Federated learning has been used extensively in business inno-vation scenarios in various industries.This research adopts the federated learning approach for the first time to address the issue of bank-enterprise info...Federated learning has been used extensively in business inno-vation scenarios in various industries.This research adopts the federated learning approach for the first time to address the issue of bank-enterprise information asymmetry in the credit assessment scenario.First,this research designs a credit risk assessment model based on federated learning and feature selection for micro and small enterprises(MSEs)using multi-dimensional enterprise data and multi-perspective enterprise information.The proposed model includes four main processes:namely encrypted entity alignment,hybrid feature selection,secure multi-party computation,and global model updating.Secondly,a two-step feature selection algorithm based on wrapper and filter is designed to construct the optimal feature set in multi-source heterogeneous data,which can provide excellent accuracy and interpretability.In addition,a local update screening strategy is proposed to select trustworthy model parameters for aggregation each time to ensure the quality of the global model.The results of the study show that the model error rate is reduced by 6.22%and the recall rate is improved by 11.03%compared to the algorithms commonly used in credit risk research,significantly improving the ability to identify defaulters.Finally,the business operations of commercial banks are used to confirm the potential of the proposed model for real-world implementation.展开更多
Credit risk assessment involves conducting a fair review and evaluation of an assessed subject’s solvency and creditworthiness.In the context of real estate enterprises,credit risk assessment provides a basis for ban...Credit risk assessment involves conducting a fair review and evaluation of an assessed subject’s solvency and creditworthiness.In the context of real estate enterprises,credit risk assessment provides a basis for banks and other financial institutions to choose suitable investment objects.Additionally,it encourages real estate enterprises to abide by market norms and provide reliable information for the standardized management of the real estate industry.However,Chinese real estate companies are hesitant to disclose their actual operating data due to privacy concerns,making subjective evalu-ation approaches inevitable,occupying important roles in accomplishing Chinese real estate enterprise credit risk assessment tasks.To improve the normative and reliability of credit risk assessment for Chinese real estate enterprises,this study proposes an integrated multi-criteria group decision-making approach.First,a credit risk assessment index for Chinese real estate enterprises is established.Then,the proposed framework combines proportional hesitant fuzzy linguistic term sets and preference ranking organization method for enrichment evaluation II methods.This approach is suitable for processing large amounts of data with high uncertainty,which is often the case in credit risk assessment tasks of Chinese real estate enterprises involving massive subjec-tive evaluation information.Finally,the proposed model is validated through a case study accompanied by sensitivity and comparative analyses to verify its rationality and feasibility.This study contributes to the research on credit assessment for Chinese real estate enterprises and provides a revised paradigm for real estate enterprise credit risk assessment.展开更多
A rough set method is presented in this paper to assess the credit of contractors. Unlike traditional methods, the rough set method deduces credit-classifying rules from actual data to predict new cases. The method us...A rough set method is presented in this paper to assess the credit of contractors. Unlike traditional methods, the rough set method deduces credit-classifying rules from actual data to predict new cases. The method uses a contractors＇ database with a genetic algorithm and an exhaustive reduction implemented using ROSETTA software that integrates rough set method. The classification accuracy of the rough set model is not as good as that of a decision tree, logistic regression, and neural network models, but the rough set model more accurately predicts contractors with bad credit. The results show that the rough set model is especially useful for detecting corporations with bad credit in the currently disordered Chinese construction market.展开更多
Background:Supply chain finance(SCF)is a series of financial solutions provided by financial institutions to suppliers and customers facing demands on their working capital.As a systematic arrangement,SCF utilizes the...Background:Supply chain finance(SCF)is a series of financial solutions provided by financial institutions to suppliers and customers facing demands on their working capital.As a systematic arrangement,SCF utilizes the authenticity of the trade between(SMEs)and their“counterparties”,which are usually the leading enterprises in their supply chains.Because in these arrangements the leading enterprises are the guarantors for the SMEs,the credit levels of such counterparties are becoming important factors of concern to financial institutions’risk management(i.e.,commercial banks offering SCF services).Thus,these institutions need to assess the credit risks of the SMEs from a view of the supply chain,rather than only assessing an SME’s repayment ability.The aim of this paper is to research credit risk assessment models for SCF.Methods:We establish an index system for credit risk assessment,adopting a view of the supply chain that considers the leading enterprise’s credit status and the relationships developed in the supply chain.Furthermore,We conducted two credit risk assessment models based on support vector machine(SVM)technique and BP neural network respectly.Results:(1)The SCF credit risk assessment index system designed in this paper,which contained supply chain leading enterprise’s credit status and cooperative relationships between SMEs and leading enterprises,can help banks to raise their accuracy on predicting a small and medium enterprise whether default or not.Therefore,more SMEs can obtain loans from banks through SCF.(2)The SCF credit risk assessment model based on SVM is of good generalization ability and robustness,which is more effective than BP neural network assessment model.Hence,Banks can raise the accuracy of credit risk assessment on SMEs by applying the SVM model,which can alleviate credit rationing on SMEs.Conclusions:(1)The SCF credit risk assessment index system can solve the problem of banks incorrectly labeling a creditworthy enterprise as a default enterprise,and thereby improve the credit rating status in the process of SME financing.(2)By analyzing and comparing the empirical results,we find that the SVM assessment model,on evaluating the SME credit risk,is more effective than the BP neural network assessment model.This new assessment model based on SVM can raise the accuracy of classification between good credit and bad credit SMEs.(3)Therefore,the SCF credit risk assessment index system and the assessment model based on SVM,is the optimal combination for commercial banks to use to evaluate SMEs’credit risk.展开更多
