Credit Evaluation System Research Articles

Research on Credit Evaluation of Financial Enterprises Based on the Genetic Backpropagation Neural Network

In this paper, an improved neural network enterprise credit rating model, which is grounded on a genetic algorithm, is suggested. With the characteristics of self-adaptiveness and self-learning, the genetic algorithm is utilized to adjust and enhance the thresholds and weights of the neural network connections. The potential problems of the backpropagation (BP) neural network with slothful speed of convergence and the possibility of falling into the local minimum point are solved to a convinced degree using the genetic algorithm in combination. The hybrid technique of the genetic BP neural network is applied to a credit rating system. Using commercial banks’ datasets, our experimental evaluations suggest that, using a combination of the BP neural network and the genetic algorithm, the proposed model has high accuracy in enterprise credit rating and has good application value. Moreover, the proposed model is approximately 15.9% more accurate than the classical BP neural network approach.

Credit Score Prediction System using Deep Learning and K-Means Algorithms

In financial markets, credit rating and risk assessment tools are used to minimize potential risk up to some extent for credit score. Nowadays, the banking and financial industry has experienced rapid expansion. Therefore, with this growth, the numbers of credit card applications with various credit products are increasing day by day because many people want to avail these services for their personal interest. The challenge here is to identify insights on the performance of a finance industry by using deep learning algorithms as they directly affect the viability of that industry. These industries have a limited number of resources and capital, which can be used to deliver the services among the customers. In this research work, we proposed prediction of credit scoring system using deep learning and K-Means algorithm for the financial industry. The scheme contains a predictive model which uses feature selection (FS) classification and deep learning applications simultaneously to train the proposed model to perform effectively. The scheme 1) pre-processing credit card data 2) uses a feature selection technique to minimize the dimension of data in order to obtain the finest training data 3) applies a deep learning algorithm to map the input weight with hidden biases to achieve excellent performance 4) Decision support system is used to enable the deep learning algorithm to provide a more accurate and intelligent decision. Furthermore, the proposed model is validated on different credit scoring dataset in real-world scenarios and is capable of improving the effectiveness and accuracy. The studies indicate that our predictive model performs well for credit scoring of existing customer and helps lenders to allocate funds in finance industry.

Developing a multi-criteria sustainable credit score system using fuzzy BWM and fuzzy TOPSIS

Developing a multi-criteria sustainable credit score system using fuzzy BWM and fuzzy TOPSIS

Empirical Evidence of Faulty Credit Scoring and Business Failure in P2P Lending

Purpose: This study attempts to identify the cause of the failure of a platform operator in a P2P lending market, from the perspective of the internal credit rating system. Design/methodology/approach: Data from Moneyauction, the first P2P lending platform in Korea, which led the market for a while and then unexpectedly closed down, was analyzed using a series of binary logistic regression and relative weight analysis methods. The study concentrates on the effect and importance of the self-assessed credit score system used by Moneyauction with regard to investor funding decisions and the actual repayment performance outcomes of borrowers. The predictive power of this self-assessed credit score is also identified. Findings: The findings show that while the internal credit score is considered the most important factor in an investor s funding decision, its importance with regard to a borrower s actual repayment performance is significantly lower compared to other factors. Specifically, the predictability when using a model with an internal credit score with regard to a borrower’s repayment performance is inferior to a model without this factor. The findings therefore suggest that low-quality self-assessed credit rating systems may in fact contribute to the failure of individual platforms, even when the market is growing rapidly. Research limitations/implications: A series of business failures in a P2P market in the early stages of growth could make it difficult for the market to grow as a promising means of alternative finance due to the mounting distrust of potential participants and the exodus of existing investors. Therefore, the results of this study may present important issues to be discussed in relation to healthy market growth. The findings of this study are from the special case of Moneyauction in Korea. Thus, there is a limit to generalizing the results in this study, and further research is needed on additional platforms in similar situations in different markets. Originality/value: None of the previous studies on P2P lending markets has investigated individual platform failure cases. Existing studies mainly focus on the statistical significance of the effects of borrower characteristics on investors decisions or borrowers repayment performances. This study is also distinct in terms of its methodology in that it goes one step further and discusses the relative importance among all aspects of the borrowers characteristics.

