Financial statements (FS) such as Balance Sheet (BS), Income Statement (IS), and Cash-flow Statement (CS) summarize the annual financial performance of a company. FS are widely used for evaluating corporate governance, credit appraisal, risk analysis, validating taxation, and making investment decisions. Financial auditing is a complex and knowledge-intensive discipline aimed at ensuring integrity, accuracy, fairness, and the absence of material misstatement in published FS.
Given the importance of FS, there are incentives to hide, omit, or falsify information to misrepresent the true financial health of the company, for instance, to reduce tax liabilities or to increase investor confidence.
Given the complex, time-consuming, and expertise-dependent nature of auditing, auditors would benefit from an AI-assisted system that automatically detects instances of misinformation in FS and identifies likely sources of this misinformation in the financial data.
In this paper, we present unsupervised techniques to identify misinformation in FS and generate explanations regarding the financial variables that are likely sources of misinformation. Auditors can then explore in more detail the associated data sources and business processes to validate these suggestions.
A crucial feature of our approach is the use of past corpus of FS and associated audit reports to generate insights, which assist in providing valuable support. We demonstrate the efficacy of these techniques on a large corpus of 11,460 FS over 5 years and associated audit reports. This paper integrates and adds more novel contributions over previously reported research (Shinde et al., 2022; Vaishampayan et al., 2022; Pawar et al., 2023), which we have used as the foundation for our AI-assisted Auditor Assistance system.
Blogger's Review: This paper showcases the potential of AI in financial auditing by effectively identifying misinformation in financial statements through unsupervised learning techniques, aiding auditors in enhancing efficiency and ensuring financial transparency. This research provides significant technical support for future auditing practices.