Search

Micro, Small, and Medium-sized Enterprises (MSMEs) are essential for the growth and development of the country's economy, as they create jobs, generate income, and foster production and innovation. In recent years, credit risk assessment (CRA) has been an essential process used by financial institutions to evaluate the creditworthiness of MSMEs and determine the likelihood of default. Traditionally, CRA has relied on credit scores and financial statements, but with the advent of machine learning (ML) algorithms, lenders have a new tool at their disposal. By and large, ML algorithms are designed to classify borrowers based on their credit history and transactional data while leveraging the entity relationship involved in credit transactions. This study introduces an innovative knowledge graph-driven credit risk assessment model (RGCN-RF) based on the Relational Graph Convolutional Network (RGCN) and Random Forest (RF) algorithm. RGCN is employed to identify topological structures and relationships, which is currently nascent in traditional credit risk assessment methods. RF categorises MSMEs based on the enterprise embedding vector generated from RGCN. Extensive experimentation is conducted to assess model performance utilising the Indian MSMEs database. The balanced accuracy of 92% obtained using the RGCN-RF model demonstrates a considerable advancement over prior techniques in identifying risk-free enterprises. [ABSTRACT FROM AUTHOR]

Modern industrial systems are typically characterised by their multiple elements (technological, communicational, physical, etc.). These elements are interconnected and structured in such a way as to make them "immune" to, or only marginally affected by, any harmful events. On the basis of this assertion, the traditional bimodal definition (which only considers functional and failure states) is inadequate for understanding the behaviour of complex systems. It is in this context that the concept of resilience has caught on in both the academic and corporate fields because it is capable of taking into account all the ways a system may behave following a harmful event, from the so-called "reaction and absorption" of shocks, to recovery and adaptation of the system to new operating conditions. In a previous paper (Ventura in Eur Bus Law Rev 34(2):239–268, 2023) introduced a model set within a wider system of corporate compliance management drawn up in accordance with the NIST and ISO international standards. This model is based on the joint use of Erik Hollnagel's Functional Resonance Analysis Method (FRAM) and Saaty's Analytic Hierarchy Process (AHP). After defining its properties, from a purely methodological viewpoint, the proposed model was then applied to a very common case study in the Italian industrial context: the acquisition of a plant with features making it eligible for tax credit both for Investments in the South and for Industry 4.0. This paper sets out to go further by evaluating the validity of this model also from a cost-benefit analysis point of view. The three possible situations will be analysed (without any risk assessment, risk assessment using the FRAM method, risk assessment using the FRAM/AHP method), establishing which of the three is most useful for corporate management. [ABSTRACT FROM AUTHOR]

Related party transactions (RPTs) can serve as channels for the spread of credit risk events among blockchain firms. However, current credit risk-assessment models typically only consider a firm's individual characteristics, overlooking the impact of related parties in the blockchain. We suggest incorporating RPT network analysis to improve credit risk evaluation. Our approach begins by representing an RPT network using a weighted adjacency matrix. We then apply DANE, a deep network embedding algorithm, to generate condensed vector representations of the firms within the network. These representations are subsequently used as inputs for credit risk-evaluation models to predict the default distance. Following this, we employ SHAP (Shapley Additive Explanations) to analyze how the network information contributes to the prediction. Lastly, this study demonstrates the enhancing effect of using DANE-based integrated features in credit risk assessment. [ABSTRACT FROM AUTHOR]

This paper introduces a novel Dimension Reduction-based Adaptive-to-model Semi-supervised Classification method, specifically designed for scenarios where the number of unlabeled samples significantly exceeds that of labeled samples. Leveraging the strengths of sufficient dimension reduction and non-parametric interpolation, the method significantly amplifies the value derived from unlabeled samples, thus enhancing the precision of the classification model. An iterative version is also presented to extract further insights from the interpolated unlabeled samples. Theoretical analyses and numerical studies demonstrate substantial improvements in classifier accuracy, particularly in the context of model misspecified. The effectiveness of the proposed method in enhancing classification accuracy is further substantiated through two empirical analyses: credit card application evaluations and coronary heart disease diagnostic assessments. [ABSTRACT FROM AUTHOR]

This article is a book review of "Optimizing Project Work Management, and Delivery" by Gary L. Richardson and Brad M. Jackson. The book aims to provide an integrated decision architecture for project management that can be applied to all project types. It discusses various delivery methods, project profiles, project success drivers, and project externals. The book also explores different delivery strategies, such as the classic predictive model, the iterative development model, and the critical chain model. It concludes with a series of success recipes for project managers to follow. The reviewer recommends this book to project managers and program managers in various industries. [Extracted from the article]

Personal credit assessment plays a crucial role in the financial system, which not only relates to the financial activities of individuals but also affects the overall credit system and economic health of society. However, the current problem of data imbalance affecting classification results in the field of personal credit assessment has not been fully solved. In order to solve this problem better, we propose a data-enhanced classification algorithm based on a Pixel Convolutional Neural Network (PixelCNN) and a Generative Adversarial Network (Wasserstein GAN, WGAN). Firstly, the historical data containing borrowers' borrowing information are transformed into grayscale maps; then, data enhancement of default images is performed using the improved PixelCNN-WGAN model; and finally, the expanded image dataset is inputted into the CNN, AlexNet, SqueezeNet, and MobileNetV2 for classification. The results on the real dataset LendingClub show that the data enhancement algorithm designed in this paper improves the accuracy of the four algorithms by 1.548–3.568% compared with the original dataset, which can effectively improve the classification effect of the credit data, and to a certain extent, it provides a new idea for the classification task in the field of personal credit assessment. [ABSTRACT FROM AUTHOR]

Credit risk, stemming from the failure of a contractual party, is a significant variable in financial institutions. Assessing credit risk involves evaluating the creditworthiness of individuals, businesses, or entities to predict the likelihood of defaulting on financial obligations. While financial institutions categorize consumers based on creditworthiness, there is no universally defined set of attributes or indices. This research proposes Range control-based class imbalance and Optimized Granular Elastic Net regression (ROGENet) for feature selection in credit risk assessment. The dataset exhibits severe class imbalance, addressed using Range-Controlled Synthetic Minority Oversampling TEchnique (RCSMOTE). The balanced data undergo Granular Elastic Net regression with hybrid Gazelle sand cat Swarm Optimization (GENGSO) for feature selection. Elastic net, ensuring sparsity and grouping for correlated features, proves beneficial for assessing credit risk. ROGENet provides a detailed perspective on credit risk evaluation, surpassing conventional methods. The oversampling feature selection enhances the accuracy of minority class by 99.4, 99, 98.6 and 97.3%, respectively. [ABSTRACT FROM AUTHOR]

