• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.51-60
• /
• 2023

This study focuses on the design of a GPT-based system for relatively rapid technology credit assessment of SMEs. This system addresses the limitations of traditional time-consuming evaluation methods and proposes a GPT-based model to comprehensively evaluate the technological capabilities of SMEs. This model fine-tunes the GPT model to perform fast technical credit assessment on SME-specific text data. Also, It presents a system that automates technical credit evaluation of SMEs using GPT and LLM-based chatbot technology. This system relatively shortens the time required for technology credit evaluation of small and medium-sized enterprises compared to existing methods. This model quickly assesses the reliability of the technology in terms of usability of the base model.

• The Journal of Industrial Distribution & Business
• /
• v.13 no.10
• /
• pp.1-8
• /
• 2022

Purpose: Support vector machines (SVMs) ensemble has been proposed to improve classification performance of Credit risk recently. However, currently used fusion strategies do not evaluate the importance degree of the output of individual component SVM classifier when combining the component predictions to the final decision. To deal with this problem, this paper designs a support vector machines (SVMs) ensemble method based on fuzzy integral, which aggregates the outputs of separate component SVMs with importance of each component SVM. Research design, data, and methodology: This paper designs a personal credit risk evaluation index system including 16 indicators and discusses a support vector machines (SVMs) ensemble method based on fuzzy integral for designing a credit risk assessment system to discriminate good creditors from bad ones. This paper randomly selects 1500 sample data of personal loan customers of a commercial bank in China 2015-2020 for simulation experiments. Results: By comparing the experimental result SVMs ensemble with the single SVM, the neural network ensemble, the proposed method outperforms the single SVM, and neural network ensemble in terms of classification accuracy. Conclusions: The results show that the method proposed in this paper has higher classification accuracy than other classification methods, which confirms the feasibility and effectiveness of this method.

• Journal of Information Technology Applications and Management
• /
• v.14 no.2
• /
• pp.151-168
• /
• 2007

The corporate credit rating represents an assessment of the relative level of risk associated with the timely payments required by the debt obligation. In this study, the corporate credit rating model employs artificial intelligence methods including Neural Network (NN) and Case-Based Reasoning (CBR). At first we suggest three classification models, as partitioned neural networks, all of which convert multi-group classification problems into two group classification ones: Ordinal Pairwise Partitioning (OPP) model, binary classification model and simple classification model. The experimental results show that the partitioned NN outperformed the conventional NN. In addition, we put to use CBR that is widely used recently as a problem-solving and learning tool both in academic and business areas. With an advantage of the easiness in model design compared to a NN model, the CBR model proves itself to have good classification capability through the highest hit ratio in the corporate credit rating.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.1
• /
• pp.873-880
• /
• 2021

The purpose of this study is to investigate the impact of internal control on credit risk of joint stock commercial banks in Vietnam from 2007 to 2018. Furthermore, we specify bank-specific characteristics and macroeconomic conditions, and analyze how these factors affect credit risk of banks: the number of board members, the number of board members with banking or finance background as ratio of total board members, loans to total assets ratio, loans to deposit ratio, the number of days between the year-end and the publication of the financial statements, and the use of top four auditing firms proxy for five elements of internal control. By using the dataset of 30 Vietnamese joint stock commercial banks and Bayesian linear regression via Random-walk Metropolis Hastings algorithm, the results of this study show that five elements of internal control have a impact on bank credit risk, namely, control environment, risk assessment, control activities, information and communication, and monitoring activities. For factors of banks' characteristics, bank size and financial leverage have a negative impact on banks' credit risk, and bank age has a positive effect. For macroeconomic factors, inflation has a positive impact and economic growth has a negative impact on banks' credit risk.

• Nuclear Engineering and Technology
• /
• v.50 no.1
• /
• pp.18-24
• /
• 2018

This study proposes a new method of analyzing the burnup credit in boiling water reactor spent fuel assemblies against various operating parameters. The operating parameters under investigation include fuel temperature, axial burnup profile, axial moderator density profile, and control blade usage. In particular, the effects of variations in one and two operating parameters on the curve of effective multiplication factor ($k_{eff}$) versus burnup (B) are, respectively, the so-called single and compound effects. All the calculations were performed using SCALE 6.1 together with the Evaluated Nuclear Data Files, part B (ENDF/B)-VII238-neutron energy group data library. Furthermore, two geometrical models were established based on the General Electric (GE)14 $10{\times}10$ boiling water reactor fuel assembly and the Generic Burnup-Credit (GBC)-68 storage cask. The results revealed that the curves of $k_{eff}$ versus B, due to single and compound effects, can be approximated using a first degree polynomial of B. However, the reactivity deviation (or changes of $k_{eff}$, ${\Delta}k$) in some compound effects was not a summation of the all ${\Delta}k$ resulting from the two associated single effects. This phenomenon is undesirable because it may to some extent affect the precise assessment of burnup credit. In this study, a general formula was thus proposed to express the curves of $k_{eff}$ versus B for both single and compound effects.