Chinese social credit system: key features and possibility of using in Ukraine

The article considers the key features of the social credit (rating) system implementation and functioning, which is the main tool for digitalization of Chinese society, and in the future is considered by the Chinese authorities as a basic mechanism of electronic government. The historical retrospective of the phenomenon of social rating emergence and development, which was later transformed into social credit, is presented. Attention is paid to the differences in the implementation and functioning of the social credit system, depending on regional characteristics. The participants in the social credit system and the main mechanisms for collecting information for the social credit level formation, including through the mandatory use of specially designed ID-cards, and recently the almost widespread use of the verification for a person by face, have been determined. Despite the position of the Chinese authorities, according to which the use of the social credit system is successful, a list of shortcomings that are now inherent in this system, both of an author’s and of an expert nature, is given. The practice of implementation the state digital eco-environment «Diia» (State and I), which is a key tool for building a digital state, as well as the functional content of the «Diia» eco-environment (service) and its main components, is analyzed. The basic shortcomings that are now inherent in the service are determined, in particular, the key tool in the fight against coronavirus – «Diia. Vdoma», as well as the controversial character of the proposed innovation for the business environment «Diia. City». The features of the declared novel of the relationship between the citizen and state ‒ the concept of «paperless», are studied. The issue of regulation of the «Diia» eco-environment functioning is raised in the context of the legislative introduction of the concept of «paperless» announced on September 1, 2021. The conclusion is substantiated that the basic mechanisms are already being introduced in Ukraine, which form the basis for the Chinese social credit system functioning, in particular, through the tools of citizensʼ verification. On the basis of the analysis carried out, proposals are made to improve the functionality of the «Diia» eco-environment.

Modelling a sustainable credit score system (SCSS) using BWM and fuzzy TOPSIS

ABSTRACT Sustainable development has emerged as a critical agenda for all organisations around the world. Despite the fact that profitability and sustainability are inorganically linked to financial institutions, sustainable lending has been a constant focus of attention. Due to regulatory pressure and stakeholder concerns, financial institutions are forced to implement a variety of sustainable measures; they are also gradually thinking to give more support to socially impactful and sustainable projects. Financial institutions can play a major role in establishing sustainable development by adopting the green lending policy. However, there have been few studies on sustainability credit score systems (SCSS) that take into account social and environmental factors. To fill the gaps of existing literature, this study proposes a multi-criteria SCSS that takes into account the environment and social aspects in addition to financial and managerial aspects. A combined Best-Worst Method (BWM) and the fuzzy-Technique for Order Preferences by Similarity to an Ideal Solution (TOPSIS) method are used in this study to create a credit scoring system. The BWM is used to determine the weight of factors, and the fuzzy-TOPSIS is used to evaluate applicants. The ambiguity while evaluating borrowers has been captured by applying fuzzy set theory. A real-life case study is used to demonstrate the efficacy of the proposed model. The model is unique in terms of the number of social and environmental factors considered. This research will assist financial institutions in identifying borrowers who engage in sustainable business practices. Borrowers can be holistically prioritised by applying the model.

Credit evaluation method of generating companies considering the market behavior in China electricity market

AbstractSince the reformation of the electricity market of China is increasing and the modernization of the national governance system is being promoted, the electricity market management system needs to be gradually improved. Credit evaluation is an essential part of the electricity market management system. Therefore, a complete credit evaluation system plays a fundamental role in ensuring that the electricity market can operate safely, stably, efficiently, and reliably. The traditional credit evaluation methods focus on the financial situation and credit records of the generating companies. With the gradual development of the electricity market transactions, the market behavior needs to be included in the credit evaluation indicator system to standardize the behavior of the generating companies and reduce the risks of the market transactions. This study establishes a complete credit evaluation system from three perspectives: market behavior, financial situation, and social responsibility. In addition, to determine the weight of indicators in the credit evaluation, the analytic hierarchy process (AHP) algorithm, fuzzy theory, and the non‐dominated sorted genetic algorithm II (NSGA‐II) algorithm are combined. The variance of the evaluation results and the deviation degree of the indicator weight are considered the objective functions of the NSGA‐II algorithm to optimize the indicator weight. Finally, comparing as an example the results of the credit evaluation before and after the optimization of an electricity market shows that the credit evaluation method can effectively distinguish the generating companies that adopt different market behaviors and has a high practical significance.

The Issue and Risk Analysis of the Credit Card

In order to systematically evaluate credit card risk, opportunities for specific action and activity are used on paper. Based on the rapid development of the local credit card market, the current risks of the application and the issue of the credit card are discussed. With a credit card application using a credit card, a situation may arise where a customer may wish to repay the loan on time. In addition, the credit rating system, marketing and approval method, credit card overpayment, incentive orders and penalties, use management and other related angles are considered to solve the credit card risk problem.

