Demand Forecasting Tool Driving the Digital Twin of a Perishable Food Process

Dear Editor, The food industry emphasizes improving demand forecasting to align production with consumer needs and reduce waste. This letter thus presents a study that integrates artificial intelligence (AI) and digital twin (DT) technologies to enhance decision-making and efficiency in food production. A data-driven DT was implemented in an Italian company for Raspberry production planning, based on a daily demand forecasting tool powered by a dynamic extreme gradient boosting (XGBoost) algorithm. The model achieved a mean absolute percentage error (MAPE) of 16.37% with 1.69 average of absolute extra working hours (AEW) and a tracking signal (TS) range of [-1.9, +4.3].