“…Also, in order to detect COVID-19, Kandati et al [12] proposed a novel hybrid algorithm named the genetic clustered FL (Genetic CFL) and proved that the Genetic CFL method is superior to the traditional AI method. In the financial field, Tian et al [13] established a federated XGBoost model to predict credit card defaults in order to reduce the occurrence of credit card defaults, and they proposed an optional split extraction model for unbalanced datasets. In the research field of credit-scoring models, He et al [14] proposed a decentralized multi-party method based on logistic regression to implement multi-party collaborative model training in order to use multi-source information for credit scoring while ensuring data privacy.…”
Section: Federated Learning and Its Applicationsmentioning
confidence: 99%
“…Step 3: Each bank client uploads the encrypted parameters to the computing server, and the computing server decrypts and calculates the global parameters using Formulas ( 11)- (13).…”
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.
“…Also, in order to detect COVID-19, Kandati et al [12] proposed a novel hybrid algorithm named the genetic clustered FL (Genetic CFL) and proved that the Genetic CFL method is superior to the traditional AI method. In the financial field, Tian et al [13] established a federated XGBoost model to predict credit card defaults in order to reduce the occurrence of credit card defaults, and they proposed an optional split extraction model for unbalanced datasets. In the research field of credit-scoring models, He et al [14] proposed a decentralized multi-party method based on logistic regression to implement multi-party collaborative model training in order to use multi-source information for credit scoring while ensuring data privacy.…”
Section: Federated Learning and Its Applicationsmentioning
confidence: 99%
“…Step 3: Each bank client uploads the encrypted parameters to the computing server, and the computing server decrypts and calculates the global parameters using Formulas ( 11)- (13).…”
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.
“…[9] Boosting-type algorithms attempt to decrease the deviation of weak classifiers, develop specific approaches in the model process, give more weight to the samples with the highest error rate, and then integrate each basic model to generate the final judgment. The XGBoost [34], GBDT [35], and AdaBoost [36] techniques are considered boosting algorithms [37]. Bagging algorithms primarily employ several sub-sample sets after sampling to create various weak classifiers and combine the classifiers using the ensemble technique to provide the prediction outcomes [38].…”
One of the most common cybercrimes that people encounter is credit card fraud. Systems for identifying fraudulent transactions that are based on intelligent machine learning are particularly successful in real-world situations. Nevertheless, when creating these systems, machine learning algorithms face the issue of imbalanced data or an unbalanced distribution of classes. Because of this, balancing the dataset becomes a crucial sub-task. A review of cutting-edge methods highlights the necessity for a thorough assessment of class imbalance management techniques in order to create a smart and effective system to identify fraudulent transactions. The goal of the current study is to compare several strategies for dealing with class imbalance. Therefore, the present study compares the performance of our novel K-CGAN method with SMOTE, B-SMOTE, and ADASYN in terms of Recall, F1-score, Accuracy, and Precision. The result shows that novel K-CGANs generated high quality test dataset and performs better as compared to other resampling techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.