General-purpose financial statements prepared under GAAP are for a consolidated reporting entity--a collection of legal entities that includes the parent and any subsidiaries it controls. This reporting model results in a loss of information about the individual legal entities within the consolidated reporting entity. Our study examines the role of parent-only balance sheet information in assessing the credit risk of the parent when it is a bank holding company. We obtain evidence from three trading platforms: credit default swaps (CDS), outstanding bonds, and new bonds. We find that parent-only leverage is useful for debtholders to assess the parent's credit risk even after considering consolidated leverage. Moreover, in CDS markets, parent-only leverage is more useful for firms without downstream guarantee than for firms with guarantee and is less useful for firms with a stronger internal capital market. Our study raises the awareness of parent-only financial information for credit risk assessments. [ABSTRACT FROM AUTHOR]

This paper responds to Professor Paolo Giudici's call for papers in ‘Safe Machine Learning’ and explores the application of Bayesian inference within the SAFE model framework, aiming to enhance the accuracy and reliability of environmental, social, and governance (ESG) factor analysis in the financial sector. The paper begins by introducing the basic concept of the SAFE model, which integrates ESG factors into the assessment of corporate credit ratings to promote sustainable development in the financial field. Furthermore, this paper discusses forecast estimation, uncertainty quantification, Gaussian processes, iterative optimization, and model robustness within the SAFE model framework. It is important to note that the SAFE model is not limited to the aforementioned applications; it also has the capacity to understand the model's extensive utility in other financial sectors, which can reflect the model's comprehensive scope. [ABSTRACT FROM AUTHOR]

Objective To investigate the differences of protein expressions in the primary tumors, adjacent tissues, and metastatic tumors of gastrointestinal neuroendocrine neoplasms. Methods Nine patients with gastrointestinal neuroendocrine tumors (GI-NENs) with liver metastasis who underwent surgery at the National Cancer Center/Cancer Hospital, Chinese Academy of Medical Sciences from July 2015 to April 2019 were selected. The protein expressions of the primary tissues, liver metastatic tissues, and adjacent tissues were detected by the data independent acquisition (DIA) technology. P<0.05 and | log2FC|>0.5 (FC as the difference multiple) were used as the criteria to identify the differentially expressed proteins in the primary tissues vs adjacent tissues, primary tissues vs liver metastatic tissues, primary tissues with different degrees of differentiation, and liver metastatic tissues with different degrees of differentiation. The differentially expressed proteins were investigated by volcano map analysis, cluster analysis, Gene Ontology (GO) function analysis, and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis. Results Compared with adjacent tissues, 85 proteins were downregulated and 42 proteins were upregulated in the primary tissues of gastric NENs. The differentially expressed proteins were mainly enriched in the biological processes related to the regulation of guanosidase triphosphate activity and the catabolism of deoxyribonucleoside monophosphate, the glycosaminoglycan biosynthesis chondroitin sulfate/dermatan sulfate, pantothenate, and CoA biosynthesis signaling pathways. 114 proteins were downregulated and 155 proteins were upregulated in the primary tissues of intestinal NENs. The differentially expressed proteins were mainly enriched in the biological processes related to glutathione metabolism and sulfur compound metabolism, collecting duct acid secretion, and taurine and hytaurine metabolism signaling pathways. Compared with the primary tissues of neuroendocrine cancers (NECs), 168 proteins were downregulated and 278 proteins were upregulated in G1-2 differentiation primary tissues. The differentially expressed proteins were significantly enriched in biological processes such as DNA metabolism and DNA replication, as well as replication, mismatch repair, and other pathways. Compared with the metastatic tissues of NECs, 95 proteins were downregulated and 97 proteins were upregulated in G1-2 differentiated metastases. The differentially expressed proteins were significantly enriched in the activity and catalytic activity of transcriptional coactivators, base excision repair, and protein efflux pathways. Compared with G1 differentiated primary tissues, 530 proteins were downregulated and 211 proteins were upregulated in G1 differentiated metastatic tissues. Compared with G2 differentiated primary lesions, 53 proteins were downregulated and 96 proteins were upregulated in G2 differentiated metastatic tissues. Compared with the primary lesions of NECs, 109 proteins were downregulated and 92 proteins were upregulated in the metastatic tissues of NECs. In G1 and G2 differentiated GI-NENs, there are many similar signal pathways enriched in differentially expressed proteins between primary lesions and metastases, while only one signal pathway enriched in differentially expressed proteins between primary and metastatic tissues of NECs is the same as that enriched in differentially expressed proteins between primary and metastatic tissues of GI-NENs, which is the drug metabolism signal pathway. The differentially expressed proteins in G1 differentiated primary and metastatic tissues were mainly expressed in cytoplasm (20.26%), mitochondria (18.67%), and nucleus (15.48%). The differentially expressed proteins in the primary and metastatic tissues of G2 differentiation were mainly expressed in the cytoplasm (20.24%), nucleus (18.25%), and cell membrane (15.08%). The differentially expressed proteins in the primary and metastatic tissues of NECs were mainly expressed in the nucleus (23.78%), cytoplasm (22.7%), and cell membrane (11.35%). Conclusion The protein expressions of GI-NENs in the primary tissues, adjacent tissues, and metastatic tissues were significantly different in different sites and degrees of differentiation. [ABSTRACT FROM AUTHOR]

AbstractMany early 19th century economic thinkers have provided ideas to explain the causes of commercial crises, as against the Classical belief on the impossibility of a general disequilibrium between demand and supply. J.S. Mill contributed to this debate suggesting an analysis of money and credit as generators of economic fluctuations and crises. Mill apprehended the significance of the function of money as a store of value and explained cyclical fluctuations based on three interrelated causes: the role of money as credit, the propensity of moneylenders to overexpand their credit and the effect of the general tendency of profits to fall. [ABSTRACT FROM AUTHOR]

Credit risk refers to the possibility of borrower default, and its assessment is crucial for maintaining financial stability. However, the journey of credit risk data generation is often gradual, and machine learning techniques may not be readily applicable for crafting evaluations at the initial stage of the data accumulation process. This article proposes a credit risk modeling methodology, TED-NN, that first constructs an indicator system based on expert experience, assigns initial weights to the indicator system using the Analytic Hierarchy Process, and then constructs a neural network model based on the indicator system to achieve a smooth transition from an empirical model to a data-driven model. TED-NN can automatically adapt to the gradual accumulation of data, which effectively solves the problem of risk modeling and the smooth transition from no to sufficient data. The effectiveness of this methodology is validated through a specific case of credit risk assessment. Experimental results on a real-world dataset demonstrate that, in the absence of data, the performance of TED-NN is equivalent to the AHP and better than untrained neural networks. As the amount of data increases, TED-NN gradually improves and then surpasses the AHP. When there are sufficient data, its performance approaches that of a fully data-driven neural network model. [ABSTRACT FROM AUTHOR]

