Abstract
This chapter studies the potential of improving business forecasting with the help of artificial intelligence, more precisely TimeGPT, a generative pre-trained transformer for time series. The chapter emphasizes the practical points of view, including computational efficiency, scalability, and challenges of roll-out from the point of view of explainability. Results from two cases of business forecasting that include revenue forecasting for an IT company and cost forecasting for a state-owned company are presented and the results are comparatively analyzed against more traditional forecasting methods utilized for the same purpose. This chapter contributes to the literature on using AI in business forecasting by providing comparative empirical studies that highlight the potential of these new forecasting opportunities and to practice by showcasing real-world experiences.

This publication has 15 references indexed in Scilit: