GitiHubi/deepAD

Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks - A lab we prepared for the KDD'19 Workshop on Anomaly Detection in Finance that will walk you through the detection of interpretable accounting anomalies using adversarial autoencoder neural networks. The majority of the lab content is based on Jupyter Notebook, Python and PyTorch.

36
/ 100
Emerging

This project helps finance professionals identify unusual patterns in accounting data that could signal fraud or errors. It takes in your financial transaction records and highlights suspicious entries that might be worth investigating further. It's designed for forensic accountants, auditors, and financial analysts who need to spot anomalies in large datasets.

No commits in the last 6 months.

Use this if you need to detect subtle, interpretable anomalies within your financial accounting data using advanced machine learning.

Not ideal if you're looking for a simple, off-the-shelf fraud detection software without diving into technical details or if your data isn't structured for financial analysis.

forensic-accounting financial-auditing fraud-detection risk-management financial-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

88

Forks

19

Language

Jupyter Notebook

License

Last pushed

Aug 28, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/GitiHubi/deepAD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.