Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks
This addresses the challenge of fraud detection in financial audits by enhancing interpretability and adaptability beyond handcrafted rules, though it appears incremental in applying existing deep learning methods to this domain.
The paper tackled the problem of detecting accounting fraud by proposing adversarial autoencoder networks to learn meaningful representations of journal entries, improving interpretability and enabling unsupervised anomaly detection, with experiments on two datasets and feedback from forensic accountants supporting its effectiveness.
The detection of fraud in accounting data is a long-standing challenge in financial statement audits. Nowadays, the majority of applied techniques refer to handcrafted rules derived from known fraud scenarios. While fairly successful, these rules exhibit the drawback that they often fail to generalize beyond known fraud scenarios and fraudsters gradually find ways to circumvent them. In contrast, more advanced approaches inspired by the recent success of deep learning often lack seamless interpretability of the detected results. To overcome this challenge, we propose the application of adversarial autoencoder networks. We demonstrate that such artificial neural networks are capable of learning a semantic meaningful representation of real-world journal entries. The learned representation provides a holistic view on a given set of journal entries and significantly improves the interpretability of detected accounting anomalies. We show that such a representation combined with the networks reconstruction error can be utilized as an unsupervised and highly adaptive anomaly assessment. Experiments on two datasets and initial feedback received by forensic accountants underpinned the effectiveness of the approach.