Credit Risk Evaluation Research Articles

Research on finance Credit Risk Quantification Model Based on Machine Learning Algorithm

Machine learning is a branch of artificial intelligence (AI) technology that enables systems to learn and make predictions and decisions without the need for explicit programming. Machine learning algorithms learn patterns and relationships from data and are able to gradually improve their accuracy.This paper mainly introduces the application of deep learning in financial academia and the financial industry, with a particular focus on the application of machine learning and deep learning in financial quantitative trading. The paper mentions the complexity and challenges of financial markets and the difficulties machine learning faces in processing financial time series data, such as overfitting, non-stationarity, heteroscedasticity and autocorrelation. To overcome these challenges, the paper explores machine learning model design in financial quantitative trading and risk prediction, including data transformation and model construction. In the related work part, it introduces the history and development of quantitative investment, as well as the application of quantitative investment, such as high-frequency trading, arbitrage strategy and commodity trading advisory strategy. It then focuses on the application of machine learning in financial quantification, including the use of supervised and unsupervised learning in stock price forecasting and trading strategy generation. The paper also compares traditional quantitative strategies with machine learning strategies and discusses the advantages of machine learning in solving high-dimensional and non-linear problems. The methodology section introduces the application of the random forest model in financial quantification, including the model principle, feature importance calculation and experimental design. Through the pre-processing, feature selection and model construction of the credit risk prediction dataset, the construction and evaluation process of the random forest model is demonstrated. Finally, the performance of the random forest model is evaluated and compared with other models to demonstrate its advantages and applicability in financial quantification.

Research on financing countermeasures of online game SMEs based on the identification of intangible assets information.

As an important part of the cultural industry, small and medium-sized online game enterprises undertake the functions of technological innovation, employment absorption and cultural cultivation. However, the lack of credit ability restricts the financial development of such enterprises. To solve the financing problem of online small and medium-sized game enterprises, this paper firstly uses the information of intangible assets to identify their credit ability, and considers that the information of intangible assets is a problem worthy of attention in evaluating credit risk. Secondly, the intangible assets information disclosure index, the revenue sharing contract of credit synergy and the dynamic game mechanism are constructed to study the importance of the intangible assets index and the evolution of the dynamic game. Finally, the empirical study shows that the intangible assets of delisting and special treated online game small and medium-sized enterprises still have value, this type of enterprise and credit suppliers have the behavior of seeking advantages and avoiding disadvantages. Therefore, credit synergy should be constructed and government regulation should be implemented.

Research on Credit Risk Prediction Method of Blockchain Applied to Supply Chain Finance

INTRODUCTION: From the perspective of blockchain, it establishes a credit risk evaluation index system for supply chain finance applicable to blockchain, constructs an accurate credit risk prediction model, and provides a reliable guarantee for the research of credit risk in supply chain finance.OBJECTIVES: To address the inefficiency of the current credit risk prediction and evaluation model for supply chain finance.METHODS: This paper proposes a combined blockchain supply chain financial credit risk prediction and evaluation method based on kernel principal component analysis and intelligent optimisation algorithm to improve Deep Echo State Network. Firstly, the evaluation system is constructed by describing the supply chain financial credit risk prediction and evaluation problem based on blockchain technology, analysing the evaluation indexes, and constructing the evaluation system; then, the parameters of DeepESN network are optimized by combining the kernel principal component analysis method with the JSO algorithm to construct the credit risk prediction and evaluation model of supply chain finance; finally, the effectiveness, robustness, and real-time performance of the proposed method are verified by simulation experiment analysis.RESULTS: The results show that the proposed method improves the prediction efficiency of the prediction model.CONCLUSION: The problems of insufficient scientific construction of index system and poor efficiency of risk prediction model of B2B E-commerce transaction size prediction method are effectively solved.