Traditionally most cross-selling models in retail banking use demographics information and interactions with marketing as input to statistical models or machine learning algorithms to predict whether a customer is willing to purchase a given financial product or not. We overcome with such limitation by building several models that also use several years of account transaction data. The objective of this study is to analysis credit card transactions of customers, in order to come up with a good prediction in cross-selling products. We use deep-learning algorithm to analyze almost 800,000 credit cards transactions. The results show that such unique data contains valuable information on the customers' consumption behavior and it can significantly increase the predictive accuracy of a cross-selling model. In summary, we develop an auto-encoder to extract features from the transaction data and use them as input to a classifier. We demonstrate that such features also have predictive power that enhances the performance of the cross-selling model even further. [ABSTRACT FROM AUTHOR]

This study examines the applications, benefits, challenges, and ethical considerations of artificial intelligence (AI) in the banking and finance sectors. It reviews current AI regulation and governance frameworks to provide insights for stakeholders navigating AI integration. A descriptive analysis based on a literature review of recent research is conducted, exploring AI applications, benefits, challenges, regulations, and relevant theories. This study identifies key trends and suggests future research directions. The major findings include an overview of AI applications, benefits, challenges, and ethical issues in the banking and finance industries. Recommendations are provided to address these challenges and ethical issues, along with examples of existing regulations and strategies for implementing AI governance frameworks within organizations. This paper highlights innovation, regulation, and ethical issues in relation to AI within the banking and finance sectors. Analyzes the previous literature, and suggests strategies for AI governance framework implementation and future research directions. Innovation in the applications of AI integrates with fintech, such as preventing financial crimes, credit risk assessment, customer service, and investment management. These applications improve decision making and enhance the customer experience, particularly in banks. Existing AI regulations and guidelines include those from Hong Kong SAR, the United States, China, the United Kingdom, the European Union, and Singapore. Challenges include data privacy and security, bias and fairness, accountability and transparency, and the skill gap. Therefore, implementing an AI governance framework requires rules and guidelines to address these issues. This paper makes recommendations for policymakers and suggests practical implications in reference to the ASEAN guidelines for AI development at the national and regional levels. Future research directions, a combination of extended UTAUT, change theory, and institutional theory, as well as the critical success factor, can fill the theoretical gap through mixed-method research. In terms of the population gap can be addressed by research undertaken in a nation where fintech services are projected to be less accepted, such as a developing or Islamic country. In summary, this study presents a novel approach using descriptive analysis, offering four main contributions that make this research novel: (1) the applications of AI in the banking and finance industries, (2) the benefits and challenges of AI adoption in these industries, (3) the current AI regulations and governance, and (4) the types of theories relevant for further research. The research findings are expected to contribute to policy and offer practical implications for fintech development in a country. [ABSTRACT FROM AUTHOR]

The widespread usage of machine learning systems and econometric methods in the credit domain has transformed the decision-making process for evaluating loan applications. Automated analysis of credit applications diminishes the subjectivity of the decision-making process. On the other hand, since machine learning is based on past decisions recorded in the financial institutions' datasets, the process very often consolidates existing bias and prejudice against groups defined by race, sex, sexual orientation, and other attributes. Therefore, the interest in identifying, preventing, and mitigating algorithmic discrimination has grown exponentially in many areas, such as Computer Science, Economics, Law, and Social Science. We conducted a comprehensive systematic literature review to understand (1) the research settings, including the discrimination theory foundation, the legal framework, and the applicable fairness metric; (2) the addressed issues and solutions; and (3) the open challenges for potential future research. We explored five sources: ACM Digital Library, Google Scholar, IEEE Digital Library, Springer Link, and Scopus. Following inclusion and exclusion criteria, we selected 78 papers written in English and published between 2017 and 2022. According to the meta-analysis of this literature survey, algorithmic discrimination has been addressed mainly by looking at the CS, Law, and Economics perspectives. There has been great interest in this topic in the financial area, especially the discrimination in providing access to the mortgage market and differential treatment (different fees, number of parcels, and interest rates). Most attention has been devoted to the potential discrimination due to bias in the dataset. Researchers are still only dealing with direct discrimination, addressed by algorithmic fairness, while indirect discrimination (structural discrimination) has not received the same attention. [ABSTRACT FROM AUTHOR]

The complexity of the financial environment and the international community makes the capital flow face various challenges, and it is difficult to obtain accurate credit prediction results in the actual application environment. Considering the complex non-linear characteristics of customer information, the Analytic Hierarchy Process is studied to meet the needs of bank credit risk assessment. On this basis, a depth neural network with different complexities was selected for the three indicators built to classify the features. The composition of the neural network module and the number of neurons were determined by experiment, and Dropout was used to prevent overfitting of the test dataset. Stability and ablation experiments showed that the model can control the error between datasets to 0.021. The ablation experiment showed that the numbers of hidden layers and neurons were the best. Simulation tests showed that the sensitivity and accuracy of this method were 85.25% and 92.55%, respectively, which were superior to other classification methods. The real data of banks in the past four years were tested. The results could accurately classify the risks of enterprises and individual customers, and the results of stress test showed that the model is stable. It is found that traditional credit risk assessment models rely on statistical means and rule decisions, and these methods may not fully reveal the complex non-linear relationship and the internal relationship of financial indicators in high-dimensional data. The combination of deep learning technology and hierarchical analysis can better deal with and explain the complex non-linear problems in bank risk assessment. [ABSTRACT FROM AUTHOR]

The development of a digital social credit system in China has sparked debates around urban governance and citizenship performance. Although China’s social credit system is portrayed as a single technical system, the article offers a new perspective on digital social credit focused on geographical variegation. We analyze how variegation is manifested through use of multiple data streams and a diverse range of aims operationalized in various social credit systems at the municipal level. Social credit can be seen as part of algorithmic urban governance and an instrument of urban citizenship performance through scoring, ranking, incentives, and punishments. Analysis of social credit systems’ development in Chinese cities contributes to debates around the role of the urban Global East and evolution of digital and algorithmic governance in and beyond China. [ABSTRACT FROM AUTHOR]

