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
Purpose: From a social and labor inclusion perspective, the article presents a digital prototype conceptualized to provide a “Diagnostic Page”, which delivers various prescribers and suppliers of support products th...Purpose: From a social and labor inclusion perspective, the article presents a digital prototype conceptualized to provide a “Diagnostic Page”, which delivers various prescribers and suppliers of support products that mitigate the problems of the respective patients. It also provides a “Patient Card Page”, where all the information about financing the respective products is placed, as well as all the documents likely to be needed for the commercial transactions to be carried out by all the parties involved. It also aims to provide a digital medium to grow a community in this niche market. In the action research methodology approach, the prototype was taken to funding competitions and conferences, where interviews and surveys were carried out, and a number of suggestions were collected on the type of platform to consider in order to respond to the concerns and needs of end users, such as patients, prescribers, suppliers and associations. Methods: The digital platform where the system is hosted uses algorithms that, on the diagnostic page, consider keywords used by patients and return a series of prescribers and suppliers of support products, in which the corresponding percentage of attenuation is taken into account and the best solution found to overcome the level of difficulty presented by the respective patients is delivered. Results and Conclusions: It is hoped that, with this platform, people with motor problems will be able to obtain their diagnosis instantly, through the algorithm implemented, and that they will immediately be provided with a series of prescribers, suppliers and support products best suited to their needs, as well as all the information or conditions necessary to purchase or finance them. On the other hand, prescribers, suppliers and associations have an online platform where they can offer their consultations, products and other support as freelancers who are part of a community.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.
文摘Purpose: From a social and labor inclusion perspective, the article presents a digital prototype conceptualized to provide a “Diagnostic Page”, which delivers various prescribers and suppliers of support products that mitigate the problems of the respective patients. It also provides a “Patient Card Page”, where all the information about financing the respective products is placed, as well as all the documents likely to be needed for the commercial transactions to be carried out by all the parties involved. It also aims to provide a digital medium to grow a community in this niche market. In the action research methodology approach, the prototype was taken to funding competitions and conferences, where interviews and surveys were carried out, and a number of suggestions were collected on the type of platform to consider in order to respond to the concerns and needs of end users, such as patients, prescribers, suppliers and associations. Methods: The digital platform where the system is hosted uses algorithms that, on the diagnostic page, consider keywords used by patients and return a series of prescribers and suppliers of support products, in which the corresponding percentage of attenuation is taken into account and the best solution found to overcome the level of difficulty presented by the respective patients is delivered. Results and Conclusions: It is hoped that, with this platform, people with motor problems will be able to obtain their diagnosis instantly, through the algorithm implemented, and that they will immediately be provided with a series of prescribers, suppliers and support products best suited to their needs, as well as all the information or conditions necessary to purchase or finance them. On the other hand, prescribers, suppliers and associations have an online platform where they can offer their consultations, products and other support as freelancers who are part of a community.
