What is it about?
Explaining accounting anomalies that were detected by a trained autoencoder neural network. This is achieved by enhancing the popular SHapley Additive exPlanations algorithm to explain the encoded output of the autoencoder neural network. The method is tested using three synthetic and real-world datasets.
Featured Image
Photo by Scott Graham on Unsplash
Read the Original
This page is a summary of: RESHAPE: Explaining Accounting Anomalies in Financial Statement Audits by enhancing SHapley Additive exPlanations, October 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3533271.3561667.
You can read the full text:
Contributors
The following have contributed to this page