Against the background of digital development, this study's research object is the platform-based highway transportation supply chain. It also analyzes two modes of supply chain financial credit financing, namely, upstream, and downstream enterprises of the platform, and network freight platform as the main financing body. Notably, the financial provider sets up a transaction credit based on the principle of business truth, and closed-loop transactions, determine the upper limit of the credit line based on the principle of financing self-compensation, build the expected profit maximization model, and establish the optimal credit line. Combined with the Highway Freight Index and Logistics Prosperity Index, the dynamic early warning value is established for the financing mode, where the platform as the main financing body. Through numerical analysis, the credit line and expected profit increase with the transaction credit, expected freight volume, and credit interest rate under the two modes, and the increase deriving from the credit interest rate is more significant. Finally, this paper describes the two-dimensional credit matrix of the financing subject via transaction credit and credit interest rate, which provides an intuitive credit reference for financial institutions to conduct the credit financing of the platform-based highway transportation supply chain. [ABSTRACT FROM AUTHOR]

This research investigates the stability and occurrence of Hopf bifurcation in a credit risk contagion model, which includes distributed delay, using the chain trick method. The model is a generalized version of those previously examined. The model is an expanded version of those previously studied. Comparative analysis showed that unlike earlier models, which only used the nonlinear resistance coefficient to determine the rate of credit risk infection, the credit risk contagion rate is also affected by the weight given to past behaviors of credit risk participants. Therefore, it is recommended to model the transmission of credit risk contagion using dispersed delays. [ABSTRACT FROM AUTHOR]

This study aims to determine the affecting factors of repayment performance in Small Medium Enterprises (SMEs) in Indonesia for individual loan program. The data in this study is gathered by credit active during 2023 which contain of 300 samples from several region in Indonesia that came from one of Non-Banking Financial Institutions (NBFIs). The data is analyzed by logit regression model by Stata software version 18. The study indicates that the borrower’s income and amount of loan disbursements have significantly affected the repayment of the borrower’s outstanding loan for both principal and interest in time. Furthermore, the study shows that the higher amount of loan disbursement might affect the lower probability of defaulting due to high assessment of credit appraisal. Since the loan programs are delivered for individual for owner or management of Small Medium Enterprises (SMEs) in Indonesia. A prudent procedure is needed to establish for newer borrowers of the individual loan programs. The screening process consists of income cash flow analysis and how long the cash flow will be generated for repaying the programs. the novelty for this result enhances the current research for SMEs financing program in Indonesia for individual loan credit program. Specially credit loan program is delivered and sponsored by Indonesia government. Not much research focused on individual loan programs for SME’s owner or management. [ABSTRACT FROM AUTHOR]

Purpose: This study investigates the association between debt overhang and carbon emissions (both direct and indirect emissions) using a sample of US publicly listed firms. Design/methodology/approach: The study applies generalized least squares (GLS) regression analyses to a sample of 2,043 US firm-year observations over a period of 14 years from 2007 to 2020. The methods include contemporaneous effect, lagged effect, alternative measures of carbon emissions and debt overhang, intensive versus non-intensive analysis, channel analysis, firm fixed effects, change analysis, controlling for credit rating analysis, propensity score matching approach, instrumental variable analysis with industry and year fixed effect. Findings: This study's findings reveal that the debt overhang problem increases carbon emissions. This finding holds when the authors use alternative measures of carbon emissions and debt overhang. The authors find that carbon abatement investment is a channel that is negatively impacted by debt overhang, which in turn increases carbon emissions. This study's results are robust for several endogeneity tests, including firm fixed effects, change analysis, propensity score matching approach and two-stage least squares (2SLS) instrumental variable analysis. Practical implications: The outcome of this research has policy implications for several stakeholders, including investors, firms, market participants and regulators. This study's findings offer insights for investors and firms, helping them allocate resources effectively and make financing decisions aimed at reducing carbon emissions. Regulators and policymakers can also use the findings to formulate policies that promote alternative sustainable finance practices. Originality/value: The outcome of this research is likely to help firms develop their understanding of the debt overhang problem and undertake strategies that yield a significant amount of funding to invest in reducing carbon emissions. [ABSTRACT FROM AUTHOR]

Credit risk prediction method acts as a vital financial tool for measuring the default probability of credit applicants. For financial institutions, proper credit risk management becomes mandatory to avoid significant losses incurred by borrowers' default. Thus, statistics are an increasingly vital technique that can analyse and measure credit risk. Generally, manual auditing and statistical methods measure credit risk. Current developments in financial artificial intelligence (AI) evolved from machine learning (ML)-driven credit risk methods that obtained great interest from academia and industry. The most significant step in the process of developing a credit risk assessment method is feature selection, which chooses a subset of appropriate features for enhancing the performance of an ML technique. With this motivation, this study concentrates on the design of sand cat swarm optimization-based feature selection with hybrid deep learning (SCSOFS-HDL) model for credit risk assessment. The presented SCSOFS-HDL technique presents a new SCSOFS technique for the optimal selection of feature subsets from the credit risk data. In addition, the deep LSTM Supervised Autoencoder Neural Network (DLSTM-SANN) model is presented for classification purposes. To enhance the performance of the DLSTM-SANN technique, the political optimizer (PO) methodology is utilized for the hyperparameter tuning process. The experimental validation of the SCSOFS-HDL technique is tested on credit risk datasets and the results highlighted the better performance of the SCSOFS-HDL algorithm with maximum accuracy of 96.49% and 96.12% on German Credit and Australian Credit datasets, respectively. [ABSTRACT FROM AUTHOR]

The rapid development of supply chain finance (SCF) has significantly alleviated the financing difficulties of small and medium-sized enterprises (SMEs). However, it is important to recognize that within the accounts receivable financing segment of the SCF credit market, the credit risk associated with SMEs poses a serious challenge and potential threat to the stability, health, and sustainable development of the SCF system. This paper pays special attention to the stability of the two-party evolutionary game between SMEs and financial institutions (FIs) within the context of the Chinese SCF credit market. To identify a pathway to reduce credit risks for SMEs while simultaneously enhancing system stability, this paper adopts the stochastic evolutionary game (SEG) model and combines the fixed-point method to determine the conditions that satisfy the stability of the system's index p mean square of the system. This study has made attempts in various aspects, such as the innovative construction and investigation of a nonlinear SEG model, the endeavor to study the stability of SEG systems using fixed-point methods, and the innovative construction of a more realistic two-player SEG system. The data and simulation results generated from hypothetical scenarios show that the conclusions of the article are credible and feasible. Through the study, we conclude that the higher credit ratio from FI and the higher penalty intensity from core enterprises (CEs) will accelerate the stability of the system. Based on solid data and modeling analysis, insights into the regulation of FI are provided. [ABSTRACT FROM AUTHOR]

