Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311048310> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4311048310 endingPage "19" @default.
- W4311048310 startingPage "1" @default.
- W4311048310 abstract "Detecting fraud accurately in credit cards is critical as this financial sector incurs significant losses for cardholders. Nonetheless, most studies adopted standard machine learning and few incremental learning, which are inadequate for addressing credit card challenges, such as rapid data arrival, unlimited data, data sensitivity, and performance decline over time. For this purpose, we propose a chunk-based incremental feature learning approach that optimises the fraud model topology for each new chunk and keeps track of one chunk each time. The model consists of several connected sub-models, where a new sub-model is optimally created for each new chunk. To avoid the network growing indefinitely, we limit the number of sub-models. To this end, we retain the most relevant sub-models to the current chunk’s data distribution and re-combine them to create the optimal model. We evaluate our approach using two credit card datasets: the first of medium scale contains 2-day payments in 2013, and the second of considerable scale possesses 6-month payments in 2019. We split these datasets into multiple chunks to learn and test incrementally. We compare our approach with static learning methods trained with different scenarios. Moreover, we vary the number of historical sub-models to check their impact on the predictive performance." @default.
- W4311048310 created "2022-12-23" @default.
- W4311048310 creator A5026015679 @default.
- W4311048310 creator A5073738403 @default.
- W4311048310 date "2022-11-30" @default.
- W4311048310 modified "2023-09-26" @default.
- W4311048310 title "Chunk-based incremental feature learning for credit-card fraud data stream" @default.
- W4311048310 cites W1507480455 @default.
- W4311048310 cites W1973329722 @default.
- W4311048310 cites W2099419573 @default.
- W4311048310 cites W2533835508 @default.
- W4311048310 cites W2742642850 @default.
- W4311048310 cites W2756359217 @default.
- W4311048310 cites W2884755130 @default.
- W4311048310 cites W3128553169 @default.
- W4311048310 cites W3173100042 @default.
- W4311048310 cites W3162132986 @default.
- W4311048310 doi "https://doi.org/10.1080/0952813x.2022.2153277" @default.
- W4311048310 hasPublicationYear "2022" @default.
- W4311048310 type Work @default.
- W4311048310 citedByCount "0" @default.
- W4311048310 crossrefType "journal-article" @default.
- W4311048310 hasAuthorship W4311048310A5026015679 @default.
- W4311048310 hasAuthorship W4311048310A5073738403 @default.
- W4311048310 hasConcept C119857082 @default.
- W4311048310 hasConcept C121332964 @default.
- W4311048310 hasConcept C124101348 @default.
- W4311048310 hasConcept C136764020 @default.
- W4311048310 hasConcept C138885662 @default.
- W4311048310 hasConcept C145097563 @default.
- W4311048310 hasConcept C154945302 @default.
- W4311048310 hasConcept C2776401178 @default.
- W4311048310 hasConcept C2778755073 @default.
- W4311048310 hasConcept C2780747020 @default.
- W4311048310 hasConcept C2983355114 @default.
- W4311048310 hasConcept C41008148 @default.
- W4311048310 hasConcept C41895202 @default.
- W4311048310 hasConcept C60777511 @default.
- W4311048310 hasConcept C62520636 @default.
- W4311048310 hasConcept C89198739 @default.
- W4311048310 hasConceptScore W4311048310C119857082 @default.
- W4311048310 hasConceptScore W4311048310C121332964 @default.
- W4311048310 hasConceptScore W4311048310C124101348 @default.
- W4311048310 hasConceptScore W4311048310C136764020 @default.
- W4311048310 hasConceptScore W4311048310C138885662 @default.
- W4311048310 hasConceptScore W4311048310C145097563 @default.
- W4311048310 hasConceptScore W4311048310C154945302 @default.
- W4311048310 hasConceptScore W4311048310C2776401178 @default.
- W4311048310 hasConceptScore W4311048310C2778755073 @default.
- W4311048310 hasConceptScore W4311048310C2780747020 @default.
- W4311048310 hasConceptScore W4311048310C2983355114 @default.
- W4311048310 hasConceptScore W4311048310C41008148 @default.
- W4311048310 hasConceptScore W4311048310C41895202 @default.
- W4311048310 hasConceptScore W4311048310C60777511 @default.
- W4311048310 hasConceptScore W4311048310C62520636 @default.
- W4311048310 hasConceptScore W4311048310C89198739 @default.
- W4311048310 hasLocation W43110483101 @default.
- W4311048310 hasOpenAccess W4311048310 @default.
- W4311048310 hasPrimaryLocation W43110483101 @default.
- W4311048310 hasRelatedWork W2751515787 @default.
- W4311048310 hasRelatedWork W2966860114 @default.
- W4311048310 hasRelatedWork W3148119887 @default.
- W4311048310 hasRelatedWork W3185798959 @default.
- W4311048310 hasRelatedWork W4206291359 @default.
- W4311048310 hasRelatedWork W4210887036 @default.
- W4311048310 hasRelatedWork W4213059755 @default.
- W4311048310 hasRelatedWork W4312452763 @default.
- W4311048310 hasRelatedWork W4361238142 @default.
- W4311048310 hasRelatedWork W4366363614 @default.
- W4311048310 isParatext "false" @default.
- W4311048310 isRetracted "false" @default.
- W4311048310 workType "article" @default.