This research presents a data-driven forecasting framework for coffee retail operations to predict sales demand and identify peak demand periods across multiple store locations. The study applies time-series forecasting techniques, including baseline models and Gradient Boosting regression, to predict daily revenue and hourly demand. The model achieves high forecasting accuracy and improves operational planning. An interactive Streamlit dashboard is used to support real-time decision-making.
Kundan Kumar Singh (Mon,) studied this question.