Credit risk assessment is an important process in bank financial risk management. Traditional machine-learning methods cannot solve the problem of data islands and the high error rate of two-way decisions, which is not conducive to banks' accurate credit risk assessment of users. To this end, this paper establishes a federated three-way decision incremental naive Bayes bank user credit risk assessment model (FTwNB) that supports asymmetric encryption, uses federated learning to break down data barriers between banks, and uses asymmetric encryption to protect data security for federated processes. At the same time, the model combines the three-way decision methods to realize the three-way classification of user credit (good, bad and delayed judgment), so as to avoid the loss of bank interests caused by the forced division of uncertain users. In addition, the model also incorporates incremental learning steps to eliminate training samples with poor data quality to further improve the model performance. This paper takes German Credit data and Default of Credit Card Clients data as examples to conduct simulation experiments. The result shows that the performance of the FTwNB model has been greatly improved, which verifies that it has good credit risk assessment capabilities. [ABSTRACT FROM AUTHOR]

This research is based on a significant problem in credit risk analysis in the banking sector caused by class imbalance. We face the problem of the model’s inability to accurately identify risks in the ‘‘Charged Off’’ class. As a solution, we propose a stacked ensemble approach that utilizes synthetic minority over-sampling technique (SMOTE) to balance the class distribution. Experiments were conducted by applying SMOTE to the training data before training the credit model using gradient boosting (XGBoost) and random forest (RF) algorithms in a single ensemble. The results show significant improvements in precision, recall, and F1-score after applying SMOTE on the unbalanced classes. The updated model achieved a striking accuracy rate of 0,97 on resampled training data. This re-search clearly identifies the problem of class imbalance as a major challenge in credit risk analysis. The application of SMOTE in a stacked ensemble was found to be effective in improving model performance, making a valuable contribution to the development of more reliable credit models for better risk management and revenue generation in financial institutions. [ABSTRACT FROM AUTHOR]

The AUC, i.e. the area under the receiver operating characteristic (ROC) curve, or its scaled version, the Gini coefficient, are the standard measures of the discriminatory power of credit scoring. Using binormal ROC curve models, we show how the shape of the curves affects the economic benefits of using scoring models with the same AUC. Based on the results, we propose that the shape parameter of the fitted ROC curve is reported alongside its AUC/Gini whenever the quality of a scorecard is discussed. [ABSTRACT FROM AUTHOR]

This paper aims to show how the 100% money proposal, which Irving Fisher came to support in 1935, connects to the rest of his work on monetary instability—in particular, to his credit cycle analysis of 1911 and his debt-deflation theory of 1932–33. Behind these respective analyses, we identify a common explanatory pattern of monetary fluctuations, the "debt–money–prices" triangle, which we use to show how Fisher's explanations evolved over time, and how his advocacy of 100% money came as a logical conclusion. [ABSTRACT FROM AUTHOR]

This study explores the potential of utilizing alternative data sources to enhance the accuracy of credit scoring models, compared to relying solely on traditional data sources, such as credit bureau data. A comprehensive dataset from the Home Credit Group's home loan portfolio is analysed. The research examines the impact of incorporating alternative predictors that are typically overlooked, such as an applicant's social network default status, regional economic ratings, and local population characteristics. The modelling approach applies the model-X knockoffs framework for systematic variable selection. By including these alternative data sources, the credit scoring models demonstrate improved predictive performance, achieving an area under the curve metric of 0.79360 on the Kaggle Home Credit default risk competition dataset, outperforming models that relied solely on traditional data sources, such as credit bureau data. The findings highlight the significance of leveraging diverse, non-traditional data sources to augment credit risk assessment capabilities and overall model accuracy. [ABSTRACT FROM AUTHOR]

The credit risk assessment acts as an important part in daily affairs for financial institutions. But in the era of big data, the growing business volume makes it an urgent demand to develop digital ways of credit risk assessment. Currently, the machine learning is universally employed to establish various data-driven models for this purpose. However, machine learning models generally suffer from limited ability of feature representation and robustness, and cannot deal with more complex financial security scenarios. To deal with this issue, this work introduces ensemble learning to construct a stronger credit risk prediction model via integration of several basic machine learning models. Thus, an ensemble learning-enhanced smart prediction model for financial credit risk is proposed in this paper. Three classification-based machine learning models (support vector machine, artificial neural network and radial basis function) are selected as the basic classifiers, and "voting" strategy is utilized to integrate them into a novel strong classifier. A real-world financial credit dataset released by a Chinese commercial bank was selected as the experimental scenario. The obtained results show that the proposal has better prediction accuracy compared with basic machine learning models without ensemble learning. [ABSTRACT FROM AUTHOR]

The rapid advancement of technologies has pushed for additional enhancements to banking and other credit platforms. While assisting small and medium sized business in lowering financing costs, banks and credit platforms must take into account practical matters like, their own capital expenses and risk evaluation. Even though, there are several methods for credit risk assessment, no comprehensive literature reviews have provided sufficient accuracy and better results while implementing in banking sectors. To overcome these issues, this manuscript proposes credit risk assessment in the banking sector using an Adaptive Binarized Spiking Marine Predators Neural Network (ABSMPNN) for accurate identification of customer credit quality within a short period of time. The evaluation using the credit risk dataset from Kaggle leads to the decision to grant or reject the customer's loan application. The concentration phase of the Variable Color Harmony Algorithm (VCHA) effectively achieves the selection of the most relevant features from the noisy and irrelevant ones. The optimization of neural network parameters with Adaptive Marine Predators Algorithm (AMPA) has further improved the overall accuracy (98.9%) with minimization of loss function. The outcomes depict that the introduced model attains higher accuracy and lower computational period of credit risk evaluation when compared with state-of-the-art. [ABSTRACT FROM AUTHOR]

With the growing significance of Credit Risk Analysis (CRA) with a focus on privacy, there is a pressing demand for a Privacy Preserving Machine Learning (PPML) decision support system. In this context, we introduce a framework for privacy‐preserving credit risk analysis that utilizes Homomorphic Encryption aware Logistic Regression (HELR) on encrypted data. The implementation involves the use of TenSEAL and Torch libraries for Logistic Regression (LR), integrating the proposed HELR on polynomial degrees 3 and 5 across German, Taiwan, Japan, and Australian datasets. The presented model yields satisfactory results compared to non‐Homomorphic Encryption (HE) models, demonstrating a minimal accuracy difference ranging from 0.5% to 7.8%. Notably, HELR_g5 outperforms HELR_g3, exhibiting a higher Area Under Curve (AUC) value. Additionally, a thorough security analysis indicates the resilience of the proposed system against various privacy attacks, including poison attacks, evasion attacks, member inference attacks, model inversion attacks, and model extraction attacks at different stages of machine learning. Finally, in the comparative analysis, we highlight that the proposed model ensures data privacy, encompassing training privacy and model privacy during the training phase, as well as input and output privacy during the inference phase a level of privacy not achieved by existing systems. [ABSTRACT FROM AUTHOR]

