Controllers typically don’t do the same things every day. For an avid numbers-cruncher, the variety of projects and areas of the business that require one’s attention helps make many aspects of the job interesting and enjoyable at times.
With the exception of the month-end close. We have yet to hear from a finance pro who says he or she enjoys closing the books at the end of the month.
Experienced controllers know it’s a necessary evil. But even the most stoic of bean counters say they wish they and their team members could reduce the time spent on closing.
Case in point: Bill Hanna, aka The Financial Controller, a YouTube educator with more than 200,000 followers, estimates he spends 30% of his time reconciling his company’s books for the end of the month. That’s despite the fact that Hanna relies on third-party vendors for tax compliance and payroll to help juggle all the balls in the air, and he’s a firm proponent of automating processes like accounts payable (A/P), accounts receivable (A/R) and billing, wherever and whenever possible.
Would you like to reduce the time and effort needed to close the books at your organization? An obvious solution to consider is artificial intelligence (AI).
Dare to dream: The ‘continuous’ close
“Accounting teams are measured by the time it takes to close the books,” says Aaron Harris, chief technology officer at Sage. Harris shared his thoughts in a webinar, “Real World Accounting with AI: ROI, Benefits, and Pitfalls.”
“When [finance teams] look at implementing technology, [streamlining] the close needs to be a goal,” says Harris. With automation, continuous accounting and continuous auditing, “we may soon see a day where we don’t need the month close … where all the data is current and we can trust it.”
Sage polled a range of financial and fintech professionals on AI and how they’d like to put it to use in their organizations. No surprise, making the month-end easier ranked high:
What’s your top priority for implementing AI?
- 30% – moving teams from data entry to data analysis
- 20% – streamlining month-end closing procedures
- 18% – financial reporting for forecasting
- 15% – improved A/P and A/R management
- 9% – continuous auditing
- 5% – outlier/exception reporting
- 4% – predictive cyber security
Where business leaders are right now with AI
The Sage poll also reveals how technology like automation is helping their teams now:
Which processes in your organization are currently automated?
- 43% – A/P
- 33% – payroll
- 33% – none
- 26% – A/R
- 17% – purchasing
- 16% – sales order processing
- 13% – forecasting (Chances are the number of companies using AI for forecasting is going to go up over the next 3 to 5 years. Finance pros see AI as a no-brainer for planning and analyzing data.)
When does your company plan to start utilizing AI?
- 24% – we plan to implement AI within the next 2 to 3 years
- 24% – our company already uses AI
- 16% – we have plans to explore AI this year
- 13% – we don’t intend to utilize AI
- 12% – we don’t have intentions to use AI but I’m interested in learning more about AI solutions
- 11% – we will invest in and implement AI within the next 12 months
Go to the source and ask
The more people start to use popular AI programs like OpenAI’s ChatGPT and Google’s Bard, the more likely they are to notice problems.
Here’s a common scenario: You ask for a summary on a topic. Multiple paragraphs of text come back in under five seconds including quotes and data. Click on the sources cited and you might not find the quotes or figures in the block of text.
Ask Chat or Bard to please cite the source of the mysterious info and it can’t.
One good point in ChatGPT and Bard’s favor: They quickly acknowledge any errors and apologize, which is nice. But often it either can’t or won’t explain where it pulled the bad info from. Or why.
Two years ago, the American Accounting Association put the then-latest version of ChatGPT to the test against accounting students:
“Using data from 14 countries and 186 institutions, we compare[d] ChatGPT and student performance for 28,085 questions from accounting assessments and textbook test banks. As of January 2023, ChatGPT provide[d] correct answers for 56.5% of questions and partially correct answers for an additional 9.4% of questions. When considering point values for questions, students significantly outperform ChatGPT with a 76.7% average on assessments compared to 47.5% for ChatGPT if no partial credit is awarded and 56.5% if partial credit is awarded. … [W]hen providing a reference, [ChatGPT sometimes] generates a real-looking reference that is completely fabricated … the work, and sometimes authors, don’t even exist.”
To be fair, maybe the latest version of ChatGPT can match up with human accountants better now. We decided to ask Perplexity AI, which is drawing praise from coders and fintech pros, for an honest appraisal of its abilities:
Can you handle continuous financial closes for my company?
Perplexity: Handling the closure of a company involves various financial considerations, such as the impact on employees’ 401(k) accounts, the reporting of discontinued operations in financial statements, and the potential options for filing bankruptcy. … From an accounting perspective, discontinued operations refer to parts of a company’s core business or product line that have been divested or shut down, and specific reporting rules apply under generally accepted accounting principles (GAAP) … in summary, handling continuous financial closes for a company involves ensuring accurate and complete financial reporting and may also encompass considerations related to employee benefits, accounting for discontinued operations, and potential bankruptcy proceedings.
Sounds like Perplexity confused the month-end close with shutting down a business. To clarify, we asked: Can you calculate real-time cash on hand if we give you the data?
Perplexity: Calculating real-time cash on hand involves analyzing the cash flow of a business to determine the amount of cash and cash equivalents generated or spent over a specific period.
We then hit on the right question to get an answer for this article’s title :
How much time can you save us if we use you to close the books?
Perplexity: Using Perplexity AI to assist with your month-end close process can potentially save your team around 20-40% of the time typically spent on this task. This estimate is based on the potential for streamlining and automating the financial close process, as well as the ability to provide relevant and accurate responses to queries.
