of subjectivity in the data. The model created in this study made use of cutting-edge technology such as neural networking and financial data. This paper's unique approach and model construction based on a comparison of existing models is rare in the literature and justify the originality of this paper with a practical value at the global level. [ABSTRACT FROM AUTHOR]

Nowadays, due to the worldwide crisis, there is a necessity to predict and make a prognosis for the future development of the companies from the view of their financial health. Mainly mining organizations in Slovakia face a problem with creditworthiness when a number of companies declared bankruptcy. The paper has the ambition to predict development in chosen Slovakian mining organization through the most used bankruptcy and bonity models, which brings results, serving for comparing with companies in time and sector. The results were evaluated according to the individual areas of financial position that influenced the development the most. Such results are profitable for the sustainable development of mining organizations together with providing the energetic independence of the countries. [ABSTRACT FROM AUTHOR]

This project focuses on automating the credit card application assessment process using advanced machine learning techniques, including Random Forest, Gradient Boosting, SVMs, Logistic Regression, Regularization Methods, and Hyperparameter Tuning. The objective is to improve the efficiency, accuracy, and fairness of credit card approval decisions. Historical credit card application data, comprising applicant demographics, financial history, and employment details, is collected and pre-processed. Feature engineering and exploratory data analysis (EDA) enhance the dataset’s predictive power. Three machine learning algorithms, Random Forest, Logistic Regression, and Gradient Boosting are applied. Regularization techniques (L1 and L2) and hyperparameter tuning are used to prevent overfitting and optimize model performance. The project assesses model performance by employing metrics such as accuracy, precision, recall, F1-score, and ROC-AUC metrics, and conducts feature importance analysis to identify key factors influencing approval decisions. The project aims to deliver robust, accurate, and fair credit card approval models, benefitting both financial institutions and applicants

This study examines why split bond ratings occur between credit rating agencies with different reputations in Japan. Using a sample of Japanese corporate bonds newly issued during the 2006–2021 period, I find that the ratings assigned by a less reputable Japanese rating agency (JCR) are significantly higher than those by a more reputable Japanese rating agency (R&I) for the same bonds because JCR is likely to rate the creditworthiness of bond issuers more highly than R&I. The disagreement between JCR and R&I over the creditworthiness of issuers causes split bond ratings. Moreover, bonds with multiple split ratings have higher yield spreads. [Display omitted] • This study examines why split ratings occur between rating agencies in Japan. • The ratings assigned by JCR are higher than those by R&I for the same bonds. • JCR rates the creditworthiness of issuers more highly than R&I. • The disagreement about the creditworthiness of issuers causes split ratings. • Bonds with multiple split ratings have higher yield spreads. [ABSTRACT FROM AUTHOR]

• We present a new method to explore the contagion mechanism among the same bank customers. • We detect the presence of critical clients for the propagation of external shocks. • This is useful in improving the information set in assessing customers' creditworthiness. • Our method is based on a weighted, directed complex network. • We employ, as an example, a unique dataset that considers customers' mutual transactions. 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. [ABSTRACT FROM AUTHOR]