Enhanced group decision-making through an intelligent algorithmic approach for multiple-attribute credit evaluation with 2-tuple linguistic neutrosophic sets

With the development of the internet economy, e-commerce has rapidly risen, and a large number of small and micro e-commerce enterprises have emerged. However, these enterprises have low financial information transparency, small scale, and high development uncertainty. Therefore, combining the characteristics of the internet economy, it is of great significance to dynamically evaluate credit risk. This not only helps to enhance the quality and rationality of credit risk evaluation results, but also helps to improve financing efficiency and reduce financing risks. The credit evaluation for small and micro enterprises is a multiple-attribute group decision-making (MAGDM). Recently, the TODIM (an acronym in Portuguese of interactive and multicriteria decision making) and TOPSIS method has been inaugurated to cope with MAGDM issues. The 2-tuple linguistic neutrosophic sets (2TLNSs) are inaugurated as an effective tool for characterizing uncertain information during the credit evaluation for small and micro enterprises. In this paper, the 2-tuple linguistic neutrosophic TODIM-TOPSIS (2TLNN-TODIM-TOPSIS) method is inaugurated to solve the MAGDM under 2TLNSs. Finally, a numerical case study for credit evaluation for small and micro enterprises is inaugurated to confirm the proposed method. The prime contribution of this paper are outlined: (1) The information entropy based on score function and accuracy function are built on the 2TLNSs to obtain weight information; (2) an integrated the 2-tuple linguistic neutrosophic TODIM-TOPSIS (2TLNN-TODIM-TOPSIS) method is established to cope with MAGDM; (3) An illustrative example for credit evaluation for small and micro enterprises has accomplished to illustrate the 2TLNN-TODIM-TOPSIS; (4) some comparative analysis are employed to verify the 2TLNN-TODIM-TOPSIS method.

Robust integration of blockchain and explainable federated learning for automated credit scoring

This article examines the integration of blockchain, eXplainable Artificial Intelligence (XAI), especially in the context of federated learning, for credit scoring in financial sectors to improve the credit assessment process. Research shows that integration of these cutting-edge technologies is in its infancy, specifically in the areas of embracing broader data, model verification, behavioural reliability and model explainability for intelligent credit assessment. The conventional credit risk assessment process utilises historical application data. However, reliable and dynamic transactional customer data are necessary for robust credit risk evaluation in practice. Therefore, this research proposes a framework for integrating blockchain and XAI to enable automated credit decisions. The main focus is on effectively integrating multi-party, privacy-preserving decentralised learning models with blockchain technology to provide reliability, transparency, and explainability. The proposed framework can be a foundation for integrating technological solutions while ensuring model verification, behavioural reliability, and model explainability for intelligent credit assessment.

A Comprehensive Review of the Significance of Low-code Automation in Risk Management for Banks

This study provides a comprehensive examination of the influence of low-code development platforms in the risk management area within the banking sector. This research delves into the tactical utilization of low-code automation in the realm of risk management, with a particular emphasis on compliance monitoring, fraud detection, credit risk evaluation, and operational risk management. Additionally, the study centers on the metamorphosis of software design, development, and deployment processes, made possible by the easy accessibility of low-code platforms. The objective of the study is to illustrate how the digitization and automation of manual tasks in these domains augment service. provision, expedite the identification of compliance violations, and simplify credit risk evaluation, thereby conferring advantages to both banks and their clientele. Through meticulous analysis, this investigation seeks to furnish important perspectives on the uptake and influence of low-code development platforms in the banking sector, illuminating the potential for improved operational efficiency, regulatory adherence, and superior risk management.

