AI has been heralded — and put to use — as a groundbreaking new tool that companies can use in the budgeting process. But even companies that have embraced AI are still struggling with aspects of the budgeting process in today’s complex and rapidly changing business environment. Why is that? When does it make sense to rely on AI, and when does it not? In this article, the authors describe experiments they have conducted on the use of AI in the budgeting process — and conclude that AI can and should replace human managers in tactical tasks, where data-driven decision-making leads to faster and more efficient outcomes, but that in the strategic realm, where long-term planning, market adaptability, and business foresight are critical, human involvement and insight remain indispensable.

In recent years, artificial intelligence and machine learning have been deployed as game-changers for corporate budgeting, in the hopes that they will bring unprecedented accuracy and efficiency to financial forecasting and resource allocation. For example, Amy Weaver, the CFO of Salesforce, has consistently turned to predictive AI as a strategic asset to enhance expense forecasting. At Caterpillar Inc., the senior VP of finance, Kyle Epley, leveraged machine learning to cut quarterly forecasting time from three weeks to just 30 minutes. Similarly, Dev Ahuja, the CFO of Novelis Inc., is using in-house machine learning for cash-flow forecasting and budgeting. In that context, Gartner predicted that 50% of organizations will use AI to replace “time-consuming bottom-up forecasting approaches” by 2028.