Much like traditional credit scoring, decentralized credit scoring calculates a borrower's creditworthiness, but the fully automated process is executed on the blockchain by Decentralized Finance (DeFi) platforms. Originally, DeFi emerged as an alternative to the centralized traditional finance (TradFi) system; however, decentralized credit scoring combines DeFi data and traditional data that include a wide range of information sources, from traditional credit reports to social media information. Despite their fairness‐oriented narrative, an examination of the business models of the protocols and entities operating in this space reveals that these hybrid scores are subject to the same algorithmic distortions that have been observed in traditional and alternative credit scoring models. Moreover, decentralized credit scores present their own distinctive set of fairness issues. Particularly, both upgrade to smart contracts and their reliance on external algorithms, known as oracles, which feed outside data, introduce heightened potential for error and bias in the credit scoring process. These "black box 3.0" issues can result in opaque automation of biased processes and perpetuate social injustices, requiring regulatory intervention to strengthen the linkage points between DeFi and TradFi and better protect consumers from the black box 3.0 consequences of decentralized credit scores. [ABSTRACT FROM AUTHOR]

To reflect both fuzziness and hesitation in the evaluation of interactivity between attributes in the identification process of 2-order additive fuzzy measure, this work uses the hesitant fuzzy linguistic term set (HFLTS) to describe and depict the interactivity between attributes. Firstly, the interactivity between attributes is defined by the supermodular game theory. According to this definition, a linguistic term set is established to characterize the interactivity between attributes. Under the linguistic term set, the experts employ linguistic expressions generated by context-free grammar to qualitatively describe the interactivity between attributes. Secondly, through the conversion function, the linguistic expressions are transformed into the hesitant fuzzy linguistic term sets (HFLTSs). The individual evaluation results of all experts were further aggregated with the defined hesitant fuzzy linguistic weighted power average operator (HFLWPA). Thirdly, based on the standard Euclidean distance formula of the hesitant fuzzy linguistic elements (HFLEs), the hesitant fuzzy linguistic interaction degree (HFLID) between attributes is defined and calculated by constructing a piecewise function. As a result, a 2-order additive fuzzy measure identification method based on HFLID is proposed. Based on the proposed method, using the Choquet fuzzy integral as nonlinear integration operator, a multi-attribute decision making (MADM) process is then presented. Taking the credit assessment of the big data listed companies in China as an application example, the analysis results of application example prove the feasibility and effectiveness of the proposed method. This work successfully reflects both the fuzziness and hesitation in evaluating the interactivity between attributes in the identification process of 2-order additive fuzzy measure, enriches the theoretical framework of 2-order additive fuzzy measure, and expands the applicability and methodology of 2-order additive fuzzy measure in multi-attribute decision making. [ABSTRACT FROM AUTHOR]

The k-nearest neighbors (k-NN) algorithm, a fundamental machine learning technique, typically employs the Euclidean distance metric for proximity-based data classification. This research focuses on the feature importance infused k-NN model, an advanced form of k-NN. Diverging from traditional algorithm uniform weighted Euclidean distance, feature importance infused k-NN introduces a specialized distance weighting system. This system emphasizes critical features while reducing the impact of lesser ones, thereby enhancing classification accuracy. Empirical studies indicate a 1.7% average accuracy improvement with proposed model over conventional model, attributed to its effective handling of feature importance in distance calculations. Notably, a significant positive correlation was observed between the disparity in feature importance levels and the model's accuracy, highlighting proposed model's proficiency in handling variables with limited explanatory power. These findings suggest proposed model's potential and open avenues for future research, particularly in refining its feature importance weighting mechanism, broadening dataset applicability, and examining its compatibility with different distance metrics. [ABSTRACT FROM AUTHOR]

The representation of women in advertising creative departments has been studied worldwide. The findings have shown a low representation that does not favor the emergence of a critical mass of women, who could contribute with alternative visions to make advertising more inclusive. The underrepresentation, above all, occurs in managerial positions where they do not usually reach 35%. This study aims to update and report quantitatively on the phenomenon of the glass ceiling in Spain. In addition, in order to contextualize the level of segregation, these departments are compared with available international data. The results of a content analysis of the credit forms of 839 Spanish campaigns published in 2019 (a sample of 1,311 creatives) revealed gender dynamics, with a balanced starting group of creatives in nonmanagerial positions (just over 40% are women), but a figure of just 18% of women in managerial roles A higher glass ceiling effect was also found when European and global data were compared. The results analyzed through the perspective of the proportional representation theory (Kanter, 1977a, 1977b, 1987), suggest the need to raise awareness of gender inequalities within creative departments; this would foster the equality demanded by today’s society, of which advertising should not be oblivious [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to investigate whether professional data analysts' trust of black-box systems is increased by explainability artifacts. Design/methodology/approach: The study was developed in two phases. First a black-box prediction model was estimated using artificial neural networks, and local explainability artifacts were estimated using local interpretable model-agnostic explanations (LIME) algorithms. In the second phase, the model and explainability outcomes were presented to a sample of data analysts from the financial market and their trust of the models was measured. Finally, interviews were conducted in order to understand their perceptions regarding black-box models. Findings: The data suggest that users' trust of black-box systems is high and explainability artifacts do not influence this behavior. The interviews reveal that the nature and complexity of the problem a black-box model addresses influences the users' perceptions, trust being reduced in situations that represent a threat (e.g. autonomous cars). Concerns about the models' ethics were also mentioned by the interviewees. Research limitations/implications: The study considered a small sample of professional analysts from the financial market, which traditionally employs data analysis techniques for credit and risk analysis. Research with personnel in other sectors might reveal different perceptions. Originality/value: Other studies regarding trust in black-box models and explainability artifacts have focused on ordinary users, with little or no knowledge of data analysis. The present research focuses on expert users, which provides a different perspective and shows that, for them, trust is related to the quality of data and the nature of the problem being solved, as well as the practical consequences. Explanation of the algorithm mechanics itself is not significantly relevant. [ABSTRACT FROM AUTHOR]