The characteristics of the financing model are firstly analyzed when the e-commerce enterprises participate in the supply chain finance. Internet supply chain finance models are divided into three categories with the ...The characteristics of the financing model are firstly analyzed when the e-commerce enterprises participate in the supply chain finance. Internet supply chain finance models are divided into three categories with the standard of whether the Electronic commerce enterprises provide funds for small and medium enterprises instead of banks. And then we further study the financing process and the functions of the e-commerce platform with specific examples. Finally, combined with the characteristics of the supply chain finance model, we set up a small and medium enterprises credit evaluation model based on the principle of variable weight with its dynamic data. At the same time, a multi time points and multi indicators decision-making method based on the principle of variable weight is proposed and a specific example is presented. In this paper, the Multi-criteria decision-making model with the principle of variable weight has been used two times. At last, a typical case has been analyzed based on this model with a higher accuracy rate of credit risk assessment.展开更多
In order to improve the precision of personal credit risk assessment, applying rough set and neural network to the credit risk scoring prediction problem in an attempt to suggest a new model with better classification...In order to improve the precision of personal credit risk assessment, applying rough set and neural network to the credit risk scoring prediction problem in an attempt to suggest a new model with better classification accuracy. To evaluate the prediction accuracy of the model, we compare its performance with those of SVM, linear discriminate analysis, logistic regression analysis, K-nearest neighbors, classification and regression tree, neural network and PCA-NN. The experimental results show the model have a very good prediction accuracy展开更多
基金funded by the State Grid Jiangsu Electric Power Company(Grant No.JS2020112)the National Natural Science Foundation of China(Grant No.62272236).
文摘Federated learning has been used extensively in business inno-vation scenarios in various industries.This research adopts the federated learning approach for the first time to address the issue of bank-enterprise information asymmetry in the credit assessment scenario.First,this research designs a credit risk assessment model based on federated learning and feature selection for micro and small enterprises(MSEs)using multi-dimensional enterprise data and multi-perspective enterprise information.The proposed model includes four main processes:namely encrypted entity alignment,hybrid feature selection,secure multi-party computation,and global model updating.Secondly,a two-step feature selection algorithm based on wrapper and filter is designed to construct the optimal feature set in multi-source heterogeneous data,which can provide excellent accuracy and interpretability.In addition,a local update screening strategy is proposed to select trustworthy model parameters for aggregation each time to ensure the quality of the global model.The results of the study show that the model error rate is reduced by 6.22%and the recall rate is improved by 11.03%compared to the algorithms commonly used in credit risk research,significantly improving the ability to identify defaulters.Finally,the business operations of commercial banks are used to confirm the potential of the proposed model for real-world implementation.
基金supported by the National Natural Science Foundation of China(Grant Nos.72171182 and 72031009)the Spanish Ministry of Economy and Competitiveness through the Spanish National Research Project(Grant No.PGC2018-099402-B-I00)the Spanish postdoctoral fellowship program Ramon y Cajal(Grant No.RyC-2017-21978).
文摘Credit risk assessment involves conducting a fair review and evaluation of an assessed subject’s solvency and creditworthiness.In the context of real estate enterprises,credit risk assessment provides a basis for banks and other financial institutions to choose suitable investment objects.Additionally,it encourages real estate enterprises to abide by market norms and provide reliable information for the standardized management of the real estate industry.However,Chinese real estate companies are hesitant to disclose their actual operating data due to privacy concerns,making subjective evalu-ation approaches inevitable,occupying important roles in accomplishing Chinese real estate enterprise credit risk assessment tasks.To improve the normative and reliability of credit risk assessment for Chinese real estate enterprises,this study proposes an integrated multi-criteria group decision-making approach.First,a credit risk assessment index for Chinese real estate enterprises is established.Then,the proposed framework combines proportional hesitant fuzzy linguistic term sets and preference ranking organization method for enrichment evaluation II methods.This approach is suitable for processing large amounts of data with high uncertainty,which is often the case in credit risk assessment tasks of Chinese real estate enterprises involving massive subjec-tive evaluation information.Finally,the proposed model is validated through a case study accompanied by sensitivity and comparative analyses to verify its rationality and feasibility.This study contributes to the research on credit assessment for Chinese real estate enterprises and provides a revised paradigm for real estate enterprise credit risk assessment.
