AutoAudit: Mining Accounting and Time-Evolving Graphs

TL;DR

AutoAudit is a system designed to detect money laundering, identify suspicious periods, and prioritize accounts in large-scale, time-evolving accounting graphs, offering high accuracy, interpretability, and scalability for auditors.

Contribution

The paper introduces AutoAudit, a novel system that effectively detects money laundering, highlights suspicious graph regions, and uncovers patterns, with proven high accuracy and scalability.

Findings

Detects nearly 100% of money laundering transactions

Identifies the most suspicious periods in accounting graphs

Scales linearly to large datasets

Abstract

How can we spot money laundering in large-scale graph-like accounting datasets? How to identify the most suspicious period in a time-evolving accounting graph? What kind of accounts and events should practitioners prioritize under time constraints? To tackle these crucial challenges in accounting and auditing tasks, we propose a flexible system called AutoAudit, which can be valuable for auditors and risk management professionals. To sum up, there are four major advantages of the proposed system: (a) "Smurfing" Detection, spots nearly 100% of injected money laundering transactions automatically in real-world datasets. (b) Attention Routing, attends to the most suspicious part of time-evolving graphs and provides an intuitive interpretation. (c) Insight Discovery, identifies similar month-pair patterns proved by "success stories" and patterns following Power Laws in log-logistic scales. (d) Scalability and Generality, ensures AutoAudit scales linearly and can be easily extended to other real-world graph datasets. Experiments on various real-world datasets illustrate the effectiveness of our method. To facilitate reproducibility and accessibility, we make the code, figure, and results public at https://github.com/mengchillee/AutoAudit.