Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048656210> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3048656210 endingPage "149853" @default.
- W3048656210 startingPage "149841" @default.
- W3048656210 abstract "Machine learning approaches are widely used to analyze and detect the increasingly serious problem of credit card fraud. However, typical credit card datasets present imbalanced classification situations because of severely skewed class distributions. Although researchers have proposed some strategies to deal with these imbalances, disadvantages remain. We propose an oversampling method based on variational automatic coding (VAE), combined with classic deep learning techniques, to solve this problem. The VAE method is used to generate a large amount of diverse cases from minority groups in an imbalanced dataset, which are then used to train the classification network. The proposed method is tested on an open credit card fraud dataset, which contains transactions conducted by European cardholders over two days in September 2013. Experimental results show that the VAE method performs better than synthetic minority oversampling techniques and traditional deep neural network methods. In addition, it outperforms recent oversampling methods based on generative adversarial network (GAN) models. After submitting the extended dataset to the baseline for training, the test of the VAE model performs well on indicators including precision, F-measure, accuracy and specificity. These experimental results suggest that the VAE-based oversampling method can be effectively applied to imbalanced classification problems." @default.
- W3048656210 created "2020-08-18" @default.
- W3048656210 creator A5051963490 @default.
- W3048656210 creator A5066208092 @default.
- W3048656210 creator A5070928752 @default.
- W3048656210 date "2020-01-01" @default.
- W3048656210 modified "2023-10-17" @default.
- W3048656210 title "Using Variational Auto Encoding in Credit Card Fraud Detection" @default.
- W3048656210 cites W1551909886 @default.
- W3048656210 cites W1602011302 @default.
- W3048656210 cites W1973533434 @default.
- W3048656210 cites W2032908054 @default.
- W3048656210 cites W2045049630 @default.
- W3048656210 cites W2057819225 @default.
- W3048656210 cites W2074346829 @default.
- W3048656210 cites W2096942889 @default.
- W3048656210 cites W2118978333 @default.
- W3048656210 cites W2148125134 @default.
- W3048656210 cites W2148143831 @default.
- W3048656210 cites W2164330572 @default.
- W3048656210 cites W2217007515 @default.
- W3048656210 cites W2779931100 @default.
- W3048656210 cites W2795873205 @default.
- W3048656210 cites W2803577513 @default.
- W3048656210 cites W2805595195 @default.
- W3048656210 cites W2895850111 @default.
- W3048656210 cites W2907754184 @default.
- W3048656210 cites W2919115771 @default.
- W3048656210 cites W2945876440 @default.
- W3048656210 cites W2946523705 @default.
- W3048656210 cites W2964551072 @default.
- W3048656210 cites W2968086136 @default.
- W3048656210 cites W2990772077 @default.
- W3048656210 cites W2999438024 @default.
- W3048656210 doi "https://doi.org/10.1109/access.2020.3015600" @default.
- W3048656210 hasPublicationYear "2020" @default.
- W3048656210 type Work @default.
- W3048656210 sameAs 3048656210 @default.
- W3048656210 citedByCount "28" @default.
- W3048656210 countsByYear W30486562102021 @default.
- W3048656210 countsByYear W30486562102022 @default.
- W3048656210 countsByYear W30486562102023 @default.
- W3048656210 crossrefType "journal-article" @default.
- W3048656210 hasAuthorship W3048656210A5051963490 @default.
- W3048656210 hasAuthorship W3048656210A5066208092 @default.
- W3048656210 hasAuthorship W3048656210A5070928752 @default.
- W3048656210 hasBestOaLocation W30486562101 @default.
- W3048656210 hasConcept C119857082 @default.
- W3048656210 hasConcept C124101348 @default.
- W3048656210 hasConcept C125411270 @default.
- W3048656210 hasConcept C136764020 @default.
- W3048656210 hasConcept C145097563 @default.
- W3048656210 hasConcept C153180895 @default.
- W3048656210 hasConcept C154945302 @default.
- W3048656210 hasConcept C197323446 @default.
- W3048656210 hasConcept C2776257435 @default.
- W3048656210 hasConcept C2777212361 @default.
- W3048656210 hasConcept C2780747020 @default.
- W3048656210 hasConcept C2983355114 @default.
- W3048656210 hasConcept C31258907 @default.
- W3048656210 hasConcept C41008148 @default.
- W3048656210 hasConceptScore W3048656210C119857082 @default.
- W3048656210 hasConceptScore W3048656210C124101348 @default.
- W3048656210 hasConceptScore W3048656210C125411270 @default.
- W3048656210 hasConceptScore W3048656210C136764020 @default.
- W3048656210 hasConceptScore W3048656210C145097563 @default.
- W3048656210 hasConceptScore W3048656210C153180895 @default.
- W3048656210 hasConceptScore W3048656210C154945302 @default.
- W3048656210 hasConceptScore W3048656210C197323446 @default.
- W3048656210 hasConceptScore W3048656210C2776257435 @default.
- W3048656210 hasConceptScore W3048656210C2777212361 @default.
- W3048656210 hasConceptScore W3048656210C2780747020 @default.
- W3048656210 hasConceptScore W3048656210C2983355114 @default.
- W3048656210 hasConceptScore W3048656210C31258907 @default.
- W3048656210 hasConceptScore W3048656210C41008148 @default.
- W3048656210 hasLocation W30486562101 @default.
- W3048656210 hasOpenAccess W3048656210 @default.
- W3048656210 hasPrimaryLocation W30486562101 @default.
- W3048656210 hasRelatedWork W3006426972 @default.
- W3048656210 hasRelatedWork W3037068030 @default.
- W3048656210 hasRelatedWork W3096019139 @default.
- W3048656210 hasRelatedWork W4210384905 @default.
- W3048656210 hasRelatedWork W4225149278 @default.
- W3048656210 hasRelatedWork W4225548927 @default.
- W3048656210 hasRelatedWork W4291692947 @default.
- W3048656210 hasRelatedWork W4312373044 @default.
- W3048656210 hasRelatedWork W4382680690 @default.
- W3048656210 hasRelatedWork W4385195734 @default.
- W3048656210 hasVolume "8" @default.
- W3048656210 isParatext "false" @default.
- W3048656210 isRetracted "false" @default.
- W3048656210 magId "3048656210" @default.
- W3048656210 workType "article" @default.