The influence of ESG performance on credit risk and financial distress: an empirical study on Taiwan corporate sustainability

ABSTRACT The United Nations has urged global corporations to integrate environmental, social, and governance (ESG) metrics into their operational standards. Reflecting the worldwide shift towards sustainable development, the Taiwanese government has initiated a serious of programmes to highlight corporate adherence to ESG principles, implementing a range of policies aimed at fostering corporate sustainability. This research delved into the potential of enhancing ESG performance, rooted in the ethos of sustainable management, to mitigate credit risk and circumvent financial instability. The findings suggest that, with the exception of carbon emissions and water consumption, enhancements in the majority of ESG performance indicators can mitigate credit risk and financial instability. Furthermore, companies exhibiting strong ESG performance tend to receive favourable credit risk ratings and avoid financial instability. Additionally, the study underscores the advantages of ESG performance in bolstering competitiveness and motivating companies to progress towards sustainable development objectives. As a result, governmental bodies ought to establish a robust framework for ESG indicators and regulatory protocols. The insights gleaned from this study can offer valuable guidance to business entities and stakeholders in their decision-making processes.

Research on Credit Risk Evaluation In Commercial Banks In China

Credit loans of Chinese commercial banks have been increasing; however, the risk of loan default is also rising rapidly, and Chinese commercial banks have been paying more and more attention to the management of credit risk, and that leads to the commercial banks’ exploration of the credit risk evaluation. Moreover, data mining and mathematical statistics techniques are applied in credit rating, risk monitoring, and prediction of customer default risk.

Accuracy Comparison between Five Machine Learning Algorithms for Financial Risk Evaluation

An accurate prediction of loan default is crucial in credit risk evaluation. A slight deviation from true accuracy can often cause financial losses to lending institutes. This study describes the non-parametric approach that compares five different machine learning classifiers combined with a focus on sufficiently large datasets. It presents the findings on various standard performance measures such as accuracy, precision, recall and F1 scores in addition to Receiver Operating Curve-Area Under Curve (ROC-AUC). In this study, various data pre-processing techniques including normalization and standardization, imputation of missing values and the handling of imbalanced data using SMOTE will be discussed and implemented. Also, the study examines the use of hyper-parameters in various classifiers. During the model construction phase, various pipelines feed data to the five machine learning classifiers, and the performance results obtained from the five machine learning classifiers are based on sampling with SMOTE or hyper-parameters versus without SMOTE and hyper-parameters. Each classifier is compared to another in terms of accuracy during training and prediction phase based on out-of-sample data. The 2 data sets used for this experiment contain 1000 and 30,000 observations, respectively, of which the training/testing ratio is 80:20. The comparative results show that random forest outperforms the other four classifiers both in training and actual prediction.

Development of a credit risk evaluation system using multilayer neural networks

This paper deals with the development of a credit risk assessment system using multilayer neural networks. The main objective of this work is to provide a decision support tool for risk assessment, considering relevant variables in the process. To achieve this objective, the backpropagation algorithm and the Adam optimizer were used to train the model. In terms of materials and methods, a training and validation data set including relevant financial information of credit applicants was used. A multilayer neural network was implemented that made predictions and calculated the loss using the categorical cross-entropy function. The results obtained during the development of the system showed a favorable performance and a satisfactory level of accuracy in identifying and classifying different levels of credit risk. However, it is emphasized that the system does not provide absolute results; human intervention is recommended as a last resort for decision making

Enhanced group decision-making through an intelligent algorithmic approach for multiple-attribute credit evaluation with 2-tuple linguistic neutrosophic sets

With the development of the internet economy, e-commerce has rapidly risen, and a large number of small and micro e-commerce enterprises have emerged. However, these enterprises have low financial information transparency, small scale, and high development uncertainty. Therefore, combining the characteristics of the internet economy, it is of great significance to dynamically evaluate credit risk. This not only helps to enhance the quality and rationality of credit risk evaluation results, but also helps to improve financing efficiency and reduce financing risks. The credit evaluation for small and micro enterprises is a multiple-attribute group decision-making (MAGDM). Recently, the TODIM (an acronym in Portuguese of interactive and multicriteria decision making) and TOPSIS method has been inaugurated to cope with MAGDM issues. The 2-tuple linguistic neutrosophic sets (2TLNSs) are inaugurated as an effective tool for characterizing uncertain information during the credit evaluation for small and micro enterprises. In this paper, the 2-tuple linguistic neutrosophic TODIM-TOPSIS (2TLNN-TODIM-TOPSIS) method is inaugurated to solve the MAGDM under 2TLNSs. Finally, a numerical case study for credit evaluation for small and micro enterprises is inaugurated to confirm the proposed method. The prime contribution of this paper are outlined: (1) The information entropy based on score function and accuracy function are built on the 2TLNSs to obtain weight information; (2) an integrated the 2-tuple linguistic neutrosophic TODIM-TOPSIS (2TLNN-TODIM-TOPSIS) method is established to cope with MAGDM; (3) An illustrative example for credit evaluation for small and micro enterprises has accomplished to illustrate the 2TLNN-TODIM-TOPSIS; (4) some comparative analysis are employed to verify the 2TLNN-TODIM-TOPSIS method.

