About this document

Machine Learning for Fraud Detection by David Mantuano is a document available to read on EtoBox.

This paper presents a machine learning approach to detect accounting fraud in publicly traded U.S. firms by utilizing raw accounting variables instead of traditional financial ratios. The authors address the challenges of imbalanced datasets and propose methods such as Biased Penalty Support Vector Machine and Ensemble Methods to improve detection accuracy. Empirical results demonstrate that their approach significantly outperforms existing methods in terms of balanced accuracy and computational efficiency.

Author

David Mantuano

Language

EN