Credit card fraudulent data is highly imbalanced, and it has presented an overwhelmingly large portion of nonfraudulent transactions and a small portion of fraudulent transactions. The measures used to judge the verac...Credit card fraudulent data is highly imbalanced, and it has presented an overwhelmingly large portion of nonfraudulent transactions and a small portion of fraudulent transactions. The measures used to judge the veracity of the detection algorithms become critical to the deployment of a model that accurately scores fraudulent transactions taking into account case imbalance, and the cost of identifying a case as genuine when, in fact, the case is a fraudulent transaction. In this paper, a new criterion to judge classification algorithms, which considers the cost of misclassification, is proposed, and several undersampling techniques are compared by this new criterion. At the same time, a weighted support vector machine (SVM) algorithm considering the financial cost of misclassification is introduced, proving to be more practical for credit card fraud detection than traditional methodologies. This weighted SVM uses transaction balances as weights for fraudulent transactions, and a uniformed weight for nonfraudulent transactions. The results show this strategy greatly improve performance of credit card fraud detection.展开更多
In order to improve the performance of support vector machine (SVM) applications in the field of credit risk evaluation, an adaptive Lq SVM model with Gauss kernel (ALqG-SVM) is proposed to evaluate credit risks. The ...In order to improve the performance of support vector machine (SVM) applications in the field of credit risk evaluation, an adaptive Lq SVM model with Gauss kernel (ALqG-SVM) is proposed to evaluate credit risks. The non-adaptive penalty of the object function is extended to (0, 2] to increase classification accuracy. To further improve the generalization performance of the proposed model, the Gauss kernel is introduced, thus the non-linear classification problem can be linearly separated in higher dimensional feature space. Two UCI credit datasets and a real life credit dataset from a US major commercial bank are used to check the efficiency of this model. Compared with other popular methods, satisfactory results are obtained through a novel method in the area of credit risk evaluation. So the new model is an excellent choice.展开更多
Traditional Folk relations of debit and credit have existed for thousands of years in Chinese society. In the rapidly develop of the context of mobile internet and social network, the borrowing that relies on the rela...Traditional Folk relations of debit and credit have existed for thousands of years in Chinese society. In the rapidly develop of the context of mobile internet and social network, the borrowing that relies on the relationship among people is not just a financial domain scope discussion topic. In the rapidly developing Chinese mobile Internet, a new anonymous mechanism which is based on interpersonal credit extension and evaluation ultimately form borrowing is continuously formed.?In this paper, the author researches and analyzes on what is relationship lending mechanism, the basic operation modes of relationship lending mechanism, a part of theoretical supporting and values.展开更多
With the development of the Internet and E commerce, enterprises can achieve global device purchasing with a good cost performance. But the credit risk is the key factor in selecting a device provider. Credit risk in...With the development of the Internet and E commerce, enterprises can achieve global device purchasing with a good cost performance. But the credit risk is the key factor in selecting a device provider. Credit risk involves many qualitative and quantitative factors. We construct a multi agent credit rating model system based on CSCW, which organically combines the people's aptitude and the capability of machines. Enterprises can use this credit rating system for forecasting and defeating the credit risk of global device purchasing.展开更多
文摘Credit card fraudulent data is highly imbalanced, and it has presented an overwhelmingly large portion of nonfraudulent transactions and a small portion of fraudulent transactions. The measures used to judge the veracity of the detection algorithms become critical to the deployment of a model that accurately scores fraudulent transactions taking into account case imbalance, and the cost of identifying a case as genuine when, in fact, the case is a fraudulent transaction. In this paper, a new criterion to judge classification algorithms, which considers the cost of misclassification, is proposed, and several undersampling techniques are compared by this new criterion. At the same time, a weighted support vector machine (SVM) algorithm considering the financial cost of misclassification is introduced, proving to be more practical for credit card fraud detection than traditional methodologies. This weighted SVM uses transaction balances as weights for fraudulent transactions, and a uniformed weight for nonfraudulent transactions. The results show this strategy greatly improve performance of credit card fraud detection.
基金The National Natural Science Foundation of China (No.70531040)the National Basic Research Program of China (973 Program) (No.2004CB720103)
文摘In order to improve the performance of support vector machine (SVM) applications in the field of credit risk evaluation, an adaptive Lq SVM model with Gauss kernel (ALqG-SVM) is proposed to evaluate credit risks. The non-adaptive penalty of the object function is extended to (0, 2] to increase classification accuracy. To further improve the generalization performance of the proposed model, the Gauss kernel is introduced, thus the non-linear classification problem can be linearly separated in higher dimensional feature space. Two UCI credit datasets and a real life credit dataset from a US major commercial bank are used to check the efficiency of this model. Compared with other popular methods, satisfactory results are obtained through a novel method in the area of credit risk evaluation. So the new model is an excellent choice.
文摘Traditional Folk relations of debit and credit have existed for thousands of years in Chinese society. In the rapidly develop of the context of mobile internet and social network, the borrowing that relies on the relationship among people is not just a financial domain scope discussion topic. In the rapidly developing Chinese mobile Internet, a new anonymous mechanism which is based on interpersonal credit extension and evaluation ultimately form borrowing is continuously formed.?In this paper, the author researches and analyzes on what is relationship lending mechanism, the basic operation modes of relationship lending mechanism, a part of theoretical supporting and values.
文摘With the development of the Internet and E commerce, enterprises can achieve global device purchasing with a good cost performance. But the credit risk is the key factor in selecting a device provider. Credit risk involves many qualitative and quantitative factors. We construct a multi agent credit rating model system based on CSCW, which organically combines the people's aptitude and the capability of machines. Enterprises can use this credit rating system for forecasting and defeating the credit risk of global device purchasing.