Combining Feature Selection and Classification Using LASSO-Based MCO Classifier for Credit Risk Evaluation

Combining Feature Selection and Classification Using LASSO-Based MCO Classifier for Credit Risk Evaluation

Credit Risk Evaluation of Real Estate Industry Based on GA-GARCH-KMV Model

Credit risk assessment in the real estate industry has garnered significant attention from government regulators, investors, and business scholars. However, the evaluation of credit risk in this sector poses numerous challenges, primarily due to the intricate interplay of economic cycles and political landscapes. In this study, we propose a novel method that leverages the GARCH(1,1) model in conjunction with the Genetic Algorithm (GA) to enhance the KMV model's performance. By refining the default point and equity value volatility in the KMV model, our approach offers more accurate credit risk evaluations in the real estate industry. Empirical results demonstrate the superior accuracy of our improved KMV model, providing valuable insights for early credit risk warning in the real estate sector.

Key indicators for the credit risk evaluation of clients and their changing characteristics

Key indicators for the credit risk evaluation of clients and their changing characteristics

A novel profit-based validity index approach for feature selection in credit risk prediction

<abstract> <p>Establishing a reasonable and effective feature system is the basis of credit risk early warning. Whether the system design is appropriate directly determines the accuracy of the credit risk evaluation results. In this paper, we proposed a feature system through a validity index with maximum discrimination and commercial banks' loan profit maximization. First, the first objective function is the minimum validity index constructed by the intra-class, between-class, and partition coefficients. The maximum difference between the right income and wrong cost is taken as the second objective function to obtain the optimal feature combination. Second, the feature weights are obtained by calculating the change in profit after deleting each feature with replacement to the sum of all change values. An empirical analysis of 3, 425 listed companies from <italic>t</italic>-1 to <italic>t</italic>-5 time windows reveals that five groups of feature systems selected from 614 features can distinguish between defaults and non-defaults. Compared with 14 other models, it is found that the feature systems can provide at least five years' prediction and enable financial institutions to obtain the maximum profit.</p> </abstract>

Understanding Credit Risk in Internet Consumer Finance: An Empirical Analysis with a Focus on the Young Generation

In recent years, internet finance has garnered increasing attention from the public. Online lending, emerging within the framework of Internet finance as a pivotal component, has witnessed substantial growth. While online credit, within the realm of Internet finance, presents numerous advantages over traditional lending, it concurrently exposes a plethora of credit risk issues. This study aims to facilitate the effective utilization of online credit tools by the young generation within the context of Internet finance. Additionally, it seeks to ensure the overall stability of the Internet finance environment and mitigate risks for the youth. Given the significance of understanding credit risk management for college students in the age of internet finance, this paper adopts the logistic model to evaluate credit risk in internet consumer finance and provides pertinent recommendations from the perspective of the young generation.

