This article is an introduction to machine learning for financial forecasting, planning and analysis (FP\&A). Machine learning appears well suited to support FP\&A with the highly automated extraction of information from large amounts of data. However, because most traditional machine learning techniques focus on forecasting (prediction), we discuss the particular care that must be taken to avoid the pitfalls of using them for planning and resource allocation (causal inference). While the naive application of machine learning usually fails in this context, the recently developed double machine learning framework can address causal questions of interest. We review the current literature on machine learning in FP\&A and illustrate in a simulation study how machine learning can be used for both forecasting and planning. We also investigate how forecasting and planning improve as the number of data points increases.

In my last blog "All AI Paths Lead to the Cloud," I talked about how the FP&A challenges facing finance leaders are not going away. These issues are only compounding due to an overabundance of data and the rapid evolution of hyper-connected mobile employees, driving businesses towards the availability, scalability, and affordability that comes with putting their financial applications to the cloud. The era of simply throwing more people and resources at the challenges simply does not economically scale. Well let's think about the problem: With more people comes additional costs (headcount, manual errors, delays, etc.) For some companies this has become the status quo, meaning they are willing to assume a certain risk tolerance that results in the under-utilization of highly skilled, well-paid assets.

In my last blog "All AI Paths Lead to the Cloud," I talked about how the FP&A challenges facing finance leaders are not going away. These issues are only compounding due to an overabundance of data and the rapid evolution of hyper-connected mobile employees, driving businesses towards the availability, scalability, and affordability that comes with putting their financial applications to the cloud. The era of simply throwing more people and resources at the challenges simply does not economically scale. Well let's think about the problem: With more people comes additional costs (headcount, manual errors, delays, etc.) For some companies this has become the status quo, meaning they are willing to assume a certain risk tolerance that results in the under-utilization of highly skilled, well-paid assets.