Design and Development of Citizen Surveillance and Social-Credit Information System for Bangladesh

Most of the areas of Bangladesh face a wide range of threats, ranging from terrorism and civil unrest to kidnapping, rape and murder. To reduce the impact of these threats, it is critical for the authorities to capture real-time information onwhat is happening in and around the city. Therefore, there is a growing requirement for utilizing the new and emerging technologies to make our cities safer. The development of the monitoring system in the technological field has become a blazing topic in the milieu of scholars and AI techniques have become an essential part of the future era. With the help of AI & deep learning, we can evaluate the social behavior (Action Recognition) of people, and by implementing the social credit score system, we can mark the citizen’s activities & analyze them. To detect and recognize the actions of a human we used YOLOV2 architecture and also incorporated the SQL database (SQLite) to record the social credit score. A citizen can visualize their credit score from an HTML based website.

Enhanced PD-implied ratings by targeting the credit rating migration matrix

A high-quality and granular probability of default (PD) model is on many practical dimensions far superior to any categorical credit rating system. Business adoption of a PD model, however, needs to factor in the long-established business/regulatory conventions built around letter-based credit ratings. A mapping methodology that converts granular PDs into letter ratings via referencing the historical default experience of some credit rating agency exists in the literature. This paper improves the PD implied rating (PDiR) methodology by targeting the historical credit migration matrix instead of simply default rates. This enhanced PDiR methodology makes it possible to bypass the reliance on arbitrarily extrapolated target default rates for the AAA and AA+ categories, a necessity due to the fact that the historical realized default rates on these two top rating grades are typically zero.

Credit scoring model using MARS method to comply with FSA regulation

Financial Service Authority (FSA) introduced a new policy on Sustainable Finance to financial institutions such as Banks. It is currently a hot issue that needs to be implemented in the selection process of potential debtors. Consequently, the credit rating system needs to be renewed. Statistical methods can help to include permits and environmental impact in the selection process. Thus, this study intends to formulate a credit rating model for productive debtors. This study used a quantitative method using Multivariate Adaptive Regression Splines (MARS). Our study’s significant finding is that the credit rating model for productive debtors that have been formulated has type I error of 0.00% and type II error of 0.54%. Furthermore, the authors believe that this model can be used to asses potential debtors’ credit rating while adhering to the policy of Sustainable Finance.

Rating as an indicator of the quality of a teacher’s professional activity

The article examines several aspects of the quality of educational services. The process of providing such services is examined, the problems in the field of teaching physics and mathematics are identified and the ways of problem resolution in the credit learning system are proposed. The introduction of credit learning technology allows for stimulation of students’ learning activity and an increase in their motivation and the level of academic mobility. The ways of increasing the motivational activity of the teacher as another key figure in the educational process are identified. The current remuneration system for university teachers in Kazakhstan accounts for work experience and the position held and includes additional payments for an academic degree but does not stimulate teachers for continuous additional training. On the other hand, the salary volume does not contribute to the high social prestige of this profession, which is complex and requires genuine pedagogical skills. The quality of teaching staff is associated with the quality of education acquired by students. In the context of the credit rating system, it is not only students who earn credits, but also teachers who should substantiate and improve their qualifications measured by their rating.

A conservative approach for online credit scoring

This research is aimed at the case of credit scoring in risk management and presents a novel machine learning method to be used for the default prediction of high-risk branches or customers. This study uses the Kruskal-Wallis non-parametric statistic to form a conservative credit-scoring model and to study the impact on modeling performance on the benefit of the credit provider. The findings show that the new credit scoring methodology represents a reasonable coefficient of determination and a very low false-negative rate. It is computationally less expensive with high accuracy with around 18% improvement in Recall/Sensitivity. Because of the recent perspective of continued credit/behavior scoring, our study suggests using this credit score for non-traditional data sources for online loan providers to allow them to study and reveal changes in client behavior over time and choose the reliable unbanked customers, based on their application data. This is the first study that develops an online non-parametric credit scoring system, which is able to reselect effective features automatically for continued credit evaluation and weigh them out by their level of contribution with a good diagnostic ability.

A Ensemble Machine Learning Based System for Merchant Credit Risk Detection in Merchant Mcc Misuse

Although credit score models have been widely applied, one of the important variables-Merchant Category Code (MCC)-is sometimes misused. MCC misuse may cause errors in credit scoring systems. The present study aimed to develop and deploy an MCC misuse detection system with ensemble models, gives insights into the development process and compares different machine learning methods. XGBoost exhibited the best performance, with overall error, sensitivity, specificity, F_1 score, AUC and PRAUC of 0.1095, 0.7777, 0.9672, 0.8518, 0.9095 and 0.9090, respectively. MCC misuse by merchants can be predicted with satisfactory accuracy by using our ensemble-based detection system. The paper can thus not only suggest the MCC misuse cannot be overlooked but also help researchers and practitioners to apply new ensemble machine learning based detection system or similar problems.

