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].
Demand Forecasting Tool Driving the Digital Twin of a Perishable Food Process / Lucantoni, L., Croci, S., Mazzuto, G., Ciarapica, F.E., Bevilacqua, M., Perenzoni, S.. - In: IEEE/CAA JOURNAL OF AUTOMATICA SINICA. - ISSN 2329-9274. - 12:11(2025), pp. 2356-2358. [10.1109/JAS.2025.125591]
Demand Forecasting Tool Driving the Digital Twin of a Perishable Food Process
Lucantoni L.
;Croci S.;Mazzuto G.;Ciarapica F. E.;Bevilacqua M.;
2025-01-01
Abstract
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].I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
