In the context of the energy and climate crises, it is crucial for organizations to utilize advanced methods to reduce energy consumption and energy costs. This study explores the application of custom trained deep learning models as well as pretrained and fine-tuned “foundational” models for economically relevant forecasting tasks, specifically predicting energy demands in retail stores, which can enhance market efficiency and contribute to grid stability. We analyze a detailed electricity consumption dataset from a hypermarket in Hungary, focusing on 48-h forecasts at 15-min intervals. Our methodology includes the implementation of classical models such as ARIMA and linear regression, as well as state-of-the-art deep learning model architectures specialized in for time series prediction, as well as a foundational model previously trained on vast datasets and available under open-source license in a “zero shot prediction” as well as a “finetuning” scenario. The promising performance points to the usability of such approaches in a broad field of economically relevant prediction tasks.