Artificial neural networks for the management of poultry industry: a simulation based on the broiler production chain

Abstract The aim of this study was to predict production indicators and determine their potential economic impact on a poultry integration system using artificial neural networks (ANN) models. Forty zootechnical parameters from broiler breeder farms, one hatchery, flocks, slaughterhouse were selected as variables. ANN models established for four output variables: “saleable hatching”, “weight at the end week 5,” “partial condemnation,” “total condemnation” analyzed in relation coefficient multiple determination (R2), correlation (R), mean error (E), squared (MSE), root square (RMSE). scenarios simulated impacts estimated. suitable simulating after validation. For incubator egg storage period are likely increase financial gains. 5” lineage (A) is important revenues. However, weight first may not have significant influence. Flock sex (female) influence rates, while chick day not. condemnation”, flock type condemnation but mortality rates impact.