A new hybrid ensemble model with voting-based outlier detection and balanced sampling for credit scoring

The credit scoring system has been revolutionized with the development of the financial system and has received increasing attention from the academia and industry. Artificial intelligence technology has reshaped credit scoring through predictive classification. In this study, a new hybrid ensemble model with voting-based outlier detection and balanced sampling is proposed to achieve superior predictive power for credit scoring. To avoid noise-filled data from misleading the classifier training, a new voting-based outlier detection method is proposed to enhance the classic outlier detection algorithms with the weighted voting mechanism and boost the outlier scores into the training set to form an outlier-adapted training set. To reduce the information loss caused by under-sampling when dealing with imbalanced data, a new bagging-based balanced sampling method is proposed to enhance the traditional under-sampling methods with the bagging strategy to obtain a balanced training set. To further improve the performance of the proposed model, a stacking-based ensemble modeling method is proposed to first perform parametrical optimization and then construct the stacking-based multi-stage ensemble model. Five datasets from the UC Irvine machine learning repository and five evaluation indicators were adopted to evaluate the model performance. The experimental results indicate the superior performance of the proposed model and prove its robustness and effectiveness.

Construction of Credit Evaluation System for Bidding Platform

Construction of Credit Evaluation System for Bidding Platform

Research on listed companies’ credit ratings, considering classification performance and interpretability

Any credit evaluation system must be able not only to identify defaults, but also to be interpretable and provide reasons for defaults. Therefore, this study uses the correlation coefficient and F-test to select the initial features of a credit evaluation system, and then a validity index for a second selection to ensure that the feature system has the optimum ability to discriminate in determining default status. We omit one feature in each iteration by replacing each feature, calculating the changes in validity index values after deleting this feature and, finally, calculating the ratio of the change value to the sum of all change values. This ratio is then used as the feature’s weight. This study also introduces a data gravity model in predicting defaults, as predicting a validation set’s default status derives the classification threshold to maximize classification accuracy. An empirical analysis of the listed company samples reveals that the feature system selected from 610 features can distinguish between both defaults and nondefaults. Compared with eight other models, our data gravity model not only exhibits good classification performance, but also has interpretability; further, this model can provide at least five-year-ahead forecasting, and can offer a timely risk warning for banks.

An Explanation Framework for Interpretable Credit Scoring

With the recent boosted enthusiasm in Artificial Intelligence (AI) and Financial Technology (FinTech), applications such as credit scoring have gained substantial academic interest. However, despite the evergrowing achievements, the biggest obstacle in most AI systems is their lack of interpretability. This deficiency of transparency limits their application in different domains including credit scoring. Credit scoring systems help financial experts make better decisions regarding whether or not to accept a loan application so that loans with a high probability of default are not accepted. Apart from the noisy and highly imbalanced data challenges faced by such credit scoring models, recent regulations such as the `right to explanation' introduced by the General Data Protection Regulation (GDPR) and the Equal Credit Opportunity Act (ECOA) have added the need for model interpretability to ensure that algorithmic decisions are understandable and coherent. A recently introduced concept is eXplainable AI (XAI), which focuses on making black-box models more interpretable. In this work, we present a credit scoring model that is both accurate and interpretable. For classification, state-of-the-art performance on the Home Equity Line of Credit (HELOC) and Lending Club (LC) Datasets is achieved using the Extreme Gradient Boosting (XGBoost) model. The model is then further enhanced with a 360-degree explanation framework, which provides different explanations (i.e. global, local feature-based and local instance- based) that are required by different people in different situations. Evaluation through the use of functionally-grounded, application-grounded and human-grounded analysis shows that the explanations provided are simple and consistent as well as correct, effective, easy to understand, sufficiently detailed and trustworthy.

Construction and Model Analysis of the Bidirectional E-Business Credit Evaluation System

Construction and Model Analysis of the Bidirectional E-Business Credit Evaluation System

Research on Credit Evaluation of Construction Market EntitiesBased on Conditional Random Field

This paper firstly judges the change of credit level of the credit subject from the dynamic perspective of "state-behavior". Then, according to the conditional random field theory, the data of credit behavior and credit status are taken as random variables in the conditional random field to construct multiple characteristic functions representing the relationship between the credit behavior and the credit status. And finally, the credit evaluation system based on the conditional random field is constructed. In summary, this paper constructs a credit evaluation framework of market entities from the credit evaluation system and conditional random field credit labeling, which can be used in the construction of market credit dynamic supervision for reference.