OBJECTIVE: This study aimed to build an artificial neural network to help the managers of university cafeterias to predict the number of daily meals. METHODS: This study was based on a survey of eight variables that influence the number of daily meals served by a university cafeteria. Backpropagation training algorithm was used and the results obtained by the network are compared with results of the studied series and the results estimated by simple arithmetic average. RESULTS: The proposed network follows the numerous changes that occur in the number of daily meals of the university cafeteria. In 73% of the analyzed days, the artificial neural networks method presented a greater success rate than the simple arithmetic average method. CONCLUSION: Artificial neural network predicted the number of meals better than the simple average method or than decisions made subjectively.
Food wasterfoulness; Artificial neural networks; Food services