As an effective measure for the local government to promote reduction of corporate carbon emissions and sustainable development of social economy, the implementation of green finance policies in enterprises and financial institutions has encountered severe strikes from the low returns of low carbon production and low interest rates of green credit business. Under the premise of liberalizing carbon emissions trading, a triple‐level network evolutionary game consisting of a local government, banks, and enterprises is constructed to analyze response behavior and strategy selection mechanism to green credit. The impacts of management tools are investigated in terms of setting carbon market price, limiting the financing upper bound of misbehaving enterprises, limiting the emissions quota of enterprises for fraudulent green credit, and rewarding clean project development on the decisions of individuals in the network. Results show the following: First, increasing the trading price of carbon emissions has a catalytic effect on enhancing the activeness of banks and enterprises to follow green finance policies, but the autonomous regulation ability of which is limited. Second, reducing the funding ceiling for emitting emissions illegally ambiguates enterprises' preferences for production strategies and discourages them from undertaking low‐carbon projects. Third, excessive restrictions on the share of emissions may evoke regulatory inaction by the local government, consequently leading to instability in the evolution network. Fourth, granting reward for clean production is instrumental for the network to promote green finance policies, but exorbitant subsidies increase the fiscal burden of the local government with no significant effect on the node selection of environment‐friendly strategies. [ABSTRACT FROM AUTHOR]

Insight into correlations of returns is foundational to understanding how a portfolio might behave, particularly during periods of market stress when diversification may be most desired. To evaluate the diversification properties of combining equity and credit in multiasset portfolios, the author studies S&P 500 and investment-grade (IG) and high-yield (HY) credit default swap (CDX) indexes using DCC-GARCH and copulas. With a deep history of CDX data now available, comovement analysis of equity and credit indexes is possible through multiple cycles and two major dislocations, which adds to the body of existing research. Moreover, this approach allows for a review through multiple lenses and evaluation of changes over time. Despite differences in their fundamental drivers of returns, placement in the capital structure, and volatilities, the author finds only modest potential for diversification between equity and CDX markets with similar directional return behaviors between IG and HY CDX and equities. Moreover, the author finds strong evidence of increased comovement, particularly in the period during and just after the Global Financial Crisis. [ABSTRACT FROM AUTHOR]

This research aims to assess multilanguage versions of the IRQS-2018 to determine Intergenerational relationship quality in the older persons. In a psychometric investigation, the instrument was completed by 707 persons whose age is older than 60; those people were from 6 populated ethnic groups in Iran. It is noteworthy that the Rasch partial credit model (PCM) and the classic method were employed.The PCM showed that items 3 and 7 were misfitting in all versions of IRQS. Furthermore, consecutive response groupings for all items were situated in the predictable order, and the version of IRQS with 11-items had further interior consistency. Although Rasch analysis specified to pertinent of IRQS 11-Items, it should be assessed in additional investigations and deviating settings such as public residence grown-up adults. [ABSTRACT FROM AUTHOR]

In recent years, the increasing prevalence of credit card usage has raised concerns about accurately predicting and managing credit card defaults. While machine learning and deep learning methods have shown promising results in default prediction, the black-box nature of these models often limits their interpretability and practical adoption. This study presents a new method for predicting credit card default using a combination of deep learning and explainable artificial intelligence (XAI) techniques. Integrating these methods aims to improve the interpretability of the decision-making process involved in credit card default prediction. The proposed approach is evaluated using a real-world dataset and compared to existing state-of-the-art models. Results show that the proposed approach achieves competitive prediction accuracy while providing meaningful insights into the factors driving credit card default risk. The present investigation adds to the increasing body of literature on explainable artificial intelligence (AI) in the realm of finance. Besides, it provides a pragmatic approach to assessing credit risk, balancing precision and comprehensibility. In conclusion, the model demonstrates strong potential as a credit risk assessment tool, with an accuracy of 0.8350, sensitivity of 0.8823, and specificity of 0.9879. Among the most important features identified by the model are payment delays and outstanding bill amounts. This study is a step toward more interpretable and transparent credit scoring models. [ABSTRACT FROM AUTHOR]

Climate change and the challenges associated with the transition to a zero‐carbon economy pose significant financial risks. Climate‐related risks (CRR) indirectly impact banks through their loan portfolios. To examine the integration of CRR into banks' credit risk assessment and monitoring, this article reviews academic and institutional literature using quantitative bibliometric techniques and content analysis of 145 academic documents from policymakers and financial supervisors. A framework emerges that incorporates CRR into credit risk management. We find four thematic areas in the literature: CRR drivers, CRR tools, CRR data and CRR pricing. Overall, uncertainty, non‐linearity, geographic and industrial dependency and non‐reversibility of CRR difficult climate‐related credit risk assessment. Moreover, CRR data present comparability, availability and reliability issues, which Artificial Intelligence can improve. Finally, evidence reveals that current financial prices do not fully reflect CRR. Our findings provide important implications to policymakers for assessing ex‐ante the financial impacts of climate transition regulations, the potential for prudential regulatory action, and the need for supra‐national policies that facilitate access to reliable and comparable climate data. [ABSTRACT FROM AUTHOR]

The number of loan requests is rapidly growing worldwide representing a multi-billion-dollar business in the credit approval industry. Large data volumes extracted from the banking transactions that represent customers' behavior are available, but processing loan applications is a complex and time-consuming task for banking institutions. In 2022, over 20 million Americans had open loans, totaling USD 178 billion in debt, although over 20% of loan applications were rejected. Numerous statistical methods have been deployed to estimate loan risks opening the field to estimate whether machine learning techniques can better predict the potential risks. To study the machine learning paradigm in this sector, the mental health dataset and loan approval dataset presenting survey results from 1991 individuals are used as inputs to experiment with the credit risk prediction ability of the chosen machine learning algorithms. Giving a comprehensive comparative analysis, this paper shows how the chosen machine learning algorithms can distinguish between normal and risky loan customers who might never pay their debts back. The results from the tested algorithms show that XGBoost achieves the highest accuracy of 84% in the first dataset, surpassing gradient boost (83%) and KNN (83%). In the second dataset, random forest achieved the highest accuracy of 85%, followed by decision tree and KNN with 83%. Alongside accuracy, the precision, recall, and overall performance of the algorithms were tested and a confusion matrix analysis was performed producing numerical results that emphasized the superior performance of XGBoost and random forest in the classification tasks in the first dataset, and XGBoost and decision tree in the second dataset. Researchers and practitioners can rely on these findings to form their model selection process and enhance the accuracy and precision of their classification models. [ABSTRACT FROM AUTHOR]

Background: The modern credit card system is critical, but it has not been fully examined to meet the unique financial needs of a constantly changing number of manufacturers and importers. Methods: An intelligent credit card system integrates the features of artificial intelligence and blockchain technology. The decentralized and unchangeable ledger of the Blockchain technology significantly reduces the risk of fraud while maintaining real-time transaction recording. On the other hand, the capabilities of AI-driven credit assessment algorithms enable more precise, effective, and customized credit choices that are specifically tailored to meet the unique financial profiles of manufacturers and importers. Results: Several metrics, including predictive credit risk, fraud detection, credit assessment accuracy, default rate comparison, loan approval rate comparison, and other important metrics affecting the credit card system, have been investigated to determine the effectiveness of modern credit card systems when using Blockchain technology and AI. Conclusion: The study of developing an intelligent scoring system for crediting manufacturers and importers of goods in Industry 4.0 can be enhanced by incorporating user adoption. The changing legislation and increasing security threats necessitate ongoing monitoring. Scalability difficulties can be handled by detailed planning that focuses on integration, data migration, and change management. The research may potentially increase operational efficiency in the manufacturing and importing industries. [ABSTRACT FROM AUTHOR]

