Learning sampling in financial statement audits using vector quantised variational autoencoder neural networks

Abstract

The audit of financial statements is designed to collect reasonable assurance that an issued statement is free from material misstatement ('true and fair presentation'). International audit standards require the assessment of a statements' underlying accounting relevant transactions referred to as 'journal entries' to detect potential misstatements. To efficiently audit the increasing quantities of such journal entries, auditors regularly conduct an 'audit sampling' i.e. a sample-based assessment of a subset of these journal entries. However, the task of audit sampling is often conducted early in the overall audit process, where the auditor might not be aware of all generative factors and their dynamics that resulted in the journal entries in-scope of the audit. To overcome this challenge, we propose the use of a Vector Quantised-Variational Autoencoder (VQ-VAE) neural networks to learn a representation of journal entries able to provide a comprehensive 'audit sampling' to the auditor. We demonstrate, based on two real-world city payment datasets, that such artificial neural networks are capable of learning a quantised representation of accounting data. We show that the learned quantisation uncovers (i) the latent factors of variation and (ii) can be utilised as a highly representative audit sample in financial statement audits.