The rise of artificial intelligence (AI) has become a topic of discussion in various fields, including professional practice. Among the professions which are expected to be significantly impacted by AI are the accounting and assurance professions.
The launch of Chat GPT in November 2022 has stirred interest and speculation about the present and future impact of AI on professional practice. AI has the potential to streamline data collection, analysis, and review, significantly impacting the field of audit. In this article, we will explore some of the ways that AI can add value to the auditing process.
Automation of Data Entry and Analysis
The traditional approach to auditing involves analysing vast amounts of structured and unstructured data. AI is already helping to automate specific tasks, such as data entry and analysis. This improves accuracy and speeds up the auditing process. AI can help generate more insights and understanding of complex data sets, which can improve the accuracy and reliability of audit reports.
The computerised analysis of accounting entries is one way AI alters auditing. AI can detect fraudulent entries and raise an alert. For example, AI has the potential to analyse a company’s transactions, flag any irregularities and produce reports detailing any fraudulent activities which may have occurred.
Review of Source Documents
AI can be applied to the review of source documents in several ways. For instance, machine learning tools allow auditors to analyse many contracts in a much shorter timeframe than is possible with a traditional manual review. For example, EY recently reported that “AI tools have been used to accurately extract information from lease contracts using pre-selected criteria in most cases – a higher level of precision than the average human reviewer is capable of. “ [Source: EY: How artificial intelligence will transform the audit”]
Financial Risk Assessment
One of the most critical areas where AI is paying significant dividends is in risk assessment. Auditors use risk assessment to determine which parts of a given client’s financial statements are in greatest danger of causing a material misstatement. The auditors focus more attention and perform more audit procedures on those areas of greatest risk. Auditors rely on their experience and professional judgment to identify the riskiest areas of the audit.
AI can also be used to identify risks that may not have been apparent in the past. For example, AI can analyse financial data and identify correlations which auditors may not have noticed. This could lead to new insights that could help auditors better understand the risks involved in a particular audit engagement.
Generation of Specific Audit Programs
Audit program development is an inevitable part of audit engagement. AI tools such as Chat GPT are already being used develop base audit programs, allowing the auditor to fine-tune the audit program to fit their specific scope and objective.
For example, Chat GPT can generate an audit program to address the risk of material misstatement in financial statements in just a few seconds. While a human still needs to review the result, the process of automatically identifying material risks will free up time for auditors to focus on adding value to the audit engagement.
We asked Chat GPT to ‘generate an audit program to address the risk of material misstatement in financial statements,’ and received the following response within a few seconds:
Sure, here is an audit program to address the risk of material misstatement in financial statements:
Planning Phase:
- Obtain an understanding of the entity’s business and industry.
- Evaluate the entity’s internal control system.
- Assess the risk of material misstatement.
- Develop an audit plan that addresses the identified risks.
Risk Assessment Phase:
- Evaluate the design and implementation of internal controls.
- Perform walkthroughs to test the effectiveness of internal controls.
- Identify significant accounts, disclosures, and assertions.
- Evaluate the risk of material misstatement for each identified area.
- Assess the likelihood and magnitude of misstatements.
Testing Phase:
- Perform substantive testing procedures to detect material misstatements.
- Test the accuracy, completeness, and validity of account balances and disclosures.
- Test the rights and obligations of assets and liabilities.
- Test the valuation and allocation of accounts.
Conclusion Phase:
- Evaluate the results of the testing procedures.
- Assess the overall risk of material misstatement.
- Determine whether the financial statements are fairly presented.
- Communicate any identified material misstatements to the appropriate level of management.
- Issue an audit report that provides an opinion on the financial statements.
Post-Audit Phase:
- Evaluate the audit process and identify any areas for improvement.
- Document the audit findings and conclusions.
- Archive the audit documentation in accordance with professional standards and legal requirements.
This audit program is designed to address the risk of material misstatement in financial statements by assessing the entity’s internal controls, performing substantive testing procedures, and communicating any identified material misstatements to the appropriate level of management.
Whilst there’s clearly nothing extraordinary in the response, the ability of Chat GPT to quickly develop an outline of an audit program suggests that within a short period of time, AI programs will be able to complete a full risk assessment based on available data. Will a human still be needed to review the ‘final’ result? Absolutely, however a process which automatically identifies material risks will free up time for auditors to focus on changes required to improve outcomes.
Client engagement and communication
One benefit of programs like ChatGPT is the ability to assist auditors in improving the quality and tone of their communication with clients. This can apply to client engagement, general communication, such as requests for information, or even specific information that needs to be conveyed to the client to improve the effectiveness of communication. These tools can provide insights into what works and what doesn’t, enabling auditors to improve the way they communicate with clients.
During the audit process, auditors may need to communicate with third parties such as creditors, debtors, and customers to verify transactions and account status. Although these communications are mostly standardized, they require considerable time and attention. Since much of this communication takes place electronically, there is potential for automation to improve efficiency. For instance, requests for verification of account balances from customers and suppliers could be automated using AI, freeing up time for auditors to focus on other important tasks.
What about the risks of using AI in audit?
The increasing use of AI in audit comes with several potential risks that need to be considered.
Firstly, there is the risk of error and bias in the data being analysed. AI algorithms rely heavily on data inputs, and if the data is incomplete, inaccurate, or biased, the results produced by the AI could also be inaccurate or biased. This could lead to incorrect conclusions being drawn from the audit, potentially damaging the reputation of the auditor, and harming the client’s business.
Additionally, the use of AI in audit could lead to a reduced level of human oversight and intervention, which could increase the risk of fraudulent activities going unnoticed. If the AI system is not properly designed or implemented, it could miss important red flags or warning signs that a human auditor might have noticed.
Another significant risk associated with the use of AI in audit is cybersecurity. AI systems which are connected to a network or the internet are vulnerable to hacking and cyber-attacks. If an attacker gains access to the AI system, they could manipulate the data inputs or alter the algorithms to produce misleading results. This could cause significant damage to the audit process and could also result in the unauthorised disclosure of sensitive client information.
As such, it is important that auditors take adequate measures to secure their AI systems and ensure that they are not vulnerable to cyber threats. This could include implementing robust authentication procedures, using encryption to protect data, and regularly updating and patching AI software to mitigate known vulnerabilities.
Already, there are concerns about security of personal data when using these tools. For example, the Italian privacy regulator has recently ordered an immediate blocking of access to ChatGPT whilst it investigates the software platform over a range of risks for privacy and cybersecurity. These issues will become more critical over time.
What’s next with AI and Audits
AI is a powerful tool that can help to make audits more efficient and cost-effective. It has also shown to be a reliable way of reducing the risk of human error. However, risks associated with replacing human oversight with automated processes must be understood and addressed proactively. Progressive accounting and audit firms are already considering how AI can be used to improve routine processes.
About the National Audits Group
As an independent auditing firm, National Audits Group provides accountants, advisors and trustees with the confidence that their audits are being managed professionally with regard to all requirements.
We are more than just auditors! Let’s get talking – call now and discuss how National Audits Group can provide cost effective solutions, to meet your operational needs and strategic objectives.
For further information, contact us directly at 1300 734 707.
Steven Watson
Managing Director, National Audits Group | www.audits.com.au
