Based on the panel data, we analyze the US commercial banks＇ CRT. According to the study, we find that the introduction of CRT will increase the level of banks＇ liquid risk. The performance of bank mainly is that it...Based on the panel data, we analyze the US commercial banks＇ CRT. According to the study, we find that the introduction of CRT will increase the level of banks＇ liquid risk. The performance of bank mainly is that its supervision and review of risk will drop, based on the impact of asymmetric information, commercial Banks transfer the bad loans to investors. Through the analysis we can see that after the transfer of credit risk in commercial bank did not increase income and reduce risk. Because commercial Banks can extend more bad loans to expand its lending scale, and bad loans will increase the bank overall risk.展开更多
Personal credit risk assessment is an important part of the development of financial enterprises. Big data credit investigation is an inevitable trend of personal credit risk assessment, but some data are missing and ...Personal credit risk assessment is an important part of the development of financial enterprises. Big data credit investigation is an inevitable trend of personal credit risk assessment, but some data are missing and the amount of data is small, so it is difficult to train. At the same time, for different financial platforms, we need to use different models to train according to the characteristics of the current samples, which is time-consuming. <span style="font-family:Verdana;">In view of</span><span style="font-family:Verdana;"> these two problems, this paper uses the idea of transfer learning to build a transferable personal credit risk model based on Instance-based Transfer Learning (Instance-based TL). The model balances the weight of the samples in the source domain, and migrates the existing large dataset samples to the target domain of small samples, and finds out the commonness between them. At the same time, we have done a lot of experiments on the selection of base learners, including traditional machine learning algorithms and ensemble learning algorithms, such as decision tree, logistic regression, </span><span style="font-family:Verdana;">xgboost</span> <span style="font-family:Verdana;">and</span><span style="font-family:Verdana;"> so on. The datasets are from P2P platform and bank, the results show that the AUC value of Instance-based TL is 24% higher than that of the traditional machine learning model, which fully proves that the model in this paper has good application value. The model’s evaluation uses AUC, prediction, recall, F1. These criteria prove that this model has good application value from many aspects. At present, we are trying to apply this model to more fields to improve the robustness and applicability of the model;on the other hand, we are trying to do more in-depth research on domain adaptation to enrich the model.</span>展开更多
At present,further research and exploration on credit risks are being carried out in the global field,and increasingly profound modem credit risks are exposed to the bond market.This requires that we cannot ignore the...At present,further research and exploration on credit risks are being carried out in the global field,and increasingly profound modem credit risks are exposed to the bond market.This requires that we cannot ignore the impact of credit rating migration risk on bond pricing,so as to adapt to the sustainable and healthy development of the bond market under the new normal of China's economy.The innovation point of this paper is to try to analyze the pricing of Convertible bonds in China from the perspective of credit rating migration risk.Tsiveriotis and Femandes(1998)model is selected,and the credit risk in the model is assumed to be caused by the credit rating migration risk,and the credit spread is used to measure the credit rating migration risk.The research conclusion of this paper is as follows:First,it is valid to consider the risk of credit rating migration in the TF(1998)model.The market price of convertible bonds is on average 1.22% higher 1han the theoretical value of the model.In general,the theoretical value obtained from the model has little deviation from the market price,and has a good fitting degree.Second,from the Angle of credit rating,the selection of 32 samples of convertible bonds only empirical research shows that the credit rating of AA-convertible bonds average deviation rate is negative,suggest that the credit rating of AA-the phenomenon of convertible bonds value is underestimated,and AAA credit rating to AA,AA+,the average deviation rate of convertible bonds is positive,that credit rating AA(containing AA)more convertible bond value is overrated phenomenon,and the higher the credit rating of the average deviation rate of convertible bond,the greater the overvalued levels.It has certain guiding significance for participants in the convertible bond market.展开更多
文摘Based on the panel data, we analyze the US commercial banks＇ CRT. According to the study, we find that the introduction of CRT will increase the level of banks＇ liquid risk. The performance of bank mainly is that its supervision and review of risk will drop, based on the impact of asymmetric information, commercial Banks transfer the bad loans to investors. Through the analysis we can see that after the transfer of credit risk in commercial bank did not increase income and reduce risk. Because commercial Banks can extend more bad loans to expand its lending scale, and bad loans will increase the bank overall risk.
文摘Personal credit risk assessment is an important part of the development of financial enterprises. Big data credit investigation is an inevitable trend of personal credit risk assessment, but some data are missing and the amount of data is small, so it is difficult to train. At the same time, for different financial platforms, we need to use different models to train according to the characteristics of the current samples, which is time-consuming. <span style="font-family:Verdana;">In view of</span><span style="font-family:Verdana;"> these two problems, this paper uses the idea of transfer learning to build a transferable personal credit risk model based on Instance-based Transfer Learning (Instance-based TL). The model balances the weight of the samples in the source domain, and migrates the existing large dataset samples to the target domain of small samples, and finds out the commonness between them. At the same time, we have done a lot of experiments on the selection of base learners, including traditional machine learning algorithms and ensemble learning algorithms, such as decision tree, logistic regression, </span><span style="font-family:Verdana;">xgboost</span> <span style="font-family:Verdana;">and</span><span style="font-family:Verdana;"> so on. The datasets are from P2P platform and bank, the results show that the AUC value of Instance-based TL is 24% higher than that of the traditional machine learning model, which fully proves that the model in this paper has good application value. The model’s evaluation uses AUC, prediction, recall, F1. These criteria prove that this model has good application value from many aspects. At present, we are trying to apply this model to more fields to improve the robustness and applicability of the model;on the other hand, we are trying to do more in-depth research on domain adaptation to enrich the model.</span>
文摘At present,further research and exploration on credit risks are being carried out in the global field,and increasingly profound modem credit risks are exposed to the bond market.This requires that we cannot ignore the impact of credit rating migration risk on bond pricing,so as to adapt to the sustainable and healthy development of the bond market under the new normal of China's economy.The innovation point of this paper is to try to analyze the pricing of Convertible bonds in China from the perspective of credit rating migration risk.Tsiveriotis and Femandes(1998)model is selected,and the credit risk in the model is assumed to be caused by the credit rating migration risk,and the credit spread is used to measure the credit rating migration risk.The research conclusion of this paper is as follows:First,it is valid to consider the risk of credit rating migration in the TF(1998)model.The market price of convertible bonds is on average 1.22% higher 1han the theoretical value of the model.In general,the theoretical value obtained from the model has little deviation from the market price,and has a good fitting degree.Second,from the Angle of credit rating,the selection of 32 samples of convertible bonds only empirical research shows that the credit rating of AA-convertible bonds average deviation rate is negative,suggest that the credit rating of AA-the phenomenon of convertible bonds value is underestimated,and AAA credit rating to AA,AA+,the average deviation rate of convertible bonds is positive,that credit rating AA(containing AA)more convertible bond value is overrated phenomenon,and the higher the credit rating of the average deviation rate of convertible bond,the greater the overvalued levels.It has certain guiding significance for participants in the convertible bond market.
