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.
Reference:
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
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
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
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 .
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.