A typical strategy for increasing grocery stores’ profitability is the production and commercialization of their branded products. This strategy requires production planning, which impacts the business profitability and food waste. The purpose of this study was to develop and test an artificial intelligence (AI) model to predict the demand of a small grocery store and to use this model to support the own branded product production planning to reduce food waste. Through machine learning (ML) and feature expansion techniques, it was possible to address several existing limitations in the available data from a small grocery store in Brazil. From five distinct ML techniques created to predict the store’s revenue, from which the demand is derived, the random forest algorithm was selected because of its superior accuracy. The model was tested using actual data from a small grocery store. The results demonstrate that AI techniques can enhance the production planning accuracy of food processing and promote a significant reduction in food waste while positively impacting profitability, among other fringe benefits, ultimately resulting in a more sustainable operation. The results open new possibilities for AI research to be applied to improve sustainability and reduce food waste.