ResearchSpace

Increasing the detection of minority class instances in financial statement fraud

Show simple item record

dc.contributor.author Moepya, Stephen O
dc.contributor.author Nelwamondo, Fulufhelo V
dc.contributor.author Twala, B
dc.date.accessioned 2017-10-09T07:45:10Z
dc.date.available 2017-10-09T07:45:10Z
dc.date.issued 2017-04
dc.identifier.citation Moepya, S.O., Nelwamondo, F.V. and Twala, B. 2017. Increasing the detection of minority class instances in financial statement fraud. In: Asian Conference on Intelligent Information and Database Systems, Kanazawa, Japan, 3-5 April 2017 en_US
dc.identifier.isbn 978-3-319-54429-8
dc.identifier.uri https://link.springer.com/chapter/10.1007/978-3-319-54430-4_4
dc.identifier.uri http://hdl.handle.net/10204/9643
dc.description Asian Conference on Intelligent Information and Database Systems, Kanazawa, Japan, 3-5 April 2017. Due to copyright restrictions, the attached PDF file only contains the abstract of the full text item. For access to the full text item, please consult the publisher's website. en_US
dc.description.abstract Financial statement fraud has proven to be difficult to detect without the assistance of data analytical procedures. In the fraud detection domain, minority class instances cannot be readily found using standard machine learning algorithms. Moreover, incomplete instances or features tend to be removed from investigations, which could lead to greater class imbalance. In this study, a combination of imputation, feature selection and classification is shown to increase the identification of minority samples given severely imbalanced data. en_US
dc.language.iso en en_US
dc.publisher Springer International Publishing AG en_US
dc.relation.ispartofseries Workflow;19186
dc.subject Financial statement fraud en_US
dc.subject Class imbalance en_US
dc.subject Feature selection en_US
dc.subject Imputation en_US
dc.title Increasing the detection of minority class instances in financial statement fraud en_US
dc.type Conference Presentation en_US
dc.identifier.apacitation Moepya, S. O., Nelwamondo, F. V., & Twala, B. (2017). Increasing the detection of minority class instances in financial statement fraud. Springer International Publishing AG. http://hdl.handle.net/10204/9643 en_ZA
dc.identifier.chicagocitation Moepya, Stephen O, Fulufhelo V Nelwamondo, and B Twala. "Increasing the detection of minority class instances in financial statement fraud." (2017): http://hdl.handle.net/10204/9643 en_ZA
dc.identifier.vancouvercitation Moepya SO, Nelwamondo FV, Twala B, Increasing the detection of minority class instances in financial statement fraud; Springer International Publishing AG; 2017. http://hdl.handle.net/10204/9643 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - Moepya, Stephen O AU - Nelwamondo, Fulufhelo V AU - Twala, B AB - Financial statement fraud has proven to be difficult to detect without the assistance of data analytical procedures. In the fraud detection domain, minority class instances cannot be readily found using standard machine learning algorithms. Moreover, incomplete instances or features tend to be removed from investigations, which could lead to greater class imbalance. In this study, a combination of imputation, feature selection and classification is shown to increase the identification of minority samples given severely imbalanced data. DA - 2017-04 DB - ResearchSpace DP - CSIR KW - Financial statement fraud KW - Class imbalance KW - Feature selection KW - Imputation LK - https://researchspace.csir.co.za PY - 2017 SM - 978-3-319-54429-8 T1 - Increasing the detection of minority class instances in financial statement fraud TI - Increasing the detection of minority class instances in financial statement fraud UR - http://hdl.handle.net/10204/9643 ER - en_ZA


Files in this item

Thumbnail
Name: Nelwamondo_2017_A ...
Size: 6.648Kb
Format: PDF
View/Open

This item appears in the following Collection(s)

Show simple item record