Multi-view Contrastive Self-Supervised Learning of Accounting Data Representations for Downstream Audit Tasks

TL;DR

This paper introduces a contrastive self-supervised learning framework that creates versatile, interpretable accounting data representations, enhancing efficiency across multiple audit tasks like anomaly detection and sampling.

Contribution

It proposes a novel multi-purpose self-supervised learning approach tailored for accounting data, addressing audit constraints and improving task transferability.

Findings

Improves efficiency of audit tasks using learned representations

Enables transfer of representations to multiple downstream tasks

Provides interpretable and rich data representations

Abstract

International audit standards require the direct assessment of a financial statement's underlying accounting transactions, referred to as journal entries. Recently, driven by the advances in artificial intelligence, deep learning inspired audit techniques have emerged in the field of auditing vast quantities of journal entry data. Nowadays, the majority of such methods rely on a set of specialized models, each trained for a particular audit task. At the same time, when conducting a financial statement audit, audit teams are confronted with (i) challenging time-budget constraints, (ii) extensive documentation obligations, and (iii) strict model interpretability requirements. As a result, auditors prefer to harness only a single preferably `multi-purpose' model throughout an audit engagement. We propose a contrastive self-supervised learning framework designed to learn audit task invariant accounting data representations to meet this requirement. The framework encompasses deliberate interacting data augmentation policies that utilize the attribute characteristics of journal entry data. We evaluate the framework on two real-world datasets of city payments and transfer the learned representations to three downstream audit tasks: anomaly detection, audit sampling, and audit documentation. Our experimental results provide empirical evidence that the proposed framework offers the ability to increase the efficiency of audits by learning rich and interpretable `multi-task' representations.