文摘A rough set method is presented in this paper to assess the credit of contractors. Unlike traditional methods, the rough set method deduces credit-classifying rules from actual data to predict new cases. The method uses a contractors＇ database with a genetic algorithm and an exhaustive reduction implemented using ROSETTA software that integrates rough set method. The classification accuracy of the rough set model is not as good as that of a decision tree, logistic regression, and neural network models, but the rough set model more accurately predicts contractors with bad credit. The results show that the rough set model is especially useful for detecting corporations with bad credit in the currently disordered Chinese construction market.
基金sponsored by NSFC project(71372173、70972053)National Soft Science Research Project(2014GXS4D153)+6 种基金Specialized Research Fund of Ministry of Education for the Doctoral Project(20126118110017)Shaanxi Soft Science Research Project(2012KRZ13、2014KRM28-2、2013KRM08、2011KRM16)Shaanxi Social Science Funds projects(12D231,13D217)Xi’an Soft Science Research Program(SF1225-2)Shaanxi Department of Education Research Project(11JK0175)Shaanxi Department of Education Research Project(15JK1547)XAUT Teachers Scientific Research Foundation(107-211414).
文摘Background:Supply chain finance(SCF)is a series of financial solutions provided by financial institutions to suppliers and customers facing demands on their working capital.As a systematic arrangement,SCF utilizes the authenticity of the trade between(SMEs)and their“counterparties”,which are usually the leading enterprises in their supply chains.Because in these arrangements the leading enterprises are the guarantors for the SMEs,the credit levels of such counterparties are becoming important factors of concern to financial institutions’risk management(i.e.,commercial banks offering SCF services).Thus,these institutions need to assess the credit risks of the SMEs from a view of the supply chain,rather than only assessing an SME’s repayment ability.The aim of this paper is to research credit risk assessment models for SCF.Methods:We establish an index system for credit risk assessment,adopting a view of the supply chain that considers the leading enterprise’s credit status and the relationships developed in the supply chain.Furthermore,We conducted two credit risk assessment models based on support vector machine(SVM)technique and BP neural network respectly.Results:(1)The SCF credit risk assessment index system designed in this paper,which contained supply chain leading enterprise’s credit status and cooperative relationships between SMEs and leading enterprises,can help banks to raise their accuracy on predicting a small and medium enterprise whether default or not.Therefore,more SMEs can obtain loans from banks through SCF.(2)The SCF credit risk assessment model based on SVM is of good generalization ability and robustness,which is more effective than BP neural network assessment model.Hence,Banks can raise the accuracy of credit risk assessment on SMEs by applying the SVM model,which can alleviate credit rationing on SMEs.Conclusions:(1)The SCF credit risk assessment index system can solve the problem of banks incorrectly labeling a creditworthy enterprise as a default enterprise,and thereby improve the credit rating status in the process of SME financing.(2)By analyzing and comparing the empirical results,we find that the SVM assessment model,on evaluating the SME credit risk,is more effective than the BP neural network assessment model.This new assessment model based on SVM can raise the accuracy of classification between good credit and bad credit SMEs.(3)Therefore,the SCF credit risk assessment index system and the assessment model based on SVM,is the optimal combination for commercial banks to use to evaluate SMEs’credit risk.
文摘The characteristics of the financing model are firstly analyzed when the e-commerce enterprises participate in the supply chain finance. Internet supply chain finance models are divided into three categories with the standard of whether the Electronic commerce enterprises provide funds for small and medium enterprises instead of banks. And then we further study the financing process and the functions of the e-commerce platform with specific examples. Finally, combined with the characteristics of the supply chain finance model, we set up a small and medium enterprises credit evaluation model based on the principle of variable weight with its dynamic data. At the same time, a multi time points and multi indicators decision-making method based on the principle of variable weight is proposed and a specific example is presented. In this paper, the Multi-criteria decision-making model with the principle of variable weight has been used two times. At last, a typical case has been analyzed based on this model with a higher accuracy rate of credit risk assessment.
文摘In order to improve the precision of personal credit risk assessment, applying rough set and neural network to the credit risk scoring prediction problem in an attempt to suggest a new model with better classification accuracy. To evaluate the prediction accuracy of the model, we compare its performance with those of SVM, linear discriminate analysis, logistic regression analysis, K-nearest neighbors, classification and regression tree, neural network and PCA-NN. The experimental results show the model have a very good prediction accuracy
