Artificial Neural Networks to Predict Egg-Production Traits in Commercial Laying Breeder Hens

In recent years, egg production has had an intense growth in Brazil, and Brazilian consumption per capita significantly increased the last decade. To reduce sanitary financial risks, decisions regarding health status of flock must be made based on objective criteria. Our aim was to determine main “input” variables for prediction performance commercial laying breeder flocks using ANN model. The software NeuroShellClassifier NeuroShell Predictor were used build ANN. A total 26 egg-production traits selected as input eight output variables. database 44,120 Excel cells generated. For training validation models, 74.9% 25.1% data used, respectively. accuracy models calculated compared analysis coefficient multiple determination (R2), mean squared error (MSE), assessment uniform scatter residual plots. outputs “weekly production,” incubated egg,”, “accumulated egg,” “viability” showed R2 greater than 0.8. Other yielded values lower predicts adequately breeders hens. method is option management industry, providing estimates relative contribution each variable outputs.