Continual Learning for Unsupervised Anomaly Detection in Continuous Auditing of Financial Accounting Data

TL;DR

This paper introduces a continual learning framework for unsupervised anomaly detection in real-time financial audit data, addressing distribution shifts and incremental data streams to improve detection accuracy.

Contribution

It presents a novel continual learning approach tailored for streaming audit data, overcoming challenges of knowledge interference and data distribution changes.

Findings

Reduces false positives in anomaly detection.

Decreases false negatives in continuous auditing.

Effective on real-world financial datasets.

Abstract

International audit standards require the direct assessment of a financial statement's underlying accounting journal entries. Driven by advances in artificial intelligence, deep-learning inspired audit techniques emerged to examine vast quantities of journal entry data. However, in regular audits, most of the proposed methods are applied to learn from a comparably stationary journal entry population, e.g., of a financial quarter or year. Ignoring situations where audit relevant distribution changes are not evident in the training data or become incrementally available over time. In contrast, in continuous auditing, deep-learning models are continually trained on a stream of recorded journal entries, e.g., of the last hour. Resulting in situations where previous knowledge interferes with new information and will be entirely overwritten. This work proposes a continual anomaly detection framework to overcome both challenges and designed to learn from a stream of journal entry data experiences. The framework is evaluated based on deliberately designed audit scenarios and two real-world datasets. Our experimental results provide initial evidence that such a learning scheme offers the ability to reduce false-positive alerts and false-negative decisions.