• The Journal of Asian Finance, Economics and Business
• /
• v.5 no.4
• /
• pp.9-20
• /
• 2018

Global rating agencies, such as Moody's and S&P, have assigned credit ratings to corporate bonds issued by Japanese firms since 1980s. Local Japanese rating agencies, such as R&I and JCR, have more market share than the global raters. We examine the yield spreads of 1,050 yen-denominated corporate bonds issued by financial firms in Japan from 1998 to 2014 and find no evidence that bonds rated by at least one global agency are associated with a significant reduction in the cost of debt as compared to those rated by only local rating agencies. Unlike non-financial firms, the reputation effect of global rating agencies does not exist for Japanese financial firms. We also observe that firms with less information asymmetry are more likely to acquire ratings from Moody's or S&P. Additionally, the firm's financial profile does not affect its choice to seek out ratings from global raters. Our findings are contradictory to those by Han, Pagano, and Shin (2012), who employ bonds issued by non-financial firms in Japan. Our conjecture is that the asymmetric nature of financial firms makes investors less likely to depend on a credit risk assessment by rating agencies in determining the yields of new bonds.

• Korean Journal of Construction Engineering and Management
• /
• v.16 no.6
• /
• pp.84-91
• /
• 2015

Project Financing (PF) is a financing method, executed based upon the projected profitability from a project itself instead of relying on the credit rating of project sponsors or any type of collateral. However, most financial institutions of Korea lacks the long term profitability assessment capability, and they prefer to acquire credit reinforcement from the construction companies in the form of the guarantor or debt argument commitments. As a result, PF contingent liabilities as an indirect debt, are burdened to the construction companies. Even though the PF contingent liabilities are not supposed to be part of the financial statements, they became a mandatory disclosure items since 2009. In this study, PF contingent liabilities were studied to indicate how they were correlated with construction firms' financial ratios. Construction firms were grouped by their credit rating and each group was compared in order to analyze PF contingent liabilities' impact on the financial condition of the company in terms of liquidity, liability, and stability.

• Journal of Korean Home Economics Education Association
• /
• v.33 no.2
• /
• pp.1-25
• /
• 2021

The purpose of this paper is to explore ways to prepare for the high school credit system in the home economics educational community through the case of high school credit system research school operation. To this end, the operation process of H high school in Gangwon-do, which operated a high school credit system in 2019, was monitored for 5 months, and surveys and interviews were conducted with students, parents, and teachers to determine the operation of the curriculum. Suggestions based on the case of H high school's operation of the high school credit system for home economics educational community are as follows. Home economics teachers should make active efforts to provide attractive and meaningful home economics lessons to their students by improving instruction and assessment, and implementing a variety of elective courses within the subject of home economics, including collaborative online curricula. Home economics teacher communities and related associations should build a solid network that connects local home economics subject research groups, share information related to curriculum operation, and use it as a channel for disseminating class research results. Home economics teacher training institutions should innovate the curriculum to help prospective teachers develop the ability to guide multiple classes in line with the changing teacher training policy, and develop and provide high-quality online and offline programs for field teacher re-education.

• Journal of Korea Technology Innovation Society
• /
• v.20 no.2
• /
• pp.292-312
• /
• 2017

The purposes of this research are to verify: first, if the technology appraisal model reflects the company's management performance and the rates of bankruptcy and overdue; second, if the existing classification system of technology levels is suitable; and third, which is the most important appraisal factor that defines the classification system of technology levels. As a result of the analysis, financial performance (stability) and non-financial performance (technology environment) proved to be significant variables in explaining technology ratings. According to the verification of the suitability of classification system, it appeared that there is a significant difference in all appraisal items of all groups. The result of neural networks model verification indicates that the most important variable was the R&D capacity, the second variables which determine the suitability of technology financing were indicators related to the company management. The second variables which determine a company's technological excellence were a company's technological base. To summarize, the technology appraisal model not only reflects both managerial performance and risks of a company, but also anticipates the future by converging the management competence and technological competitiveness into R&D capacity. This implies that if the 'forward-looking' technology appraisal model is integrated into the existing, credit rating model, the appraisal model may have positive impact on improving anticipation and stability.

• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.71-78
• /
• 2019

This study aims to identify good borrowers within the context of P2P lending. P2P lending is a growing platform that allows individuals to lend and borrow money from each other. Inherent in any loans is credit risk of borrowers and needs to be considered before any lending. Specifically in the context of P2P lending, traditional models fall short and thus this study aimed to rectify this as well as explore the problem of class imbalances seen within credit risk data sets. This study implemented an over-sampling technique known as Synthetic Minority Over-sampling Technique (SMOTE). To test our approach, we implemented five benchmarking classifiers such as support vector machines, logistic regression, k-nearest neighbor, random forest, and deep neural network. The data sample used was retrieved from the publicly available LendingClub dataset. The proposed SMOTE revealed significantly improved results in comparison with the benchmarking classifiers. These results should help actors engaged within P2P lending to make better informed decisions when selecting potential borrowers eliminating the higher risks present in P2P lending.