For the financial health of lenders and institutions, one important risk assessment called credit risk is about correctly deciding whether or not a borrower will fail to repay a loan. It not only helps in the approval or denial of loan applications but also aids in managing the non-performing loan (NPL) trend. In this study, a dataset provided by the LendingClub company based in San Francisco, CA, USA, from 2007 to 2020 consisting of 2,925,492 records and 141 attributes was experimented with. The loan status was categorized as "Good" or "Risk". To yield highly effective results of credit risk prediction, experiments on credit risk prediction were performed using three widely adopted supervised machine learning techniques: logistic regression, random forest, and gradient boosting. In addition, to solve the imbalanced data problem, three sampling algorithms, including under-sampling, over-sampling, and combined sampling, were employed. The results show that the gradient boosting technique achieves nearly perfect A c c u r a c y , P r e c i s i o n , R e c a l l , and F 1 s c o r e values, which are better than 99.92%, but its M C C values are greater than 99.77%. Three imbalanced data handling approaches can enhance the model performance of models trained by three algorithms. Moreover, the experiment of reducing the number of features based on mutual information calculation revealed slightly decreasing performance for 50 data features with A c c u r a c y values greater than 99.86%. For 25 data features, which is the smallest size, the random forest supervised model yielded 99.15% A c c u r a c y . Both sampling strategies and feature selection help to improve the supervised model for accurately predicting credit risk, which may be beneficial in the lending business. [ABSTRACT FROM AUTHOR]

The accuracy of credit risk evaluation is crucial for the profitability of any financial institution. The factorization machine is a widely available model that can effectively be utilized for classification or regression through appropriate feature transformation. In this article, we apply the factorization machine model to the field of credit risk assessment. Since some features of the credit risk assessment data are not numerical, one-hot encoding is used, resulting in sparse training data. However, the computational complexity of the factorization machine is polynomial. To illustrate the effectiveness of the factorization machine credit risk assessment model and compare its performance with other classification approaches such as logical regression, support vector machine, k-nearest neighbors, and artificial neural network, we conduct numerical experiments on four real-world credit risk evaluation datasets. The experimental results demonstrate that the proposed factorization machine credit risk assessment model achieves higher accuracy compared to other machine-learning models on real-world datasets and is computationally more efficient. Therefore, the factorization machine model can be considered as a suitable candidate for credit risk assessment. [ABSTRACT FROM AUTHOR]

Decentralized credit scoring has surfaced as a new approach in the everevolving consumer credit space. While drawing parallels to traditional credit scoring, decentralized credit scoring sets itself apart by evaluating the financial activity and behavior of users within the blockchain ecosystem. Blockchain technology has been fueling this transformation and serving as the backbone for a diverse range offinancialproducts and services collectively known as decentralized tinance (DeFi). DeFi lending, in particular, has been thriving in recent years. However, the pseudonymous nature of blockchain, coupled with the inherent volatility of cryptoassets, has resulted in the absence of reliable means of risk assessment for DeFi loan processing. Consequently, a common practice ofrelying on overcollateralized loans has emerged, limiting access to DeFi loans only to those with substantial collateral. In the face of this challenge, enterprising DeFi lending protocols sought a transformative solution and introduced crypto-native credit scoring. By tapping into blockchain data, crypto-native credit scoring aims to bridge the gap in risk assessment, rendering DeFi lending more robust and inclusive. While decentralized credit scoring has been touted as safer, more trustworthy, andequitable, we find that it may not be as promising as it has been made out to be. This Article demonstrates how DeFi loans were heavilypromoted to the same disadvantaged populations that have experienced exclusion and bias in the traditional finance system and sought out a more equitable alternative. It argues that crypto-native credit models, which currently operate without regulatory oversight andare metwithslowregulatory responses, present new fairness, accountability, and transparency harms that have yet to be identified and addressed by legal commentary. These harms include potential predatory practices by DeFi lending protocols requiring borrowers to overcollateralize their loans to build credit history. This Article further underscores the crucial role of the Consumer Financial Protection Bureau in overseeing decentralized credit scores and the involvement of financial influencers. These influencers, which have been operating without much regulatory attention, are increasingly shaping investment choices, particularly among underprivileged and financially excludedpopulations. [ABSTRACT FROM AUTHOR]

Survival models have become popular for credit risk estimation. Most current credit risk survival models use an underlying linear model. This is beneficial in terms of interpretability but is restrictive for real-life applications since it cannot discover hidden nonlinearities and interactions within the data. This study uses discrete-time survival models with embedded neural networks as estimators of time to default. This provides flexibility to express nonlinearities and interactions between variables and hence allows for models with better overall model fit. Additionally, the neural networks are used to estimate age–period–cohort (APC) models so that default risk can be decomposed into time components for loan age (maturity), origination (vintage), and environment (e.g., economic, operational, and social effects). These can be built as general models or as local APC models for specific customer segments. The local APC models reveal special conditions for different customer groups. The corresponding APC identification problem is solved by a combination of regularization and fitting the decomposed environment time risk component to macroeconomic data since the environmental risk is expected to have a strong relationship with macroeconomic conditions. Our approach is shown to be effective when tested on a large publicly available US mortgage dataset. This novel framework can be adapted by practitioners in the financial industry to improve modeling, estimation, and assessment of credit risk. [ABSTRACT FROM AUTHOR]

With the growth of people's demand for loans, banks and other financial institutions put forward higher requirements for customer credit risk level classification, the purpose is to make better loan decisions and loan amount allocation and reduce the pre-loan risk. This article proposes a Multi-Level Classification based Ensemble and Feature Extractor (MLCEFE) that incorporates the strengths of sampling, feature extraction, and ensemble classification. MLCEFE uses SMOTE + Tomek links to solve the problem of data imbalance and then uses a deep neural network (DNN), auto-encoder (AE), and principal component analysis (PCA) to transform the original variables into higher-level abstract features for feature extraction. Finally, it combined multiple ensemble learners to improve the effect of personal credit risk multi-classification. During performance evaluation, MLCEFE has shown remarkable results in the multi-classification of personal credit risk compared with other classification methods. [ABSTRACT FROM AUTHOR]