Depicting Risk Profile over Time: A Novel Multiperiod Loan Default Prediction Approach

With the rapid development of fintech, the need for dynamic credit risk evaluation is becoming increasingly important. While previous studies on credit scoring have mostly focused on single-period loan default prediction, we call for a new avenue—multiperiod default prediction (MPDP)—to depict risk profiles over time. To address the challenges raised by MPDP, such as monotonic default probability prediction and complex relationship accommodation, we propose a novel approach, hybrid and collective scoring (HACS). We design a hybrid modeling strategy to predict whether and when a borrower will default separately through a default discrimination model and a default time estimation model, respectively, and synthesize them through a probabilistic framework. To accommodate various possible patterns of default time and measure the distribution of default probability over successive time intervals, we propose a joint default modeling method to train the default time estimation model. Empirical evaluations at the model (time-to-default prediction performance and discrimination performance) and mechanism (identifiability and discriminability) levels, as well as impact analyses at the application (granting performance and profitability performance) level, show that HACS outperforms the benchmarked survival analysis and multilabel learning methods on all fronts. It can more accurately predict time-to-default and provide financial institutions and investors better decision-support in granting loans and selecting loan portfolios.

Penerapan Fitur Seleksi dan Particle Swarm Optimization pada Algoritma Support Vector Machine untuk Analisis Credit Scoring

After the Covid-19 pandemic, the banking sector faced significant challenges in contributing to achieving national goals in terms of increasing living standards and equalizing the regional economy. Hundreds of millions of low-income people have no credit or bank accounts because they do not have sufficient credit history to warrant the credit scores assigned to them. An estimated 1.7 billion people (31% of the adult population) do not have an account with a financial institution. People today are usually concentrated in developing countries, especially in China 204 million, India 357 million and Indonesia 102 million people. Because it is very difficult to make accurate predictions in determining credit worthiness for low-income people. Cooperatives are financial institutions that have a crucial role in channeling financing to members and the community to develop their businesses. An inappropriate credit distribution process can have a negative effect on KSP, resulting in frequent losses. This risk is known as problem loans, the cause is the KSP's failure to analyze the credit of prospective debtors. Therefore, calculations are needed to detect opportunities for credit risk default by prospective debtors objectively and precisely so that loan problems do not occur. Credit scoring is a method used to evaluate credit risk in terms of loan applications from consumers [4]. In this research we will provide a solution using classification techniques with feature selection methods in the Particle Swarm Optimization (PSO) Algorithm and Support Vector Machine (SVM) to predict the credit risk of prospective debtors failing to make loan payments. The application of the SVM algorithm in credit scoring research is because SVM is good at data classification. However, the standard SVM model still does not produce optimal results due to the difficulty of determining the best parameters, therefore researchers will optimize it with the Feature Selection and PSO algorithms to determine the best parameters. The results from the combination of several parameters using PSO-SVM obtained an accuracy of 87.23%, therefore the application of this method was proven to improve the performance of the SVM algorithm to increase its accuracy results in predicting the feasibility of granting credit.

Relationship of the rating of the companies with the forecast error of market analysts

This study sought to assess the existence of a relationship between the rating and the earnings forecast error of market analysts. The sample relates to 44 companies for the period from 2010 to 2018, which was selected from the data collected onthe Thomson Reuters® platform, in the I/B/E/S database. The methodology chosen was panel data analysis. The results showed that the rating impacts the level of analysts’ forecast error, so companies with better credit risk rating have lowererror in their earnings forecasts. The study contributes to the literature on capital market, specifically that of analysts’ forecasts, focusing on the rating variable as an important factor to be considered by market analysts and contributes to the literature on the predictive quality of accounting information.

A Review of Alternative Data in Credit Risk

With the increasing number of loans given to people who previously have no credit history, the current credit risk prediction models trained by conventional data, namely credit history, social capital, etc., have become less effective. The aim of this essay is to figure out how alternative data is used in credit risk evaluation from those published essays. Based on EBSCO and ScienceDirect serving as the main database sources, we filter out 24 most relevant essays. We conclude that the alternative data can considerably optimize the verdict risk prediction models, as well as solve current financing conundrum when it comes to using alternative data to train the prediction models. However, the quality of alternative data and its ethical issues should require further investigations.