FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312590949> ?p ?o ?g. }

• W4312590949 endingPage "3043" @default.
• W4312590949 startingPage "3034" @default.
• W4312590949 abstract "As technology advanced and e-commerce services expanded, credit cards became one of the most popular payment methods, resulting in an increase in the volume of banking transactions. Furthermore, the significant increase in fraud requires high banking transaction costs. As a result, detecting fraudulent activities has become a fascinating topic. In this study, we consider the use of class weight-tuning hyperparameters to control the weight of fraudulent and legitimate transactions. We use Bayesian optimization in particular to optimize the hyperparameters while preserving practical issues such as unbalanced data. We propose weight-tuning as a pre-process for unbalanced data, as well as CatBoost and XGBoost to improve the performance of the LightGBM method by accounting for the voting mechanism. Finally, in order to improve performance even further, we use deep learning to fine-tune the hyperparameters, particularly our proposed weight-tuning one. We perform some experiments on real-world data to test the proposed methods. To better cover unbalanced datasets, we use recall-precision metrics in addition to the standard ROC-AUC. CatBoost, LightGBM, and XGBoost are evaluated separately using a 5-fold cross-validation method. Furthermore, the majority voting ensemble learning method is used to assess the performance of the combined algorithms. LightGBM and XGBoost achieve the best level criteria of ROC-AUC = 0.95, precision 0.79, recall 0.80, F1 score 0.79, and MCC 0.79, according to the results. By using deep learning and the Bayesian optimization method to tune the hyperparameters, we also meet the ROC-AUC = 0.94, precision = 0.80, recall = 0.82, F1 score = 0.81, and MCC = 0.81. This is a significant improvement over the cutting-edge methods we compared it to." @default.
• W4312590949 created "2023-01-05" @default.
• W4312590949 creator A5031964906 @default.
• W4312590949 creator A5055484303 @default.
• W4312590949 creator A5086084081 @default.
• W4312590949 date "2023-01-01" @default.
• W4312590949 modified "2023-10-11" @default.
• W4312590949 title "Fraud Detection in Banking Data by Machine Learning Techniques" @default.
• W4312590949 cites W2038136632 @default.
• W4312590949 cites W2230049528 @default.
• W4312590949 cites W2785637175 @default.
• W4312590949 cites W2805595195 @default.
• W4312590949 cites W2903859616 @default.
• W4312590949 cites W2960423448 @default.
• W4312590949 cites W3005048680 @default.
• W4312590949 cites W3006462240 @default.
• W4312590949 cites W3011974631 @default.
• W4312590949 cites W3023943971 @default.
• W4312590949 cites W3028852288 @default.
• W4312590949 cites W3038539283 @default.
• W4312590949 cites W3084502104 @default.
• W4312590949 cites W3084540277 @default.
• W4312590949 cites W3090328709 @default.
• W4312590949 cites W3096395571 @default.
• W4312590949 cites W3126346562 @default.
• W4312590949 cites W3126720980 @default.
• W4312590949 cites W3128812886 @default.
• W4312590949 cites W3150319634 @default.
• W4312590949 cites W3160213214 @default.
• W4312590949 cites W3164112495 @default.
• W4312590949 cites W3178824571 @default.
• W4312590949 cites W4225136133 @default.
• W4312590949 cites W4225146313 @default.
• W4312590949 cites W4283022349 @default.
• W4312590949 cites W4283209178 @default.
• W4312590949 cites W4302570227 @default.
• W4312590949 doi "https://doi.org/10.1109/access.2022.3232287" @default.
• W4312590949 hasPublicationYear "2023" @default.
• W4312590949 type Work @default.
• W4312590949 citedByCount "2" @default.
• W4312590949 countsByYear W43125909492023 @default.
• W4312590949 crossrefType "journal-article" @default.
• W4312590949 hasAuthorship W4312590949A5031964906 @default.
• W4312590949 hasAuthorship W4312590949A5055484303 @default.
• W4312590949 hasAuthorship W4312590949A5086084081 @default.
• W4312590949 hasBestOaLocation W43125909491 @default.
• W4312590949 hasConcept C10485038 @default.
• W4312590949 hasConcept C119857082 @default.
• W4312590949 hasConcept C12267149 @default.
• W4312590949 hasConcept C124101348 @default.
• W4312590949 hasConcept C154945302 @default.
• W4312590949 hasConcept C17744445 @default.
• W4312590949 hasConcept C199539241 @default.
• W4312590949 hasConcept C2778049539 @default.
• W4312590949 hasConcept C41008148 @default.
• W4312590949 hasConcept C52001869 @default.
• W4312590949 hasConcept C520049643 @default.
• W4312590949 hasConcept C75949130 @default.
• W4312590949 hasConcept C77088390 @default.
• W4312590949 hasConcept C81669768 @default.
• W4312590949 hasConcept C8642999 @default.
• W4312590949 hasConcept C94625758 @default.
• W4312590949 hasConceptScore W4312590949C10485038 @default.
• W4312590949 hasConceptScore W4312590949C119857082 @default.
• W4312590949 hasConceptScore W4312590949C12267149 @default.
• W4312590949 hasConceptScore W4312590949C124101348 @default.
• W4312590949 hasConceptScore W4312590949C154945302 @default.
• W4312590949 hasConceptScore W4312590949C17744445 @default.
• W4312590949 hasConceptScore W4312590949C199539241 @default.
• W4312590949 hasConceptScore W4312590949C2778049539 @default.
• W4312590949 hasConceptScore W4312590949C41008148 @default.
• W4312590949 hasConceptScore W4312590949C52001869 @default.
• W4312590949 hasConceptScore W4312590949C520049643 @default.
• W4312590949 hasConceptScore W4312590949C75949130 @default.
• W4312590949 hasConceptScore W4312590949C77088390 @default.
• W4312590949 hasConceptScore W4312590949C81669768 @default.
• W4312590949 hasConceptScore W4312590949C8642999 @default.
• W4312590949 hasConceptScore W4312590949C94625758 @default.
• W4312590949 hasLocation W43125909491 @default.
• W4312590949 hasOpenAccess W4312590949 @default.
• W4312590949 hasPrimaryLocation W43125909491 @default.
• W4312590949 hasRelatedWork W2200000192 @default.
• W4312590949 hasRelatedWork W2405673391 @default.
• W4312590949 hasRelatedWork W2782093256 @default.
• W4312590949 hasRelatedWork W3199608561 @default.
• W4312590949 hasRelatedWork W3209396995 @default.
• W4312590949 hasRelatedWork W3212135906 @default.
• W4312590949 hasRelatedWork W4283697347 @default.
• W4312590949 hasRelatedWork W4308415759 @default.
• W4312590949 hasRelatedWork W4312590949 @default.
• W4312590949 hasRelatedWork W4320494184 @default.
• W4312590949 hasVolume "11" @default.
• W4312590949 isParatext "false" @default.
• W4312590949 isRetracted "false" @default.
• W4312590949 workType "article" @default.